Sage Journals: Discover world-class research

Abstract

Background: Over the last few decades, shoulder surgery has undergone rapid advancements, with ongoing exploration and the development of innovative technological approaches. In the coming years, technologies such as robot-assisted surgeries, virtual reality, artificial intelligence, patient-specific instrumentation, and different innovative perioperative and preoperative planning tools will continue to fuel a revolution in the medical field, thereby pushing it toward new frontiers and unprecedented advancements. In relation to this, shoulder surgery will experience significant breakthroughs. Main body: Recent advancements and technological innovations in the field were comprehensively analyzed. We aimed to provide a detailed overview of the current landscape, emphasizing the roles of technologies. Computer-assisted surgery utilizing robotic- or image-guided technologies is widely adopted in various orthopedic specialties. The most advanced components of computer-assisted surgery are navigation and robotic systems, with functions and applications that are continuously expanding. Surgical navigation requires a visual system that presents real-time positional data on surgical instruments or implants in relation to the target bone, displayed on a computer monitor. There are three primary categories of surgical planning that utilize navigation systems. The initial category involves volumetric images, such as ultrasound echogram, computed tomography, and magnetic resonance images. The second type is based on intraoperative fluoroscopic images, and the third type incorporates kinetic information about joints or morphometric data about the target bones acquired intraoperatively. Conclusion: The rapid integration of artificial intelligence and deep learning into the medical domain has a significant and transformative influence. Numerous studies utilizing deep learning-based diagnostics in orthopedics have remarkable achievements and performance.

Keywords

artificial intelligence computer-assisted surgery shoulder surgery patient-specific instrumentation

Introduction

The rapid and exponential advancements in computing power and imaging technology throughout the last century have resulted in a revolutionary transformation in the global healthcare system, thereby improving patient care from diagnosis to therapy. Reality technologies, a culmination of cutting-edge computing and imaging modalities, have a significant disruptive potential across various sectors of the healthcare industry, particularly in surgery. To date, these reality technologies are harnessed in the orthopedic computer-assisted surgery (CAS) systems and artificial intelligence (AI) applications to enhance surgical precision, optimize outcomes, minimize complications, and predict prognosis. In the field of orthopedic surgery, the development and application of AI initially concentrated on hip and knee surgeries, leveraging pre-operative, intra-operative, and post-operative data. Shoulder surgery has been a later adopter of AI applications, with individual reports and articles emerging but few comprehensive studies synthesizing this information. This literature review aimed to assess the emerging trends in computer-driven reality technologies, the current state of reality technology implementation in orthopedic training and shoulder surgery, and the possible future applications of these technologies in shoulder surgery (Figure 1).

Figure 1.

Recent trends, technical concepts, and components of computer-assisted surgery systems in shoulder surgery.

Patient-specific instrumentation

Patient-specific instrumentation (PSI) has been developed over a long period of time and is already widely used in shoulder surgery, such as shoulder arthroplasty.^1–3 Achieving favorable outcomes after total shoulder arthroplasty (TSA) is dependent on accurate implant placement. Ensuring the secure attachment of the glenoid component while preserving appropriate alignment is a significant technological challenge in TSA.⁴ Hence, PSI can be used to assist the surgeon intraoperatively to reliably facilitate the preoperative planning of component implantation. A meta-analysis involving 12 studies with 227 participants was performed. Results showed that compared with conventional instrumentation methods, PSI led to a substantial enhancement in glenoid positioning and a significant decrease in the incidence rate of component malpositioning, from 68.6% to 15.3%.⁵

Previous studies on surgeries involving TSA or reverse TSA (RTSA) using PSI have been conducted. These studies have primarily focused on comparing the preoperative planned position of implants with the postoperative measured position, particularly regarding inclination and version (Table 1, Table 2).^6–18 Consequently, PSI enhances the surgeon’s ability to choose an appropriate implant and secure it accurately in place while allowing accurate preoperative planning.

Table 1.

Results in Total Shoulder Arthroplasty using patient-specific instrumentation.

Author	Year	Study design	Participants	Control group	PSI/SI	PSI system	Arthroplasty system	Variation in inclination(°)^a	Variation in retroversion(°)	Significance of outcome(VS control group)
Throckmorton⁶	2015	Cadaveric	36	Standard instrument	18/18	Signature; Biomet	Comprehensive shoulder; Biomet	3.0° ± 4.3°	5.0° ± 4.8°	Significant in inclination
Walch⁷	2015	Cadaveric	18	Uncontrolled	18/0	Custom	NA	1.42° ± 1.37°	1.64° ± 1.01°	Uncontrolled study
Pietrzak⁸	2013	Cadaveric	6	Uncontrolