Sage Journals: Discover world-class research

Abstract

Background

Artificial intelligence (AI) has rapidly gained momentum in the field of orthopaedics, with an increasing number of systematic reviews and meta-analyses providing synthesised evidence. However, most studies have focused on individual subspecialties or specific applications, and a comprehensive overview across the discipline is lacking.

Aim

The aim of this study is to chart publication trends and geographical distribution, classify clinical and anatomical focus, and map AI methodologies and applications in orthopaedic settings, thereby highlighting research opportunities in underexplored areas.

Methods

We conducted a scoping review of freely accessible systematic reviews with and without meta-analysis across PubMed, Web of Science and Scopus databases from year 2015 up to July 2025 that evaluated the use of AI in orthopaedics. Data were extracted on publication characteristics, geographical origin, orthopaedic subspecialty focus, anatomical region, AI methodologies, data modalities, and application types. The methodological quality of the included reviews was appraised using the A Measurement Tool to Assess Systematic Reviews-2 (AMSTAR-2). Descriptive trends were summarised, and associations between variables were analysed using R software.

Results

We identified 183 eligible systematic reviews published in the last 10 years, with an exponential increase in publications over the past 5 years. Most reviews concentrated on fractures, arthroplasty, and surgery-related studies, particularly in the spine, knee, and hip. Imaging datasets predominated, with deep learning most frequently applied to radiological tasks, while machine learning methods were more common in structured clinical data applications. Notable gaps remain in underrepresented anatomical regions and in underexplored applications such as prescriptive modelling.

Conclusion

Our review highlights that while there is rapid growth in AI research across orthopaedics, certain clinical domains remain underexplored. These gaps represent opportunities for future work to align AI methods with clinical needs. By addressing these areas, AI has the potential to effectively support orthopaedic care and improve patient outcomes.

Keywords

artificial intelligence orthopaedics systematic reviews

Introduction

Artificial intelligence (AI) has emerged as one of the most significant technological innovations in healthcare, offering new possibilities for improving diagnostic accuracy, optimising treatment planning, predicting patient outcomes, and personalising patient care.¹ The rise in AI application in healthcare is exerting prominent impact, not only in potentially enhancing clinical decision-making while reducing human error, but also improving efficiency of healthcare delivery to the patients.² In orthopaedics, AI applications have expanded rapidly in recent years, encompassing image-based diagnosis, prognostic modelling, surgical planning and navigation, rehabilitation monitoring, and even decision support systems.³

The resurgence of interest towards the use of AI in orthopaedics has resulted in an increase in the number of published systematic reviews and meta-analyses. These studies are important to consolidate current available knowledge, assess the reliability of evidence and understand the limitations of AI application in orthopaedic settings. While these studies provide clinicians and researchers with synthesised evidence and diverse perspective, the large number of literature and diversity of these systematic reviews and meta-analyses may present a challenge for clinicians and researchers in fully understanding the research landscape in this field. Previous systematic reviews typically focus on individual subspecialties or specific applications of AI (e.g., fracture detection, joint arthroplasty, or outcome prediction); and no study has comprehensively mapped the breadth of AI research across the entire orthopaedic discipline. Significant gaps are still present in the reporting of the trend of AI use in orthopaedics especially across anatomical regions, clinical domains and types of applications for which the technology is used. Clarifying the relationship between orthopaedic focus, data modalities, AI methodologies, and clinical applications can provide important insights into how the AI application in the field has evolved and where it should progress next.

The objective of this scoping review is to identify and summarise published systematic reviews and meta-analyses that examine the use of AI in orthopaedics. Specifically, we aim to chart publication trends and geographical distribution, classify clinical and anatomical focus, and also map AI methodologies and applications in orthopaedic settings. By providing a structured overview of this emerging body of evidence, our review highlights current priorities, underexplored domains, and guide future directions for AI research in orthopaedics.

Materials and methods

Search strategy

The search and selection process were conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) (Figure 1). A search strategy was formulated and executed in three electronic databases (PubMed, Web of Science (WoS) and Scopus) from 1 January 2015 to 23 July 2025. Filters were applied in each database to retrieve reviews only: Systematic Review & Meta-analysis filters in PubMed; Review Article filter in WoS and Scopus. For accessibility reasons, we limited searches to English-language articles and to Free Full Text in PubMed or Open Access (Gold, Gold-Hybrid) in WoS and Scopus.

The search strategy combined free-text keywords for orthopaedics, systematic reviews/meta-analyses, and artificial intelligence. Boolean operators, truncation, and field tags were adapted for each database. A detailed summary of the search queries in each database is shown in Table 1.

Table 1.

Summary of search queries using selected keywords.

Database	PubMed	Web of science	Scopus
Search syntax	(orthopaedic[tiab] OR orthopedic[tiab] OR bone[tiab] OR joint[tiab] OR musculoskeletal[tiab] OR spine[tiab] OR knee[tiab] OR hip[tiab] OR shoulder[tiab] OR fracture[tiab] OR trauma[tiab] OR skeletal[tiab] OR ligament[tiab] OR cartilage[tiab])	TS=((orthopaedic* OR orthopedic* OR bone OR joint OR musculoskeletal OR spine OR knee OR hip OR shoulder OR fracture OR trauma OR skeletal OR ligament OR cartilage)	TITLE-ABS-KEY ((orthopaedic* OR orthopedic* OR bone OR joint OR musculoskeletal OR spine OR knee OR hip OR shoulder OR fracture OR trauma OR skeletal OR ligament OR cartilage)
	AND (“systematic review”[tiab] OR “meta-analysis”[tiab] OR “evidence synthesis”[tiab])	AND (“systematic review” OR “meta-analysis” OR “evidence synthesis”)	AND (“systematic review” OR “meta-analysis” OR “evidence synthesis”)
	AND (“artificial intelligence”[tiab] OR “machine learning”[tiab] OR “deep learning”[tiab] OR “neural network”[tiab] OR “natural language processing”[tiab] OR AI[tiab] OR ML[tiab] OR DL[tiab] OR algorithm[tiab] OR automation[tiab] OR “computer vision”[tiab])	AND (“artificial intelligence” OR “machine learning” OR “deep learning” OR “neural network” OR “natural language processing” OR AI OR ML OR DL OR algorithm OR automation OR “computer vision”))	AND (“artificial intelligence” OR “machine learning” OR “deep learning” OR “neural network” OR “natural language processing” OR AI OR ML OR DL OR algorithm OR automation OR “computer vision”))

Inclusion and exclusion criteria

The PCC framework (Population, Concept and Context) recommended by the Joanna Briggs Institute (JBI) for scoping review was used a guide to identify the main concepts and eligibility criteria for our scoping review.⁴ This review focuses on orthopaedic conditions concerning human population in clinical settings (musculoskeletal injuries, degenerative diseases, trauma, rehabilitation, oncology, etc.). The primary concept of this review are artificial intelligence (AI) applications, including machine learning, deep learning, radiomics, natural language processing, and other computational methods, as reported in systematic reviews and/or meta-analyses. Published reviews conducted in any geographical region, in any clinical or research setting related to orthopaedics were considered.

The inclusion criteria of the current study are as follows: (1) systematic reviews and meta-analyses that explicitly report systematic search methods (search strategy, inclusion criteria) and that synthesize primary studies, (2) reviews that evaluate or report on AI applications in orthopaedics (e.g., diagnosis, prognosis, image analysis, surgical planning/assistance, treatment assistance, etc.), (3) patients with musculoskeletal/orthopaedic conditions (excluding dental/orthodontic settings), (4) only published systematic review articles in English language were considered.

The exclusion criteria are as follows: (1) scoping reviews, narrative reviews, editorials, commentaries, primary studies, conference abstracts without full systematic review text, (2) reviews on non-orthopaedic specialties, (3) reviews without AI use or integration, (4) publications not available in English.

Data extraction

A title-and-abstract and full-text screening was performed by experienced reviewers based on the search strategy and eligibility criteria. We documented reasons for exclusion and present the selection process using a PRISMA flow diagram (Figure 1).

Figure 1.

PRISMA flow diagram of the study selection process.

The following data were extracted for each included review: (i) bibliography details (first author, title, year of publication, region of corresponding author); (ii) orthopaedic focus; (iii) anatomical region(s) of the body; (iv) AI application(s); (v) type of AI used; (vi) data modalities; and (vii) number of primary studies reviewed.

Methodological quality assessment

The methodological quality of the included reviews was appraised using the A Measurement Tool to Assess Systematic Reviews-2 (AMSTAR-2).⁵ To interpret weakness detected in each of the critical domains in AMSTAR-2, a quantitative score was calculated by assigning 1 point for ‘yes’, 0.5 points for ‘partial yes’, and 0 points for ‘no’, resulting in a maximum of 7 points for systematic reviews with meta-analyses and 5 points for those without.

Statistical analysis

Descriptive analysis was done to explore the trend and pattern of our dataset. Frequencies were used for categorical variables, while measures of central tendency and dispersion (mean, median, standard deviation, and interquartile range, where appropriate) were calculated for continuous variables.

To explore associations between categorical variables, we conducted cross-tabulation analyses using Pearson’s Chi-square tests. Strength and direction of relationships between continuous variables were assessed using Spearman’s rank correlation coefficient as the data did not fully meet the assumptions of normality required for Pearson’s correlation. Correlation coefficients were interpreted according to conventional thresholds (e.g., 0.1–0.3 = weak, 0.3–0.5 = moderate, >0.5 = strong).

For comparisons of continuous variables across more than two independent groups, we employed the Kruskal–Wallis H test. When significant differences were detected, Dunn’s post-hoc pairwise tests with Bonferroni correction were conducted to identify specific group differences while adjusting for multiple testing.

All statistical analyses were conducted using R software, version 4.5.1. A two-tailed p-value of <0.05 was considered statistically significant.

Results

Study selection

Our search strategy initially identified a total of 8461 records (PubMed = 1659; Web of Science = 2547; Scopus = 4255). After applying filters for publication year (2015–2025), article type (systematic review or meta-analysis), and language (English), a total of 4700 records remained. Following deduplication across the databases, 2999 unique records were retained for screening. Subsequently, 2693 studies were excluded after title and abstract screening as they did not fulfil the selection criteria. The remaining 306 records were sought for full-text retrieval, of which 67 reports were not retrievable due to access limitations. The remaining 239 articles were assessed for full-text review, and 56 were further excluded due to the following reasons: (i) the studies are not specific to orthopaedic settings (n = 18), (ii) the studies do not have AI integration or component (n = 16), (iii) the studies are not systematic review or meta-analysis (n = 21), and (iv) the studies are not published in the English language (n = 1). Ultimately, a total of 183 reviews were considered for the present review. The extracted data from all systematic reviews with and without meta-analysis included in the present study along with their respective methodological quality assessment results (AMSTAR-2 score) are summarised in Table 2.

Table 2.

Extracted data and methodological quality of included systematic reviews. ML – Machine learning, DL – Deep learning, NLP – Natural language processing.

Author, year	Country/Region	Orthopaedic focus	Anatomical region	AI application	AI type	Data type	No. of studies reviewed	AMSTAR-2 score
Systematic reviews without meta-analysis
Alam et al. (2025)⁶	USA	Rehabilitation	Upper limb	Treatment assistance	ML, DL	Sensor data	44	4
Allam et al. (2023)⁷	USA	Osteoporosis/Fracture	Spine	Prognosis	ML, DL	Medical imaging	6	2.5
Amran et al. (2023)⁸	Malaysia	Scoliosis	Spine	Diagnosis	ML, DL	Medical imaging	17	2.5
Amrani El Yaakoubi et al. (2023)⁹	Ireland	Kinematics	Lower limb	Biomechanical analysis	DL	Sensor data	16	4.5
Angthong et al. (2023)¹⁰	Thailand	Trauma	General	Prognosis	ML, DL, NLP	Clinical data	8	1.5
Bacco et al. (2022)¹¹	China	Back pain	Spine	Diagnosis, prognosis	NLP	Text/Unstructured	16	3
Batailler et al. (2021)¹²	France	Arthroplasty	Knee	Prognosis	ML	Clinical data	48	4
Batailler et al. (2022)¹³	France	Arthroplasty	Knee	Diagnosis, prognosis, surgical assistance	ML, DL, NLP	Clinical data, medical imaging	132	2.5
Baur et al. (2022)¹⁴	Germany	Trauma	General	Diagnosis, prognosis	ML	Clinical data	36	1
Binvignat et al. (2022)¹⁵	France	Osteoarthritis	General	Diagnosis, prognosis	ML, DL	Clinical data, medical imaging	46	3
Blackman et al. (2025)¹⁶	Sweden	Injuries	Knee	Prognosis	ML	Clinical data	9	4
Bonaldi et al. (2023)¹⁷	Italy	General	General	Image analysis	DL	Medical imaging	101	0.5
Castagno et al. (2024)¹⁸	UK	Osteoarthritis	General	Prognosis	ML, DL	Clinical data, medical imaging	39	4.5
Cha et al. (2022)¹⁹	Korea	Fracture	Hip	Diagnosis	ML, DL	Medical imaging	14	2
Cha et al. (2023)²⁰	Korea	Fracture	Hip	Prognosis	ML, DL	Medical imaging	7	2
Chavosh Nejad et al. (2024)²¹	Denmark	Arthroplasty	Hip, knee	Prognosis	ML	Clinical data	28	1.5
Cheng et al. (2025)²²	New Zealand	Kinematics	Lower limb	Biomechanical analysis	DL	Sensor data	20	4
Chong et al. (2023)²³	Hong Kong	Arthroplasty	Knee	Prognosis	ML	Clinical data	11	3.5
Clement et al., 2024)²⁴	UK	Arthroplasty	Hip	Prognosis	ML	Clinical data	7	5
Corban et al. (2021)²⁵	Canada	Injuries	Knee	Diagnosis, prognosis, treatment assistance	ML, DL	Clinical data, medical imaging	19	2
Cruz et al. (2018)²⁶	Brazil	Osteoporosis	General	Diagnosis	ML, DL	Clinical data, medical imaging	25	1.5
D’Antoni et al. (2021)²⁷	Italy	Back pain	Spine	Diagnosis	ML, DL	Medical imaging	76	3
D'Antoni et al. (2022)²⁸	Italy	Back pain	Spine	Diagnosis	ML, DL	Clinical data, medical imaging	57	2.5
Dhumale et al. (2025)²⁹	India	Musculoskeletal disorders	General	Diagnosis	ML, DL	Clinical data, medical imaging	11	3.5
Dietz et al. (2022)³⁰	USA	Injuries	Spine	Diagnosis, prognosis, treatment assistance	ML, DL	Clinical data, medical imaging	13	2.5
Dijkstra et al. (2024)³¹	Netherlands	Trauma	General	Prognosis	ML	Clinical data	45	4
Diomatari et al. (2025)³²	UK	Musculoskeletal disorders	General	Prognosis	ML	Clinical data	12	5
Donisi et al. (2022)³³	Italy	Ergonomics	General	Diagnosis, prognosis	ML, DL	Sensor data	25	1.5
Du et al. (2025)³⁴	China	Degenerative disease	Spine	Diagnosis	ML, DL	Medical imaging	11	5
Eckart et al. (2025)³⁵	USA	Kinematics	General	Prognosis	ML	Sensor data	75	1
Entezari et al. (2023)³⁶	Canada	Arthroplasty	Hip, knee	Prognosis	ML	Clinical data	25	3.5
Faiella et al. (2022)³⁷	Italy	Oncology	Spine	Diagnosis	ML, DL	Clinical data, medical imaging	13	3
Farrow et al. (2025)³⁸	UK	Trauma	General	Others	NLP	Text/Unstructured	36	5
Getzmann et al. (2024)³⁹	Italy	General	General	Image analysis	ML, DL	Medical imaging	16	3
Ghanem et al. (2023)⁴⁰	USA	Surgery	Spine	Prognosis	ML, DL	Not stated	60	3
Giaccone et al. (2025)⁴¹	Italy	Degenerative disease	Spine	Prognosis, treatment assistance	ML, DL	Clinical data, medical imaging	25	5
Gill et al. (2025)⁴²	UK	Injuries	Spine	Diagnosis, prognosis	ML, DL	Clinical data, medical imaging	14	5
Gitto et al. (2021)⁴³	Italy	Oncology	General	Image analysis	ML	Radiomics data	49	2
Gitto et al. (2024)⁴⁴	Italy	Oncology	General	Image analysis	ML	Radiomics data	55	3
Goedmakers et al. (2022)⁴⁵	Netherlands	Cervical spine disease	Spine	Image analysis	ML, DL	Medical imaging	51	4
González-Castro et al. (2024)⁴⁶	Spain	Fall	General	Prognosis	ML, DL	Clinical data, sensor data	22	4.5
Groot et al. (2021)⁴⁷	USA	Surgery	General	Prognosis	ML	Clinical data	18	5
Groot et al. (2022)⁴⁸	USA	Surgery	General	Prognosis	ML	Not stated	59	5
Gupta, Kingston, et al. (2023)⁴⁹	USA	Surgery	Foot and ankle	Prognosis, surgical assistance	ML, DL	Clinical data, medical imaging	31	3
Gupta, Haeberle, et al. (2023)⁵⁰	USA	Surgery	Shoulder	Prognosis, surgical assistance	ML, DL	Clinical data, medical imaging	45	2
Gurchiek et al. (2019)⁵¹	USA	Kinematics	General	Biomechanical analysis	ML, DL	Sensor data	46	2
Han et al. (2024)⁵²	China	Surgery	Spine	Surgical assistance	ML, DL	Clinical data, medical imaging	91	1.5
He et al. (2024)⁵³	China	Osteoporosis	General	Diagnosis	ML, DL	Clinical data, medical imaging	40	1.5
Herman et al. (2024)⁵⁴	Malaysia	Injuries	Knee	Diagnosis	ML, DL	Medical imaging	22	1.5
Hinterwimmer et al. (2022)⁵⁵	Germany	Arthroplasty	Knee	Prognosis	ML	Clinical data	19	1.5
Hu & Qu (2016)⁵⁶	China	Fall	General	Prognosis	ML	Sensor data	23	1
Hu et al. (2023)⁵⁷	China	Fracture	Hip	Prognosis	ML, DL	Clinical data, medical imaging	36	4
Hussein & Khan (2023)⁵⁸	Qatar	Kyphosis	Spine	Prognosis	ML, DL	Clinical data	9	4
Karimi et al. (2024)⁵⁹	USA	Arthroplasty	Shoulder	Prognosis	ML	Clinical data	12	3
Khan et al. (2021)⁶⁰	Norway	Kinematics	Lower limb	Biomechanical analysis	ML	Sensor data	21	2
Khan & Chaurasia (2025)⁶¹	Qatar	Surgery	Spine	Surgical assistance	ML, DL	Clinical data	3	1
Kim et al. (2024)⁶²	Korea	General	Spine	Image analysis	ML, DL	Medical imaging	12	1.5
Kokkotis et al. (2022)⁶³	Greece	Kinematics	Knee	Prognosis	ML	Sensor data	6	4
Kolaghassi et al. (2021)⁶⁴	UK	Kinematics	Lower limb	Biomechanical analysis	ML, DL	Sensor data	41	1.5
Krishnakumar et al. (2024)⁶⁵	Netherlands	Rehabilitation	Knee	Treatment assistance	ML, DL	Sensor data	71	5
Kurmis & Ianunzio (2022)⁶⁶	Australia	Surgery	General	Diagnosis, prognosis, surgical assistance	ML, DL	Clinical data, medical imaging	52	1.5
Kurmis (2023)⁶⁷	Australia	Arthroplasty	Knee	Diagnosis, prognosis, surgical assistance	ML, DL	Clinical data, medical imaging	57	2.5
Kutbi (2024)⁶⁸	Saudi Arabia	Fracture	General	Diagnosis	DL	Medical imaging	19	2
Langenberger et al. (2022)⁶⁹	Germany	Arthroplasty	Hip, knee	Prognosis	ML	Clinical data	6	5
Langerhuizen et al. (2019)⁷⁰	Australia	Fracture	General	Diagnosis	ML, DL	Medical imaging	10	4
Lans et al. (2023)⁷¹	USA	General	General	Prognosis	ML	Clinical data	59	4.5
Lee & Lee (2022)⁷²	Korea	Kinematics	General	Biomechanical analysis	ML, DL	Sensor data	48	2
Lee et al. (2024)⁷³	Korea	General	Spine	Diagnosis, image analysis	ML, DL, NLP	Clinical data, medical imaging	134	1
Lemel et al. (2025)⁷⁴	USA	Surgery	Spine	Prognosis	ML	Clinical data	35	4
Lezak et al. (2024)⁷⁵	USA	Leg length discrepancy	Lower limb	Diagnosis, image analysis	ML, DL	Medical imaging	6	2.5
Liawrungrueang et al. (2024)⁷⁶	Thailand	Surgery	Spine	Surgical assistance	ML, DL	Medical imaging	11	4
Liawrungrueang (Cholamjiak (et al. (2025)⁷⁷	Thailand	Fracture	Spine	Diagnosis	ML, DL	Medical imaging	11	4
Liawrungrueang, Cho, et al. (2025)⁷⁸	Thailand	OPLL	Spine	Diagnosis	ML, DL	Medical imaging	11	4
Liu et al. (2024)⁷⁹	Singapore	Osteoporosis	General	Diagnosis	ML, DL	Medical imaging	31	3
Longo et al. (2022)⁸⁰	Italy	Kinematics	Shoulder	Biomechanical analysis	Hybrid/Other	Sensor data	11	3.5
Longo et al. (2024)⁸¹	Italy	Arthroplasty	Knee	Prognosis	ML, DL	Clinical data, medical imaging	49	4
Longo Marino et al. (2025)⁸²	Sweden	Musculoskeletal disorders	Shoulder	Diagnosis, prognosis, surgical assistance	ML, DL	Clinical data, medical imaging	33	3.5
Longo, Lalli, et al. (2025)⁸³	Sweden	General	General	Image analysis	ML, DL	Medical imaging	53	3.5
Longo, Bandini, et al. (2025)⁸⁴	Italy	Tears	Shoulder	Diagnosis	ML, DL	Medical imaging	19	4
Lopez et al. (2021)⁸⁵	USA	Arthroplasty	Hip, knee	Surgical assistance	ML	Clinical data	49	2
Lopez et al. (2022)⁸⁶	USA	Surgery	Spine	Prognosis, surgical assistance	ML	Not stated	40	3
Lubelski et al. (2021)⁸⁷	USA	Surgery	Spine	Prognosis	ML	Clinical data	31	3
Mai et al. (2023)⁸⁸	UK	General	General	Image analysis	DL	Medical imaging	7	3
Mashud et al. (2025)⁸⁹	USA	Rehabilitation	General	Treatment assistance	ML, DL, rule-based	Sensor data	101	2
Massalimova et al. (2022)⁹⁰	Switzerland	Surgery	Spine	Diagnosis	ML, DL	Sensor data	60	1
Mathew et al. (2022)⁹¹	USA	Skeletal Maturity	Spine	Diagnosis	ML, DL	Medical imaging	8	3.5
Mead et al. (2025)⁹²	Australia	Musculoskeletal disorders	Knee	Diagnosis	DL	Medical imaging	54	3
Meena & Roy (2022)⁹³	India	Fracture	General	Diagnosis	ML, DL	Medical imaging	22	0.5
Mohammed et al. (2024)⁹⁴	Malaysia	Musculoskeletal disorders	General	Diagnosis	ML, DL, rule-based	Medical imaging	85	3
Moreira et al. (2022)⁹⁵	Portugal	Rehabilitation	Lower limb	Treatment assistance	ML	Sensor data	18	3
Mozafari et al. (2024)⁹⁶	Iran	Arthroplasty	Hip	Surgical assistance	Hybrid/Other	Medical imaging	6	3
Ndjonko et al. (2025)⁹⁷	USA	Surgery	Spine	Prognosis	ML	Clinical data	51	4
Nicora et al. (2025)⁹⁸	Italy	Rehabilitation	General	Treatment assistance	ML	Sensor data	201	1.5
Nijhuis et al. (2024)⁹⁹	Netherlands	Fracture	Wrist	Diagnosis, prognosis	ML, DL	Medical imaging	18	3.5
Nogales et al. (2024)¹⁰⁰	Spain	Rehabilitation	General	Treatment assistance	DL	Clinical data, medical imaging	23	1.5
Ogink et al. (2021)¹⁰¹	Netherlands	Surgery	General	Prognosis	ML	Clinical data	59	3
Ong, Zhu, et al. (2023)¹⁰²	Singapore	Oncology	General	Diagnosis	ML, DL	Medical imaging, radiomics data	34	2
Ong, Liu, et al. (2023)¹⁰³	Singapore	Osteoporosis	General	Diagnosis	ML, DL	Medical imaging, radiomics data	39	2
Ong et al. (2024)¹⁰⁴	Singapore	Oncology	Spine	Diagnosis, prognosis	ML, DL	Medical imaging, radiomics data	33	2
Orji et al. (2023)¹⁰⁵	USA	Fracture	Wrist	Diagnosis	ML, DL	Medical imaging	8	4
Papalia et al. (2024)¹⁰⁶	Italy	Oncology	General	Diagnosis, prognosis	ML, DL	Clinical data, medical imaging	59	1.5
Plomp et al. (2025)¹⁰⁷	Netherlands	Fracture	Hip	Surgical assistance	Hybrid/Other	Medical imaging	16	1
Priyanka et al. (2024)¹⁰⁸	India	General	General	Image analysis	DL	Medical imaging	9	2.5
Rahman et al. (2020)¹⁰⁹	Germany	General	Knee	Image analysis	ML, DL	Medical imaging	19	1.5
Rossi et al. (2022)¹¹⁰	Italy	Arthroplasty	General	Surgical assistance	Hybrid/Other	Medical imaging	14	4
Sadat-Ali et al. (2025)¹¹¹	Saudi Arabia	Osteoporosis/Fracture	General	Prognosis	ML, DL	Medical imaging	15	1.5
Salman et al. (2024)¹¹²	Qatar	Arthroplasty	Knee	Surgical assistance	ML, DL	Clinical data, medical imaging	4	3.5
Sardari et al. (2023)¹¹³	UK	Rehabilitation	General	Treatment assistance	ML, DL	Sensor data	32	1.5
Schneller et al. (2025)¹¹⁴	Switzerland	Arthroplasty	Shoulder	Prognosis	ML, DL	Clinical data, medical imaging	25	4.5
Seow et al. (2020)¹¹⁵	UK	Injuries	General	Prognosis	ML	Clinical data	10	4
Shah et al. (2023)¹¹⁶	USA	Arthroplasty	Hip, knee	Surgical assistance	ML, DL	Medical imaging	20	5
Shelmerdine et al. (2022)¹¹⁷	UK	Fracture	General	Diagnosis	ML, DL	Medical imaging	9	5
Shetty et al. (2023)¹¹⁸	India	Injuries	Knee	Diagnosis	DL	Medical imaging	24	4
Shu et al. (2020)¹¹⁹	Japan	Arthroplasty	Knee	Biomechanical analysis	ML	Clinical data	NS	0
Siouras et al. (2022)¹²⁰	Greece	Injuries	Knee	Diagnosis	DL	Medical imaging	22	4
Soyer (2024)¹²¹	Turkey	Surgery	Spine	Surgical assistance	ML, DL	Medical imaging	217	0.5
Spaanderman et al. (2025)¹²²	Netherlands	Oncology	General	Diagnosis, prognosis	ML, DL	Medical imaging	325	5
Taylor et al. (2025)¹²³	UK	Surgery	Spine	Surgical assistance	Hybrid/Other	Medical imaging	31	5
Tieu et al. (2024)¹²⁴	USA	Fracture	General	Diagnosis	DL	Medical imaging	14	1.5
Anam et al. (2021)¹²⁵	Malaysia	Osteoporosis	General	Prognosis	ML, DL	Medical imaging	62	2
van der Linden et al. (2025)¹²⁶	Netherlands	Oncology	General	Diagnosis, prognosis, image analysis	ML, DL	Clinical data, medical imaging	92	3.5
Verheijen et al. (2025)¹²⁷	USA	Stenosis	Spine	Diagnosis, image analysis	ML, DL	Medical imaging	27	4
Walsh et al. (2024)¹²⁸	Ireland	Fracture	Hip	Prognosis	ML	Clinical data	80	5
Wei et al. (2024)¹²⁹	UK	Rehabilitation	Upper limb	Treatment assistance	ML, DL	Sensor data	186	1
Xu et al. (2022)¹³⁰	China	Trauma	General	Surgical assistance	Hybrid/Other	Medical imaging	39	2.5
Yoma et al. (2025)¹³¹	UK	Kinematics	Lower limb	Biomechanical analysis	DL	Sensor data	53	5
Zhang & Yang (2024)¹³²	Canada	Osteoarthritis	Knee	Diagnosis, prognosis	ML	Sensor data	22	1.5
Zhang et al. (2024)¹³³	China	General	General	Others	NLP	Text/Unstructured	68	4
Zhang et al. (2025)¹³⁴	China	Arthroplasty	Knee	Image analysis	ML, DL	Clinical data, medical imaging	21	5
Zhong et al. (2023)¹³⁵	China	Oncology	General	Image analysis	ML	Clinical data, radiomics data	9	5
Zhou et al. (2025)¹³⁶	Malaysia	Rehabilitation	General	Treatment assistance	ML, DL	Sensor data	18	4
Systematic reviews with meta-analysis
Adami et al. (2023)¹³⁷	Italy	Fracture	General	Prognosis	Hybrid/Other	Clinical data	43	5
Adebayo et al. (2023)¹³⁸	UK	Trauma	General	Diagnosis	ML, DL	Clinical data	14	5
Amadita et al. (2025)¹³⁹	Australia	Arthroplasty	Hip, shoulder	Image analysis	ML, DL	Medical imaging	36	7
Amani et al. (2024)¹⁴⁰	Iran	Osteoporosis	Hip, spine	Diagnosis	DL	Medical imaging	10	6.5
Beculic et al. (2024)¹⁴¹	Bosnia and Herzegovina	Fracture	Spine	Diagnosis	ML, DL	Medical imaging	17	6.5
Botnari et al. (2024)¹⁴²	Romania	Tears	Knee	Diagnosis	DL	Medical imaging	12	5
Chen et al. (2024)¹⁴³	China	Developmental dysplasia	Hip	Diagnosis	DL	Medical imaging	13	6.5
Compte et al. (2023)¹⁴⁴	UK	Disc disease	Spine	Diagnosis	ML, DL	Medical imaging	27	6
Corr et al. (2025)¹⁴⁵	UK	OPLL	Spine	Diagnosis	DL	Medical imaging	7	7
Dallora et al. (2019)¹⁴⁶	Sweden	Bone age	General	Diagnosis	ML, DL	Medical imaging	26	4
Droppelmann, Rodríguez, Jorquera, et al. (2024)¹⁴⁷	Chile	Musculoskeletal disorders	Upper limb	Diagnosis	DL	Medical imaging	10	4.5
Droppelmann, Rodríguez, Smague, et al. (2024)¹⁴⁸	Chile	Tendinopathy	General	Diagnosis	DL	Medical imaging	6	6
Gokhale et al. (2023)¹⁴⁹	Australia	Arthroplasty	Knee	Prognosis	ML	Clinical data	15	7
González-Pola et al. (2025)¹⁵⁰	Mexico	General	General	Diagnosis, prognosis, surgical assistance	ML, DL	Clinical data, medical imaging	595	4
Groot et al. (2020)¹⁵¹	USA	General	General	Diagnosis, prognosis, image analysis	DL	Medical imaging	12	4
Hansen et al. (2024)¹⁵²	Denmark	Fracture	Wrist	Diagnosis	DL	Medical imaging	10	5.5
Huang et al. (2022)¹⁵³	Taiwan	Trauma/Oncology/Osteoporosis	Spine	Diagnosis, prognosis	ML, DL	Medical imaging	31	1.5
Husarek et al. (2024)¹⁵⁴	Switzerland	Fracture	General	Diagnosis	Hybrid/Other	Medical imaging	17	4.5
Jung et al. (2024)¹⁵⁵	USA	Fracture	General	Diagnosis	ML, DL	Clinical data, medical imaging	66	7
Kim et al. (2023)¹⁵⁶	Korea	Arthroplasty	Hip, knee	Diagnosis	ML, DL	Medical imaging	5	5.5
Kraus et al. (2024)¹⁵⁷	Israel	Fracture	Wrist	Diagnosis	DL	Medical imaging	10	4.5
Krivicich et al. (2024)¹⁵⁸	USA	Surgery	General	Prognosis	ML	Clinical data	10	5
Kuo et al. (2022)¹⁵⁹	UK	Fracture	General	Diagnosis	ML, DL	Medical imaging	42	7
Lex et al. (2023)¹⁶⁰	Canada	Fracture	Hip	Diagnosis, prognosis	ML, DL	Clinical data, medical imaging	39	3
Li et al. (2023)¹⁶¹	China	Oncology	General	Diagnosis	ML, DL	Clinical data, medical imaging	31	6.5
Li et al. (2024)¹⁶²	China	Fracture	Spine	Diagnosis, prognosis	ML, DL	Clinical data, medical imaging	81	6.5
Li & Wong (2024)¹⁶³	China	Scoliosis	Spine	Prognosis	ML, DL	Clinical data, medical imaging	15	1
Lopez-Melia et al. (2024)¹⁶⁴	Switzerland	Fracture	Ribs	Diagnosis	DL	Medical imaging	27	6
Meesters et al. (2021)¹⁶⁵	Netherlands	Fracture	Hip	Surgical assistance	Hybrid/Other	Medical imaging	19	6
Mohammadi et al. (2024)¹⁶⁶	Iran	Osteoarthritis	Knee	Diagnosis	ML, DL	Medical imaging	61	7
Mohammadi et al. (2025)¹⁶⁷	USA	Injuries	Knee	Diagnosis	ML, DL	Medical imaging	28	7
Musbahi et al. (2025)¹⁶⁸	UK	Arthroplasty	General	Diagnosis, prognosis	DL	Medical imaging	139	6
Namireddy et al. (2024)¹⁶⁹	UK	Fracture	Spine	Diagnosis, prognosis	ML, DL	Clinical data, medical imaging	79	4
Rahim et al. (2023)¹⁷⁰	Iran	Osteoporosis	Hip	Diagnosis	ML, DL	Medical imaging	7	7
Raj et al. (2024)¹⁷¹	India	Fracture	Hip	Diagnosis	ML, DL	Medical imaging	5	6
Ramadanov et al. (2025)¹⁷²	Germany	Fracture	Hip	Diagnosis	DL	Medical imaging	11	6.5
Rich et al. (2023)¹⁷³	USA	Oncology	General	Image analysis	DL	Medical imaging	41	3
Salzmann et al. (2025)¹⁷⁴	Germany	General	Lower limb	Image analysis	DL	Medical imaging	13	7
Tao et al. (2025)¹⁷⁵	China	Oncology	General	Diagnosis	ML, DL	Medical imaging	20	7
Tarighatnia et al. (2025)¹⁷⁶	Iran	Osteoporosis	General	Diagnosis	DL	Medical imaging	7	6.5
Teoh et al. (2024)¹⁷⁷	Malaysia	Osteoarthritis	Knee	Diagnosis	ML, DL	Clinical data, medical imaging	70	1.5
Tian et al. (2025)¹⁷⁸	China	Arthroplasty	Knee	Prognosis	ML, DL	Clinical data, medical imaging	13	6
van den Broek et al. (2024)¹⁷⁹	Netherlands	Fracture	Ribs	Diagnosis	DL	Medical imaging	12	7
A. B. Wang et al. (2024)¹⁸⁰	China	Degenerative disease	Spine	Image analysis	DL	Medical imaging	45	7
T. Wang et al. (2024)¹⁸¹	China	Stenosis	Spine	Diagnosis	ML, DL	Medical imaging	19	5.5
Wu et al. (2023)¹⁸²	China	Osteoporosis/Fracture	General	Prognosis	ML	Clinical data, radiomics data	53	6
Wu et al. (2024)¹⁸³	China	Arthroplasty	Hip	Surgical assistance	Hybrid/Other	Not stated	17	4.5
Xiang et al. (2024)¹⁸⁴	China	Kinematics	Lower limb	Biomechanical analysis	ML, DL	Sensor data	13	6
Yen et al. (2024)¹⁸⁵	Taiwan	Osteoporosis	General	Diagnosis	DL	Medical imaging	6	4.5
Zhao et al. (2024)¹⁸⁶	UK	Tears	Knee	Diagnosis	DL	Medical imaging	11	5.5
Zhao et al. (2025)¹⁸⁷	China	Osteoarthritis	Knee	Diagnosis	DL	Medical imaging	19	7
Zhu et al. (2025)¹⁸⁸	China	Scoliosis	Spine	Image analysis	DL	Medical imaging	50	6.5

Table 2 provides a consolidated overview of the reviewed studies, detailing their publication characteristics, orthopaedic focus, AI applications, and methodological quality. This table is structured to help readers directly relate each AI application to familiar clinical conditions. The orthopaedic domains are categorised according to major anatomical regions such as the spine, knee and hip with examples of specific focus areas including fracture, arthroplasty, oncology, etc. Correspondingly, the AI applications are mapped to clinical tasks such as diagnosis, surgical assistance and image analysis to name a few. This summary serves to illustrate AI utilisation across various anatomical regions and orthopaedic subspecialties which forms the foundation for our subsequent analyses presented in later sections. The accompanying discussion further elaborates on observed trends and identifies research areas that are well-established versus those that remain underexplored.

Publication trends

From 2016 to 2024, the number of systematic reviews and meta-analyses on AI applications in orthopaedics increased markedly. Publication activity began to accelerate in 2019 (n = 3), followed by a steady annual increase, peaking in 2024 with 58 publications. As illustrated in Figure 2, we observed the steepest acceleration between 2023 and 2024, with an addition of 23 publications, representing the most single-year increase, while the second steepest period occurred from 2021 to 2022, adding 15 publications annually. Modest increment was observed between 2020 – 2021 and 2022 – 2023 with 8 publications added each year, indicating a period of steady, sustained growth. Overall, the trend demonstrates a sustained upward trajectory in research activity over the last decade.

Figure 2.

Number of papers published per year from 2016 until July 2025.

Geographic distribution

A total of 183 publications originated from 35 countries. The United States (n = 29, 15.9%), China (n = 23, 12.6%), and the United Kingdom (n = 20, 10.9%) were the top three contributors, together accounting for nearly 40% of global publication output. Other notable contributors included Italy (n = 16), the Netherlands (n = 10), and Australia, Germany, Korea, and Malaysia (n = 6 each). The Herfindahl–Hirschman Index (HHI) for this distribution was 734. A value below 1500 indicates a highly dispersed authorship base with minimal concentration in any single country. Figure 3 shows a geographical representation of publication density by country.

Figure 3.

Geographic distribution of publications. The map shows the number of publications by country, with the colour scale representing the publication count.

We further examine the correlation between the number of publications and the gross domestic expenditure on research and development (GERD) of the country, expressed as a percentage of gross domestic product (GDP). Data for GERD were obtained from the World Bank Open Data for the most recent year recorded for each country. As shown in Figure 4, a statistically significant positive correlation was observed between publication output and GERD (correlation coefficient = 0.352, p = 0.0381), suggesting that higher national investment in R&D is associated with greater scientific productivity in the field of orthopaedics.

Figure 4.

Relationship between national R&D expenditure and publication output.

Distribution of other study variables

Figure 5 shows the distribution of data within each categorical variable we examined in this review. Among the included systematic reviews and meta-analyses, the most common orthopaedic focus was on fracture (n = 28), followed by arthroplasty (n = 25) and surgery (n = 18).

Figure 5.

Number of studies based on (a) orthopaedic focus, (b) body parts, (c) AI applications, (d) AI types, and (e) Data types.

Most of the studies involved general or multiple body regions (n = 69). This was followed by studies focusing on the spine (n = 41), knee (n = 33), and hip (n = 22). The shoulder (n = 7) and lower limb (n = 9) were less frequently studied, with very few reviews focusing on the wrist, upper limb, ribs, and foot/ankle (n = 1–4 each).

AI was most often applied for diagnosis (n = 86), followed by prognosis (n = 69). Other applications included surgical planning/assistance (n = 22), image analysis (n = 22), and treatment assistance (n = 12). Machine learning (n = 137) and deep learning (n = 133) dominated the AI approaches reported in the reviews. Fewer reviews mentioned hybrid/other models (n = 10), natural language processing (n = 6), or rule-based systems (n = 2). For data types, most reviews evaluated AI models using medical imaging data (n = 119) and/or clinical data (n = 68). Sensor data (n = 24) and radiomics data (n = 7) were less common.

A cross-tabulation between each variable pair was performed to evaluate the distribution of data as shown in Figure 6. To ensure valid chi-square test assumptions, we initially reduced the number of categories within each categorical variable by excluding those with insufficient frequencies. Specifically, we retained only the most frequent categories: Orthopaedic_Focus (Fracture, Arthroplasty, Surgery, General), Body_Part (General, Spine, Knee, Hip), AI_Application (Diagnosis, Prognosis, Surgical assistance, Image analysis), AI_Type (Machine Learning, Deep Learning), and Data_Type (Medical Imaging, Clinical Data). Despite this preliminary filtering, three variable pairs (Orthopaedic_Focus × Body_Part, Orthopaedic_Focus × AI_Application, and Body_Part × AI_Application) still do not meet the chi-square assumption where no more than 20% of cells should have expected frequencies less than 5. These pairs were excluded from further analysis due to insufficient cell frequencies that could lead to unreliable test results.

Figure 6.

Heatmaps of cross-tabulation between variable pairs. Red outlines indicate significant pairs.

As shown in Table 3, the analysis revealed significant associations between four variable pairs. Strong associations were observed between Orthopaedic Focus and Data Type, AI Application and AI Type, AI Application and Data Type, and AI Type and Data Type.

Table 3.

Chi-square test results showing the relationships between study variables.

Variable pair	Chi square χ²	df	p value
Orthopaedic focus — AI type	6.856	3	0.077
Orthopaedic focus — Data type	14.335	3	0.002
Body part — AI type	0.553	3	0.907
Body part — Data type	2.261	3	0.52
AI application — AI type	10.706	3	0.013
AI application — Data type	30.681	3	<0.001
AI type — Data type	9.638	1	0.002

The table shows the chi-square statistic, degrees of freedom (df) and p-value.

Publication trends based on study variables

We analysed temporal trends in all 5 categorical variables studied from year 2015 – 2024 using Spearman’s correlation test, as shown in Figure 7. Specifically, our results show that all AI applications (Diagnosis, Image analysis, Treatment assistance, Prognosis, Surgical assistance, and Biomechanical analysis) & AI Types (Deep learning, Machine learning, Hybrid/Others, and Natural language processing) were positively correlated with publication year (p < 0.05; correlation coefficient ≥ 0.70).

Figure 7.

Publication trends up to year 2024 for the top six categories of (a) orthopaedic focus, (b) body part, (c) AI application, (d) AI type, and (e) data type.

Anatomical regions (General, Knee, Spine, Hip, Lower Limb, Shoulder) mostly showed statistically significant positive correlation with year, but studies involving upper limb were only moderately correlated with publication year (correlation coefficient 0.50 ≤ |r_s| < 0.70), while wrist studies showed no significant correlation with publication year (p ≥ 0.05).

Data types (Medical Imaging, Clinical Data, Sensor Data, Text/Unstructured) mostly showed statistically significant positive correlation with publication year, but radiomics studies showed no significant correlation with publication year.

Orthopaedic focus (Arthroplasty, Oncology, Rehabilitation, Injuries, Fracture, Surgery, Kinematics, Scoliosis, Trauma, General, Osteoarthritis, Musculoskeletal Disorders, Degenerative Disease) mostly showed statistically significant positive correlation with publication year; however, the number of studies involving tears and osteoporosis only moderately correlated with publication year (correlation coefficient 0.50 ≤ |r_s| < 0.70), while osteoporosis-related fractures and back pain studies showed no significant correlation with publication year (p ≥ 0.05).

Methodological quality (AMSTAR-2)

Methodological quality was assessed separately for systematic reviews that have meta-analysis (n = 52), and those without meta-analysis (n = 131). Shapiro-wilk test for normality showed statistical significance (p < 0.05), indicating that the data was not normally distributed. Therefore, we proceeded with non-parametric Spearman’s correlation test.

Studies without meta-analysis revealed a statistically significant weak positive correlation with publication year (r_s = 0.268, p = 0.002, N = 131), indicating that study quality, as measured by AMSTAR scores, has improved over time. For studies with meta-analysis, a better correlation was seen between publication year and AMSTAR scores (r_s = 0.363, p = 0.008, N = 52), indicating a clearer trend of quality improvement compared to systematic reviews without meta-analysis (Figure 8).

Figure 8.

Publication trends for systematic review with and without meta-analysis.

Discussion

In this scoping review, we aim to map and provide an overview of systematic reviews and meta-analyses evaluating AI applications in orthopaedic settings. Our study showed steady increase in the number of published systematic reviews with and without the inclusion of meta-analyses from year 2016 to 2024. This reflects growing interest and increased investment into AI research in the field of orthopaedics. The steep growth especially after 2020 suggests the possibility of growth in this area may be due to the COVID-19 pandemic’s impact on healthcare digitization.¹⁸⁹

Geographically, we observed publishing dominance in the USA, China and the UK, reflecting regional research strengths and resource distribution in AI technologies in healthcare.¹⁹⁰ This pattern is consistent with our statistical findings, where we have identified a modest but significant positive correlation between GERD and publication output, thus providing a plausible explanation for the leading number of publications by countries with established research infrastructure and sustained research & development (R&D) funding. Similar associations were also reported by Meo, Al Masri¹⁹¹ who demonstrated a strong positive correlation between national R&D expenditure and respective bibliometric outputs across Middle Eastern countries. While informative, these geographical findings should nevertheless be interpreted with caution. Since our search strategy included only open-access and freely available full-text articles, the dominance of certain countries may partly reflect differences in open-access publishing mandates and institutional policies rather than true disparities in research output. High-income countries and well-funded institutions are more likely to publish in open-access journals or comply with funder requirements for public access, whereas studies from regions with lower open-access adoption may be underrepresented. This potential bias should be considered when interpreting the observed global distribution. Interestingly, Figure 4 shows that countries with lower GERD, such as Malaysia, produced a comparable number of AI-related publications to those of higher-GERD nation like Korea, suggesting that substantial funding is not the only determinant of progress in this field. Our findings of a relatively low HHI (734) reflects a diverse authorship landscape spreading across multiple countries with contributions not only from high-income nations but also from middle-income countries as well, indicating the growing interest of AI use in orthopaedic settings within these regions.

Our review highlights that AI applications in orthopaedics are heavily concentrated in domains of fractures, arthroplasty, and surgery-related studies, especially in high-burden anatomical sites such as the spine, knee, and hip. For instance, fractures are one of the most common orthopaedic conditions worldwide with high morbidity and healthcare costs, making them a suitable target for implementing AI-driven diagnostic and prognostic tools.¹⁹² Similarly, knee and hip arthroplasty procedures are among the fastest-growing elective surgeries, with demand projected to increase dramatically within ageing populations to address the growing needs.¹⁹³ These domains appear to attract the greatest interest in AI applications, likely due to the greater availability of specialists and also the abundance of available data in these areas as imaging modalities provide a robust source for training AI models.¹⁹⁴ These patterns suggests that research activity is not only influenced by disease burden but also by the accessibility and availability of high-quality datasets. Our findings on these well-research domains were further supported by a supplementary screening of the excluded studies due to inaccessible full text (n = 65), which revealed similar patterns in research focus areas. Among these additional studies, fracture diagnosis remained the most investigated domain (13 studies), with the majority examining general fracture detection (6 studies) and upper limb fractures (4 studies). Surgery-related applications also emerged as a significant area of interest (8 studies), particularly for spine procedures (6 studies), where AI is being explored for both intraoperative assistance and postoperative outcome prediction. Other notable focus areas include arthroplasty outcome prediction (3 studies), osteoporosis diagnosis (3 studies) and detection of ACL and meniscal tears (3 studies), which reflect the predominance of diagnostic applications identified in our main analysis. However, as this analysis was restricted to abstracts, the observation should be interpreted cautiously and viewed as contextual rather than conclusive.

An interesting finding was seen between orthopaedic focus areas and the utilization of data modalities as significant association found between them reveals that different orthopaedic subspecialties have distinct preferences for different data sources. This shows that each specialty would have unique clinical characteristics and will require specific diagnostic requirements or methodology to achieve clinically useful outcomes. Fracture research, for example, shows heavy reliance on imaging datasets which is in line with the radiological nature of fracture diagnosis and the standardized protocols for assessing fractures.¹⁹⁵ In contrast, surgical studies adopt a more balanced integration of using both imaging and clinical data. This is because operative decision-making is usually comprehensive and requires not only the consideration of the anatomical precision from imaging data, but also patient-specific clinical information such as their surgical or medical history.¹⁹⁶ This subspecialty-specific pattern suggests that orthopaedic AI research is increasingly adapting to the clinical protocols and workflow requirements of each discipline. However, several anatomical regions such as the upper limb and foot/ankle remain relatively underexplored despite their clinical importance. Addressing these gaps could potentially expand the applicability of AI in research and provide far broader clinical relevance across orthopaedic settings.

Another significant association was observed between AI type and data modality which highlights a key difference in methodological approach within orthopaedic AI research. Deep learning was the most dominant approach in medical imaging applications (112 studies), reflecting its ability to extract complex features from high-dimensional visual data such as radiographs, CT, and MRI modalities using convolutional neural networks (CNNs). For instance, Thian, Li¹⁹⁷ used Faster R-CNN (Inception-ResNet v2) to detect and localize wrist fractures and was able to achieve sensitivity of 91–96% across views. In contrast, machine learning methods show greater prominence in clinical data applications. This is because algorithms like random forests, support vector machines, and logistic regression excel in processing structured datasets, which are often smaller and more tabular in nature.¹⁹⁸ These methods offer advantages in interpretability, and computational efficiency, making them well-suited for applications such as pre-processing of electronic health record data, risk stratification and outcome predictions.¹⁹⁹ Together, these patterns suggests that methodological selection in orthopaedic AI research requires alignment between data modality, clinical task and algorithmic strength, with deep learning being the standard for imaging-based diagnostics, while machine learning plays central role in prognostics and decision-making.

The strong association between AI application and data type reflects the distinct data requirement of diagnostic versus prognostic models. We observed that diagnostic applications are primarily image-driven, with 86 studies relying on radiological data. This reflects the synergy with visual diagnostic tasks in orthopaedics, such as fracture detection,¹⁵⁵ anatomical measurement,⁷⁵ pathology identification,¹²⁴ etc. The visual nature of orthopaedic conditions combined with the standardized protocols for acquiring medical images creates optimal conditions for AI-assisted diagnosis where deep learning algorithms can potentially identify subtle findings that might be overlooked in routine clinical practice. On the other hand, prognostic applications exhibit a more balanced distribution across clinical and imaging data, reflecting the recognition that outcome prediction requires multimodal information. Prognostic models often integrate patient demographics, surgical or medical history, functional data and even lifestyle considerations in addition to imaging.²⁰⁰ This more holistic approach acknowledges that patient outcomes are influenced by a mixture of biological, functional and environmental factors, not all of which are visible on imaging.

Implications and future directions

From our review, we were able to see growing interest in the use of AI in orthopaedics research with the steady rise in number of publications in this field. Collectively, these findings reveal that orthopaedic AI research is influenced by factors such as clinical burden, data availability, and methodological pragmatism. Researchers and healthcare institutions can make use of these findings to plan and guide research for AI implementations and integrations. Our findings can help inform selection of suitable technology and increase efficiency of resource allocation by understanding which approach would work best for specific orthopaedic areas, specifically with the various anatomical regions, clinical tasks and data modalities, underscoring the adoption of AI in orthopaedic settings to be highly context dependent.

The importance of sustained investment and improved research infrastructure in driving innovation is highlighted by the significant positive correlation between national R&D expenditure and their respective publication outputs. Furthermore, there are several avenues for researchers to explore for future research as our findings not only show potential opportunities for expanding AI research into underrepresented anatomical regions such as in the shoulder, hand, foot and ankle, but also highlights the need for future studies to explore emerging application areas such as using prescriptive modelling approaches.²⁰¹ Prescriptive models go beyond the conventional diagnosing and risk prediction tasks to recommend specific actions or interventions that are likely to lead to the best outcomes for individuals and patients, thus helping to guide personalized interventions based on unique patient profiles.

Limitations

There were several limitations in the current systematic review and meta-analysis that are worth noting. First, our scope was restricted to only applications in orthopaedics, and therefore findings may not be generalizable to related specialties such as orthodontics or other musculoskeletal fields. Secondly, the literature search was limited to three electronic databases (PubMed, Scopus, and Web of Science), with no inclusion of grey literature sources such as conference proceedings, theses, or preprints. Additionally, only open-access and freely available full-text articles were included. This may have introduced selection bias, as subscription-based journals often host high-impact studies, potentially affecting the regional and institutional representation of the included literature. Nevertheless, the studies excluded due to unavailability of full texts accounted for only 22% of those that initially met the selection criteria and were sought for retrieval. A further review of their abstracts indicated research trends comparable to those identified in our full-text analyses of open-access publications. Finally, our methodological appraisal only assessed the critical domains of AMSTAR-2, and the non-critical domains of AMSTAR-2 were not evaluated in this study. While this could limit interpretation of the overall strength of evidence, our emphasis for this study is on mapping evidence and identifying research gaps rather than evaluating study quality.

Conclusion

Current AI research in orthopaedics is largely driven by clinical foci, data availability, and methodological feasibility, with certain domains remaining underexplored. Our review provides a comprehensive mapping of systematic reviews and meta-analyses in the field, offering guidance for researchers, clinicians, and policymakers to shape future research priorities effectively.

Footnotes

ORCID iDs

Wisely Zhi-Tang Koay

Raja Elina Ahmad

Tunku Kamarul

Funding

The authors disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the Ministry of Higher Education, Malaysia; FRGS/1/2021/STGO1/UM/02/5(FP033-2021).

Declaration of conflicting interests

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

References

Aslani

Pournik

Abbasi

, et al. Transforming healthcare: the role of artificial intelligence. Stud Health Technol Inf 2025; 327: 1363–1367.

George

. Implementing AI-driven clinical workflow automation to reduce physician burnout and enhance operational efficiency in tertiary care hospitals. 2025; 6: 13–17.

Han

Huang

Wang

, et al. Artificial intelligence in orthopedic surgery: current applications, challenges, and future directions. MedComm 2020; 6: e70260.

Pollock

Peters

MDJ

Khalil

, et al. Recommendations for the extraction, analysis, and presentation of results in scoping reviews. JBI evidence synthesis 2023; 21: 520–532.

Shea

Reeves

Wells

, et al. AMSTAR 2: a critical appraisal tool for systematic reviews that include randomised or non-randomised studies of healthcare interventions, or both. BMJ 2017; 358: j4008.

Alam

Hasan

Mashud

, et al. Neural network for enhancing robot-assisted rehabilitation: a systematic review. Actuators 2025; 14: 16.

Allam

Anand

Flores

, et al. Computer vision in osteoporotic vertebral fracture risk prediction: a systematic review. Neurospine 2023; 20: 1112–1123.

Amran

Basaruddin

Ijaz

, et al. Spine deformity assessment for scoliosis diagnostics utilizing image processing techniques: a systematic review. Applied Sciences-Basel 2023; 13: 11555.

Amrani El Yaakoubi

McDonald

Lennon

. Prediction of gait kinematics and kinetics: a systematic review of EMG and EEG signal use and their contribution to prediction accuracy. Bioengineering (Basel) 2023; 10: 1162.

10.

Angthong

Rungrattanawilai

Pundee

. Artificial intelligence assistance in deciding management strategies for polytrauma and trauma patients. Pol Przegl Chir 2023; 96: 114–117.

11.

Bacco

Russo

Ambrosio

, et al. Natural language processing in low back pain and spine diseases: a systematic review. Front Surg 2022; 9: 957085.

12.

Batailler

Lording

De Massari

, et al. Predictive models for clinical outcomes in total knee arthroplasty: a systematic analysis. Arthroplasty Today 2021; 9: 1–15.

13.

Batailler

Shatrov

Sappey-Marinier

, et al. Artificial intelligence in knee arthroplasty: current concept of the available clinical applications. Arthroplasty 2022; 4: 17.

14.

Baur

Gehlen

Scherer

, et al. Decision support by machine learning systems for acute management of severely injured patients: a systematic review. Front Surg 2022; 9: 924810.

15.

Binvignat

Pedoia

Butte

, et al. Use of machine learning in osteoarthritis research: a systematic literature review. RMD Open 2022; 8: e001998.

16.

Blackman

Vivekanantha

Mughal

, et al. Machine learning models predicting risk of revision or secondary knee injury after anterior cruciate ligament reconstruction demonstrate variable discriminatory and accuracy performance: a systematic review. BMC Musculoskelet Disord 2025; 26: 16.

17.

Bonaldi

Pretto

Pirri

, et al. Deep learning-based medical images segmentation of musculoskeletal anatomical structures: a survey of bottlenecks and strategies. Bioengineering-Basel 2023; 10: 137.

18.

Castagno

Gompels

Strangmark

, et al. Understanding the role of machine learning in predicting progression of osteoarthritis. Bone Jt J. 2024; 106-B(11): 1216–1222.

19.

Cha

Kim

Park

, et al. Artificial intelligence and machine learning on diagnosis and classification of hip fracture: systematic review. J Orthop Surg Res 2022; 17: 520.

20.

Cha

Kim

, et al. Effect of artificial intelligence or machine learning on prediction of hip fracture risk: systematic review. J Bone Metab 2023; 30: 245–252.

21.

Chavosh Nejad

Vestergaard Matthiesen

Dukovska-Popovska

, et al. Machine learning for predicting duration of surgery and length of stay: a literature review on joint arthroplasty. Int J Med Informatics 2024; 192: 105631.

22.

Cheng

Jiao

Meiring

, et al. Reliability and validity of current computer vision based motion capture systems in gait analysis: a systematic review. Gait Posture 2025; 120: 150–160.

23.

Chong

Chan

VWK

, et al. Application of machine learning in the prevention of periprosthetic joint infection following total knee arthroplasty: a systematic review. Arthroplasty 2023; 5: 38.

24.

Clement

. Predicting functional outcomes of total hip arthroplasty using machine learning: a systematic review. J Clin Med 2024; 13: 603.

25.

Corban

Lorange

Laverdiere

, et al. Artificial intelligence in the management of anterior cruciate ligament injuries. Orthop J Sports Med 2021; 9: 23259671211014206.

26.

Cruz

Lins

Medeiros

RVA

, et al. Artificial intelligence on the identification of risk groups for osteoporosis, a general review. Biomed Eng Online 2018; 17: 12.

27.

D’Antoni

Russo

Ambrosio

, et al. Artificial intelligence and computer vision in low back pain: a systematic review. Int J Environ Res Publ Health. 2021; 18(20): 10909. doi:10.3390/ijerph182010909.

28.

D’Antoni

Russo

Ambrosio

, et al. Artificial intelligence and computer aided diagnosis in chronic low back pain: a systematic review. Int J Environ Res Publ Health. 2022; 19(10): 5971. doi:10.3390/ijerph19105971.

29.

Dhumale

Shinde

Ambali

, et al. Integration of artificial intelligence for diagnostic methods in musculoskeletal conditions: a systematic review. Cureus. 2025; 17(2): e79391.

30.

Dietz

Vaitheesh

Alkin

, et al. Machine learning in clinical diagnosis, prognostication, and management of acute traumatic spinal cord injury (SCI): a systematic review. J Clin Orthop Trauma 2022; 35: 102046.

31.

Dijkstra

van de Kuit

de Groot

, et al. Systematic review of machine-learning models in orthopaedic trauma. Bone Jt Open 2024; 5: 9–19.

32.

Diomatari

Martin

Jenkins

, et al. Clinical prediction models for medication adverse events in patients with rheumatic and musculoskeletal conditions: a systematic literature review. Semin Arthritis Rheum 2025; 73: 152728.

33.

Donisi

Cesarelli

Pisani

, et al. Wearable sensors and artificial intelligence for physical ergonomics: a systematic review of literature. Diagnostics 2022; 12: 3048.

34.

Shao

Zhang

, et al. Artificial intelligence in degenerative cervical disease: a systematic review of MRI-based diagnostic models. Digit Health 2025; 11: 20552076241311939.

35.

Eckart

Ghimire

Stavitz

, et al. Predictive utility of the functional movement screen and Y-balance test: current evidence and future directions. Sports 2025; 13: 46.

36.

Entezari

Koucheki

Abbas

, et al. Improving resource utilization for arthroplasty care by leveraging machine learning and optimization: a systematic review. Arthroplast Today 2023; 20: 101116.

37.

Faiella

Santucci

Calabrese

, et al. Artificial intelligence in bone metastases: an MRI and CT imaging review. Int J Environ Res Publ Health 2022; 19: 1880.

38.

Farrow

Raja

Zhong

, et al. A systematic review of natural language processing applications in trauma & orthopaedics. Bone Jt Open 2025; 6: 264–274.

39.

Getzmann

Zantonelli

Messina

, et al. The use of artificial intelligence in musculoskeletal ultrasound: a systematic review of the literature. Radiol Med 2024; 129: 1405–1411.

40.

Ghanem

Ghaith

El-Hajj

, et al. Limitations in evaluating machine learning models for imbalanced binary outcome classification in spine surgery: a systematic review. Brain Sci 2023; 13: 1723.

41.

Giaccone

D'Antoni

Russo

, et al. Prevention and management of degenerative lumbar spine disorders through artificial intelligence-based decision support systems: a systematic review. BMC Musculoskelet Disord 2025; 26: 126.

42.

Gill

Ponniah

Giersztein

, et al. The diagnostic and prognostic capability of artificial intelligence in spinal cord injury: a systematic review. Brain Spine 2025; 5: 104208.

43.

Gitto

Cuocolo

Albano

, et al. CT and MRI radiomics of bone and soft-tissue sarcomas: a systematic review of reproducibility and validation strategies. Insights Imaging 2021; 12: 68.

44.

Gitto

Cuocolo

Huisman

, et al. CT and MRI radiomics of bone and soft-tissue sarcomas: an updated systematic review of reproducibility and validation strategies. Insights Imaging 2024; 15: 54.

45.

Goedmakers

CMW

Pereboom

Schoones

, et al. Machine learning for image analysis in the cervical spine: systematic review of the available models and methods. Brain Spine 2022; 2: 101666.

46.

González-Castro

Leirós-Rodríguez

Prada-García

, et al. The applications of artificial intelligence for assessing fall risk: systematic review. J Med Internet Res 2024; 26: e54934.

47.

Groot

Bindels

BJJ

Ogink

, et al. Availability and reporting quality of external validations of machine-learning prediction models with orthopedic surgical outcomes: a systematic review. Acta Orthop 2021; 92: 385–393.

48.

Groot

Ogink

Lans

, et al. Machine learning prediction models in orthopedic surgery: a systematic review in transparent reporting. J Orthop Res 2022; 40: 475–483.

49.

Gupta

Kingston

O'Malley

, et al. Advancements in artificial intelligence for foot and ankle surgery: a systematic review. Foot Ankle Orthop 2023; 8: 24730114221151079.

50.

Gupta

Haeberle

Zimmer

, et al. Artificial intelligence-based applications in shoulder surgery leaves much to be desired: a systematic review. JSES Rev Rep Tech 2023; 3: 189–200.

51.

Gurchiek

Cheney

McGinnis

. Estimating biomechanical time-series with wearable sensors: a systematic review of machine learning techniques. Sensors (Basel). 2019; 19(23): 5227. doi:10.3390/s19235227.

52.

Han

, et al. Revolutionizing spinal interventions: a systematic review of artificial intelligence technology applications in contemporary surgery. BMC Surg 2024; 24: 345.

53.

Lin

Zhu

, et al. Deep learning in the radiologic diagnosis of osteoporosis: a literature review. J Int Med Res 2024; 52: 3000605241244754.

54.

Herman Kumar

Wee

, et al. A systematic review on deep learning model in computer-aided diagnosis for anterior cruciate ligament injury. Current Medical Imaging. 2024; 20: e15734056295157. doi:10.2174/0115734056295157240418043624.

55.

Hinterwimmer

Lazic

Suren

, et al. Machine learning in knee arthroplasty: specific data are key-a systematic review. Knee Surg Sports Traumatol Arthrosc 2022; 30: 376–388.

56.

. Pre-impact fall detection. Biomed Eng Online 2016; 15: 61.

57.

Yang

Zhang

, et al. Methods to predict osteonecrosis of femoral head after femoral neck fracture: a systematic review of the literature. J Orthop Surg Res 2023; 18: 377.

58.

Hussein

Khan

. Using artificial intelligence to predict the development of kyphosis disease: a systematic review. Cureus 2023; 15: e48341.

59.

Karimi

Langberg

Malige

, et al. Accuracy of machine learning to predict the outcomes of shoulder arthroplasty: a systematic review. Arthroplasty 2024; 6: 26.

60.

Khan

Naseer

Yazidi

, et al. Analysis of human gait using hybrid EEG-fNIRS-Based BCI system: a review. Front Human Neurosci 2021; 14: 613254.

61.

Khan

Chaurasia

. Artificial intelligence and its use in spine surgery and preparation of predictive models: a systematic review. Ann Med Surg 2025; 87: 171–176.

62.

Kim

, et al. Spine muscle auto segmentation techniques in MRI imaging: a systematic review. BMC Musculoskelet Disord 2024; 25: 716.

63.

Kokkotis

Chalatsis

Moustakidis

, et al. Identifying gait-related functional outcomes in post-knee surgery patients using machine learning: a systematic review. Int J Environ Res Publ Health 2022; 20: 448.

64.

Kolaghassi

Al-Hares

Sirlantzis

. Systematic review of intelligent algorithms in gait analysis and prediction for lower limb robotic systems. IEEE Access 2021; 9: 113788–113812.

65.

Krishnakumar

van Beijnum

Baten

CTM

, et al. Estimation of kinetics using IMUs to monitor and aid in clinical decision-making during ACL rehabilitation: a systematic review. Sensors (Basel) 2024; 24: 2163.

66.

Kurmis

Ianunzio

. Artificial intelligence in orthopedic surgery: evolution, current state and future directions. ARTHROPLASTY 2022; 4: 9.

67.

Kurmis

. A role for artificial intelligence applications inside and outside of the operating theatre: a review of contemporary use associated with total knee arthroplasty. Arthroplasty 2023; 5: 40.

68.

Kutbi

. Artificial intelligence-based applications for bone fracture detection using medical images: a systematic review. Diagnostics 2024; 14: 1879.

69.

Langenberger

Thoma

Vogt

. Can minimal clinically important differences in patient reported outcome measures be predicted by machine learning in patients with total knee or hip arthroplasty? A systematic review. BMC Med Inform Decis Mak 2022; 22: 18.

70.

Langerhuizen

DWG

Janssen

Mallee

, et al. What are the applications and limitations of artificial intelligence for fracture detection and classification in Orthopaedic trauma imaging? A systematic review. Clin Orthop Relat Res 2019; 477: 2482–2491.

71.

Lans

Kanbier

Bernstein

, et al. Social determinants of health in prognostic machine learning models for Orthopaedic outcomes: a systematic review. J Eval Clin Pract 2023; 29: 292–299.

72.

Lee

. Inertial motion capture-based wearable systems for estimation of joint kinetics: a systematic review. Sensors (Basel) 2022; 22: 2507.

73.

Lee

Jung

Mahatthanatrakul

, et al. Artificial intelligence in spinal imaging and patient care: a review of recent advances. Neurospine 2024; 21: 474–486.

74.

Lemel

Shin

Meade

, et al. Predictive models for patient-reported outcomes (PROs) in elective spine surgery: a systematic review. Artificial Intelligence Surgery 2025; 5: 82–102.

75.

Lezak

Pruneski

Oeding

, et al. Diagnostic performance of deep learning for leg length measurements on radiographs in leg length discrepancy: a systematic review. J Exp Orthop 2024; 11: e70080.

76.

Liawrungrueang

Cho

Sarasombath

, et al. Current trends in artificial intelligence-assisted spine surgery: a systematic review. Asian Spine J 2024; 18: 146–157.

77.

Liawrungrueang

Cholamjiak

Promsri

, et al. Artificial intelligence for cervical spine fracture detection: a systematic review of diagnostic performance and clinical potential. Glob Spine J 2025; 15: 2547–2558.

78.

Liawrungrueang

Cho

Cholamjiak

, et al. Performance and clinical implications of machine learning models for detecting cervical ossification of the posterior longitudinal ligament: a systematic review. Asian Spine J 2025; 19: 148–159.

79.

Liu

Ong

Makmur

, et al. Application of artificial intelligence methods on osteoporosis classification with Radiographs-A systematic review. Bioengineering (Basel) 2024; 11: 484.

80.

Longo

De Salvatore

Sassi

, et al. Motion tracking algorithms based on wearable inertial sensor: a focus on shoulder. Electronics 2022; 11: 1741.

81.

Longo

De Salvatore

Valente

, et al. Artificial intelligence in total and unicompartmental knee arthroplasty. BMC Musculoskelet Disord 2024; 25: 571.

82.

Longo

Marino

Nicodemi

, et al. Artificial intelligence applications in the management of musculoskeletal disorders of the shoulder: a systematic review. J Exp Orthop 2025; 12: e70248.

83.

Longo

Lalli

Nicodemi

, et al. Artificial intelligence demonstrates potential to enhance Orthopaedic imaging across multiple modalities: a systematic review. J Exp Orthop 2025; 12: e70259.

84.

Longo

Bandini

Mancini

, et al. Artificial intelligence in rotator cuff tear detection: a systematic review of MRI-based models. Diagnostics 2025; 15: 1315.

85.

Lopez

Gazgalis

Boddapati

, et al. Artificial learning and machine learning decision guidance applications in total hip and knee arthroplasty: a systematic review. Arthroplast Today 2021; 11: 103–112.

86.

Lopez

Boddapati

Lombardi

, et al. Artificial learning and machine learning applications in spine surgery: a systematic review. Glob Spine J 2022; 12: 1561–1572.

87.

Lubelski

Hersh

Azad

, et al. Prediction models in degenerative spine surgery: a systematic review. Glob Spine J 2021; 11: 79s–88s.

88.

Mai

DVC

Drami

Pring

, et al. A systematic review of automated segmentation of 3D computed-tomography scans for volumetric body composition analysis. J Cachexia Sarcopenia Muscle 2023; 14: 1973–1986.

89.

Mashud

Hasan

Alam

. Advances in control techniques for rehabilitation exoskeleton robots: a systematic review. Actuators 2025; 14: 108.

90.

Massalimova

Timmermans

Esfandiari

, et al. Intraoperative tissue classification methods in orthopedic and neurological surgeries: a systematic review. Front Surg 2022; 9: 952539.

91.

Mathew

Palatinus

Padala

, et al. Neural networks for classification of cervical vertebrae maturation: a systematic review. Angle Orthod 2022; 92: 796–804.

92.

Mead

Cross

Roger

, et al. MRI deep learning models for assisted diagnosis of knee pathologies: a systematic review. Eur Radiol 2025; 35: 2457–2469.

93.

Meena

Roy

. Bone fracture detection using deep supervised learning from radiological images: a paradigm shift. Diagnostics 2022; 12: 2420.

94.

Mohammed

Xinying

Alnoor

, et al. A systematic review of artificial intelligence in Orthopaedic disease detection: a taxonomy for analysis and trustworthiness evaluation. Int J Comput Intell Syst 2024; 17: 303.

95.

Moreira

Figueiredo

Cerqueira

, et al. A review on locomotion mode recognition and prediction when using active orthoses and exoskeletons. Sensors 2022; 22: 7109.

96.

Mozafari

Moshtaghioon

Mahdavi

, et al. The role of artificial intelligence in preoperative planning for total hip arthroplasty: a systematic review. Front Artif Intell 2024; 7: 1417729.

97.

Ndjonko

LCM

Chakraborty

Petri

, et al. Evaluating predictive performance and generalizability of traditional and artificial intelligence models in predicting surgical site infections post-spinal surgery: a systematic review. Spine J 2025; 26: 280–291.

98.

Nicora

Santangelo

, et al. Systematic review of AI/ML applications in multi-domain robotic rehabilitation: trends, gaps, and future directions. J NeuroEng Rehabil 2025; 22: 79.

99.

Nijhuis

KDO

Dankelman

LHM

Wiersma

, et al. AI for detection, classification and prediction of loss of alignment of distal radius fractures; a systematic review. Eur J Trauma Emerg Surg 2024; 50: 2819–2831.

100.

Nogales

Rodríguez-Aragón

García-Tejedor

ÁJ

. A systematic review of the application of deep learning techniques in the physiotherapeutic therapy of musculoskeletal pathologies. Comput Biol Med 2024; 172: 108082.

101.

Ogink

Groot

Karhade

, et al. Wide range of applications for machine-learning prediction models in orthopedic surgical outcome: a systematic review. Acta Orthop 2021; 92: 526–531.

102.

Ong

Zhu

Tan

, et al. Application of machine learning for differentiating bone malignancy on imaging: a systematic review. Cancers (Basel) 2023; 15: 1837.

103.

Ong

Liu

Makmur

, et al. Artificial intelligence applications for osteoporosis classification using computed tomography. Bioeng 2023; 10: 1364.

104.

Ong

Lee

Tan

, et al. Oncologic applications of artificial intelligence and deep learning methods in CT spine Imaging-A systematic review. Cancers (Basel) 2024; 16: 2988.

105.

Orji

Reghefaoui

Palacios

MSS

, et al. Application of artificial intelligence and machine learning in diagnosing scaphoid fractures: a systematic review. Cureus J Med Sci. 2023; 15(10): e47732. doi:10.7759/cureus.47732.

106.

Papalia

Brigato

Sisca

, et al. Artificial intelligence in detection, management, and prognosis of bone metastasis: a systematic review. Cancers (Basel) 2024; 16: 2700.

107.

Plomp

Ten Duis

Meesters

AML

, et al. 3D virtual surgical planning of fractures in hip arthrodesis: a systematic review, case series and recommendations for treatment. Eur J Orthop Surg Traumatol 2025; 35: 157.

108.

Priyanka

Nayak

, et al. Impact of artificial intelligence assisted compressed sensing technique on scan time and image quality in musculoskeletal MRI - a systematic review. Radiography 2024; 30: 1704–1712.

109.

Rahman

Dürselen

Seitz

. Automatic segmentation of knee menisci - a systematic review. Artif Intell Med 2020; 105: 101849.

110.

Rossi

SMP

Mancino

Sangaletti

, et al. Augmented reality in orthopedic surgery and its application in total joint arthroplasty: a systematic review. Appl Sci-Basel 2022; 12: 5278.

111.

Sadat-Ali

Alzahrani

Alqahtani

, et al. Accuracy of artificial intelligence in prediction of osteoporotic fractures in comparison with dual-energy X-ray absorptiometry and the fracture risk assessment tool: a systematic review. World J Orthop 2025; 16: 103572.

112.

Salman

Khatkar

Al-Ani

, et al. Reliability of artificial intelligence in predicting total knee arthroplasty component sizes: a systematic review. Eur J Orthop Surg Traumatol 2024; 34: 747–756.

113.

Sardari

Sharifzadeh

Daneshkhah

, et al. Artificial intelligence for skeleton-based physical rehabilitation action evaluation: a systematic review. Comput Biol Med 2023; 158: 106835.

114.

Schneller

Kraus

Schätz

, et al. Machine learning in shoulder arthroplasty: a systematic review of predictive analytics applications. Bone Jt Open 2025; 6: 126–134.

115.

Seow

Graham

Massey

. Prediction models for musculoskeletal injuries in professional sporting activities: a systematic review. Translational Sports Medicine 2020; 3: 505–517.

116.

Shah

Lavu

Hecht

2nd , et al. Understanding the use of artificial intelligence for implant analysis in total joint arthroplasty: a systematic review. Arthroplasty 2023; 5: 54.

117.

Shelmerdine

White

Liu

, et al. Artificial intelligence for radiological paediatric fracture assessment: a systematic review. Insights Imaging 2022; 13: 94.

118.

Shetty

Dhande

Unadkat

, et al. A comprehensive review on the diagnosis of knee injury by deep learning-based magnetic resonance imaging. Cureus J Med Sci 2023; 15: e45730.

119.

Shu

Sugita

. Systematic review of computational modelling for biomechanics analysis of total knee replacement. Biosurf Biotribol 2020; 6: 3–11.

120.

Siouras

Moustakidis

Giannakidis

, et al. Knee injury detection using deep learning on MRI studies: a systematic review. Diagnostics 2022; 12: 537.

121.

Soyer

. Artificial intelligence-powered spine surgery: a systematic review of current trends and future prospects. J Turk 2024; 35: 167–172.

122.

Spaanderman

Marzetti

Wan

, et al. AI in radiological imaging of soft-tissue and bone tumours: a systematic review evaluating against CLAIM and FUTURE-AI guidelines. EBioMedicine 2025; 114: 105642.

123.

Taylor

Lam

Manoj

, et al. The clinical impact of augmented reality surgical navigation on pedicle screw placement and its effect on perioperative outcomes: a systematic review. Spine Surgery and Related Research 2025; 9: 269–282.

124.

Tieu

Kroen

Kadish

, et al. The role of artificial intelligence in the identification and evaluation of bone fractures. Bioeng 2024; 11: 338.

125.

Anam

Ponnusamy

Hussain

, et al. Osteoporosis prediction for trabecular bone using machine learning: a review. Comput Mater Continua (CMC) 2021; 67: 89–105.

126.

van der Linden

Vavliakis

de Groot

, et al. Artificial intelligence in bone metastases: a systematic review in guideline adherence of 92 studies. J Bone Oncol 2025; 52: 100682.

127.

Verheijen

EJA

Kapogiannis

Munteh

, et al. Artificial intelligence for segmentation and classification in lumbar spinal stenosis: an overview of current methods. Eur Spine J 2025; 34: 1146–1155.

128.

Walsh

Kristensen

Hjelholt

, et al. Systematic review of multivariable prognostic models for outcomes at least 30 days after hip fracture finds 18 mortality models but no nonmortality models warranting validation. J Clin Epidemiol 2024; 173: 111439.

129.

Wei

Zhang

Xie

. Continuous motion intention prediction using sEMG for upper-limb rehabilitation: a systematic review of model-based and model-free approaches. IEEE Trans Neural Syst Rehabil Eng 2024; 32: 1487–1504.

130.

Lou

, et al. Current status of robot-assisted surgery in the clinical application of trauma orthopedics in China: a systematic review. Health Sci Rep 2022; 5: e930.

131.

Yoma

Llurda-Almuzara

Herrington

, et al. Reliability and validity of lower extremity and trunk kinematics measured with markerless motion capture during sports-related and functional tasks: a systematic review. J Sports Sci 2025; 43: 1–28.

132.

Zhang

Yang

. Contemporary machine learning approaches towards biomechanical analysis in the diagnosis and prognosis prediction of knee osteoarthritis: a systematic review. Undergrad Res Nat Clin Sci Technol J 2024; 8: 1–15.

133.

Zhang

Liu

Zhou

, et al. Examining the role of large language models in orthopedics: systematic review. J Med Internet Res 2024; 26: e59607.

134.

Zhang

Hui

Tao

, et al. Application of artificial intelligence in X-ray imaging analysis for knee arthroplasty: a systematic review. PLoS One 2025; 20: e0321104.

135.

Zhong

Xing

Zhang

, et al. A systematic review of radiomics in giant cell tumor of bone (GCTB): the potential of analysis on individual radiomics feature for identifying genuine promising imaging biomarkers. J Orthop Surg Res 2023; 18: 414.

136.

Zhou

Rashid

Mat

, et al. Machine learning-based computer vision for depth camera-based physiotherapy movement assessment: a systematic review. Sensors (Basel). 2025; 25(5): 1586. doi:10.3390/s25051586.

137.

Adami

Biffi

Porcu

, et al. A systematic review on the performance of fracture risk assessment tools: FRAX, DeFRA, FRA-HS. J Endocrinol Investig 2023; 46: 2287–2297.

138.

Adebayo

Bhuiyan

Ahmed

. Exploring the effectiveness of artificial intelligence, machine learning and deep learning in trauma triage: a systematic review and meta-analysis. Digit Health 2023; 9: 20552076231205736.

139.

Amadita

Gray

Gee

, et al. CT metal artefact reduction for hip and shoulder implants using novel algorithms and machine learning: a systematic review with pairwise and network meta-analyses. Radiography 2025; 31: 36–52.

140.

Amani

Amanzadeh

Hamedan

, et al. Diagnostic accuracy of deep learning in prediction of osteoporosis: a systematic review and meta-analysis. BMC Musculoskelet Disord 2024; 25: 991.

141.

Beculic

Begagic

Dzidic-Krivic

, et al. Sensitivity and specificity of machine learning and deep learning algorithms in the diagnosis of thoracolumbar injuries resulting in vertebral fractures: a systematic review and meta-analysis. Brain and Spine. 2024; 4: 102809. doi:10.1016/j.bas.2024.102809.

142.

Botnari

Kadar

Patrascu

. A comprehensive evaluation of deep learning models on knee MRIs for the diagnosis and classification of meniscal tears: a systematic review and meta-analysis. Diagnostics 2024; 14: 1090.

143.

Chen

Cai

Zhang

, et al. The diagnostic value of artificial intelligence-assisted imaging for developmental dysplasia of the hip: a systematic review and meta-analysis. J Orthop Surg Res 2024; 19: 522.

144.

Compte

Granville Smith

Isaac

, et al. Are current machine learning applications comparable to radiologist classification of degenerate and herniated discs and modic change? A systematic review and meta-analysis. Eur Spine J 2023; 32: 3764–3787.

145.

Corr

Grimm

Leach

. Deep learning for identifying cervical ossification of the posterior longitudinal ligament: a systematic review and meta-analysis. Quant Imaging Med Surg 2025; 15: 1719–1740.

146.

Dallora

Anderberg

Kvist

, et al. Bone age assessment with various machine learning techniques: a systematic literature review and meta-analysis. PLoS One 2019; 14: e0220242.

147.

Droppelmann

Rodríguez

Jorquera

, et al. Artificial intelligence in diagnosing upper limb musculoskeletal disorders: a systematic review and meta-analysis of diagnostic tests. EFORT Open Rev 2024; 9: 241–251.

148.

Droppelmann

Rodríguez

Smague

, et al. Deep learning models for tendinopathy detection: a systematic review and meta-analysis of diagnostic tests. EFORT Open Rev 2024; 9: 941–952.

149.

Gokhale

Taylor

Gill

, et al. Hospital length of stay prediction for general surgery and total knee arthroplasty admissions: systematic review and meta-analysis of published prediction models. Digit Health 2023; 9: 20552076231177497.

150.

González-Pola

Herrera-Lozano

Graham-Nieto

, et al. Deep learning applications in orthopaedics: a systematic review and future directions. Acta Ortop Mex 2025; 39: 152–163.

151.

Groot

Bongers

MER

Ogink

, et al. Does artificial intelligence outperform natural intelligence in interpreting musculoskeletal radiological studies? A systematic review. Clin Orthop Relat Res 2020; 478: 2751–2764.

152.

Hansen

Jensen

Kusk

, et al. Deep learning performance compared to healthcare experts in detecting wrist fractures from radiographs: a systematic review and meta-analysis. Eur J Radiol 2024; 174: 111399.

153.

Huang

Pao

Chien

, et al. Thematic analysis of articles on artificial intelligence with spine trauma, vertebral metastasis, and osteoporosis using chord diagrams: a systematic review and meta-analysis. Medicine 2022; 101: e32369.

154.

Husarek

Hess

Razaeian

, et al. Artificial intelligence in commercial fracture detection products: a systematic review and meta-analysis of diagnostic test accuracy. Sci Rep 2024; 14: 23053.

155.

Jung

Dai

Liu

, et al. Artificial intelligence in fracture detection with different image modalities and data types: a systematic review and meta-analysis. PLOS Digit Health 2024; 3: e0000438.

156.

Kim

Kang

, et al. Detection of prosthetic loosening in hip and knee arthroplasty using machine learning: a systematic review and meta-analysis. Medicina (Kaunas) 2023; 59: 782.

157.

Kraus

Anteby

Konen

, et al. Artificial intelligence for X-ray scaphoid fracture detection: a systematic review and diagnostic test accuracy meta-analysis. Eur Radiol 2024; 34: 4341–4351.

158.

Krivicich

Jan

Kunze

, et al. Machine learning algorithms can be reliably leveraged to identify patients at high risk of prolonged postoperative opioid use following orthopedic surgery: a systematic review. HSS J 2024; 20: 589–599.

159.

Kuo

RYL

Harrison

Curran

, et al. Artificial intelligence in fracture detection: a systematic review and meta-analysis. Radiology 2022; 304: 50–62.

160.

Lex

Di Michele

Koucheki

, et al. Artificial intelligence for hip fracture detection and outcome prediction: a systematic review and meta-analysis. JAMA Netw Open 2023; 6: e233391.

161.

Dong

Yuan

. The diagnostic value of machine learning for the classification of malignant bone tumor: a systematic evaluation and meta-analysis. Front Oncol 2023; 13: 1207175.

162.

Liang

, et al. Machine learning value in the diagnosis of vertebral fractures: a systematic review and meta-analysis. Eur J Radiol 2024; 181: 111714.

163.

Wong

. The application of machine learning methods for predicting the progression of adolescent idiopathic scoliosis: a systematic review. Biomed Eng Online 2024; 23: 80.

164.

Lopez-Melia

Magnin

Marchand-Maillet

, et al. Deep learning for acute rib fracture detection in CT data: a systematic review and meta-analysis. Br J Radiol 2024; 97: 535–543.

165.

Meesters

AML

Trouwborst

de Vries

, et al. Does 3D-Assisted acetabular fracture surgery improve surgical outcome and physical functioning? A systematic review. J Personalized Med 2021; 11: 966.

166.

Mohammadi

Salehi

Jahanshahi

, et al. Artificial intelligence in osteoarthritis detection: a systematic review and meta-analysis. Osteoarthr Cartil 2024; 32: 241–253.

167.

Mohammadi

Jahanshahi

Shahrabi

, et al. Diagnosis of knee meniscal injuries using artificial intelligence: a systematic review and meta-analysis of diagnostic performance. PLoS One 2025; 20: e0326339.

168.

Musbahi

Ahmed

Hall

, et al. Deep learning classification models demonstrate high accuracy and clinical potential in radiograph interpretation in the arthroplasty clinical pathway: a systematic review and meta-analysis. J Exp Orthop 2025; 12: e70342.

169.

Namireddy

Gill

Peerbhai

, et al. Artificial intelligence in risk prediction and diagnosis of vertebral fractures. Sci Rep 2024; 14: 30560.

170.

Rahim

Zadeh

Javanmardi

, et al. Machine learning algorithms for diagnosis of hip bone osteoporosis: a systematic review and meta-analysis study. Biomed Eng Online. 2023; 22(1): 68. doi:10.1186/s12938-023-01132-9.

171.

Raj

Ayub

Pal

, et al. Diagnostic accuracy of artificial intelligence-based algorithms in automated detection of neck of femur fracture on a plain radiograph: a systematic review and meta-analysis. Indian J Orthop 2024; 58: 457–469.

172.

Ramadanov

Lettner

Hable

, et al. Artificial intelligence-guided assessment of femoral neck fractures in radiographs: a systematic review and multilevel meta-analysis. Orthop Surg 2025; 17: 1277–1286.

173.

Rich

Bhardwaj

Shah

, et al. Deep learning image segmentation approaches for malignant bone lesions: a systematic review and meta-analysis. Front Radiol 2023; 3: 1241651.

174.

Salzmann

Hassan Tarek

Prill

, et al. Artificial intelligence-based assessment of leg axis parameters shows excellent agreement with human raters: a systematic review and meta-analysis. Knee Surg Sports Traumatol Arthrosc 2025; 33: 177–190.

175.

Tao

Hui

Zhang

, et al. Accuracy of artificial intelligence in detecting tumor bone metastases: a systematic review and meta-analysis. BMC Cancer 2025; 25: 286.

176.

Tarighatnia

Amanzadeh

Hamedan

, et al. Deep learning-based evaluation of panoramic radiographs for osteoporosis screening: a systematic review and meta-analysis. BMC Med Imag 2025; 25: 86.

177.

Teoh

Othmani

, et al. Deciphering knee osteoarthritis diagnostic features with explainable artificial intelligence: a systematic review. IEEE Access 2024; 12: 109080–109108.

178.

Tian

Chen

Shao

, et al. Accuracy of machine learning in identifying candidates for total knee arthroplasty (TKA) surgery: a systematic review and meta-analysis. Eur J Med Res 2025; 30: 317.

179.

van den Broek

MCL

Buijs

Schmitz

LFM

, et al. Diagnostic performance of artificial intelligence in rib fracture detection: systematic review and meta-analysis. SURGERIES 2024; 5: 24–36.

180.

Wang

Zou

Yuan

, et al. Deep learning assisted segmentation of the lumbar intervertebral disc: a systematic review and meta-analysis. J Orthop Surg Res 2024; 19: 496.

181.

Wang

Chen

Fan

, et al. Machine learning and deep learning for diagnosis of lumbar spinal stenosis: systematic review and meta-analysis. J Med Internet Res 2024; 26: e54676.

182.

Chao

Bao

, et al. Predictive value of machine learning on fracture risk in osteoporosis: a systematic review and meta-analysis. BMJ Open 2023; 13: e071430.

183.

Zheng

Zhang

. Safety and efficacy of orthopedic robots in total hip arthroplasty: a network meta-analysis and systematic review. J Orthop Surg Res 2024; 19: 846.

184.

Xiang

Gao

Wang

, et al. Rethinking running biomechanics: a critical review of ground reaction forces, tibial bone loading, and the role of wearable sensors. Front Bioeng Biotechnol 2024; 12: 1377383.

185.

Yen

Chen

, et al. Diagnostic accuracy of deep learning for the prediction of osteoporosis using plain X-rays: a systematic review and meta-analysis. Diagnostics 2024; 14: 207.

186.

Zhao

Coppola

Karamchandani

, et al. Artificial intelligence applied to magnetic resonance imaging reliably detects the presence, but not the location, of meniscus tears: a systematic review and meta-analysis. Eur Radiol 2024; 34: 5954–5964.

187.

Zhao

Zhang

, et al. The value of deep learning-based X-ray techniques in detecting and classifying K-L grades of knee osteoarthritis: a systematic review and meta-analysis. Eur Radiol 2025; 35: 327–340.

188.

Zhu

Yin

Chen

, et al. Deep learning in cobb angle automated measurement on X-rays: a systematic review and meta-analysis. Spine Deform 2025; 13: 19–27.

189.

Senthil

Anand

Somala

, et al. Bibliometric analysis of artificial intelligence in healthcare research: trends and future directions. Future Healthc J 2024; 11: 100182.

190.

Tran

, et al. Global evolution of research in artificial intelligence in health and medicine: a bibliometric study. J Clin Med. 2019; 8(3): 360. doi:10.3390/jcm8030360.

191.

Meo

Al Masri

Usmani

, et al. Impact of GDP, spending on R&D, the number of universities and scientific journals on research publications in environmental sciences in the Middle East. Int J Occup Med Environ Health 2013; 26: 702–709.

192.

A-M

Bisignano

James

, et al. Global, regional, and national burden of bone fractures in 204 countries and territories, 1990–2019: a systematic analysis from the global burden of disease study 2019. The Lancet Healthy Longevity 2021; 2: e580–e592.

193.

Sloan

Premkumar

Sheth

. Projected volume of primary total joint arthroplasty in the U.S., 2014 to 2030. J Bone Joint Surg Am 2018; 100: 1455–1460.

194.

Chan

Samala

Hadjiiski

, et al. Deep learning in medical image analysis. Adv Exp Med Biol 2020; 1213: 3–21.

195.

Jones

Sharma

Hotchkiss

, et al. Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs. NPJ Digit Med 2020; 3: 144.

196.

Takeuchi

Kitagawa

. Artificial intelligence and surgery. Ann Gastroenterol Surg 2024; 8: 4–5.

197.

Thian

Jagmohan

, et al. Convolutional neural networks for automated fracture detection and localization on wrist radiographs. Radiology: Artif Intell 2019; 1: e180001.

198.

Grinsztajn

Oyallon

Varoquaux

. Why do tree-based models still outperform deep learning on typical tabular data? Adv Neural Inf Process Syst 2022; 35: 507–520.

199.

Khalilia

Chakraborty

Popescu

. Predicting disease risks from highly imbalanced data using random forest. BMC Med Inf Decis Making 2011; 11: 51.

200.

Tiulpin

Klein

Bierma-Zeinstra

SMA

, et al. Multimodal machine learning-based knee osteoarthritis progression prediction from plain radiographs and clinical data. Sci Rep 2019; 9: 20038.

201.

Al Zoubi

Khalaf

Beaulé

, et al. Leveraging machine learning and prescriptive analytics to improve operating room throughput. Front Digit Health 2023; 5: 1242214.

A scoping review of systematic reviews on artificial intelligence in orthopaedics

Abstract

Background

Aim

Methods

Results

Conclusion

Keywords

Introduction

Materials and methods

Search strategy

Inclusion and exclusion criteria

Data extraction

Methodological quality assessment

Statistical analysis

Results

Study selection

Publication trends

Geographic distribution

Distribution of other study variables

Publication trends based on study variables

Methodological quality (AMSTAR-2)

Discussion

Implications and future directions

Limitations

Conclusion

Footnotes

ORCID iDs

Funding

Declaration of conflicting interests

References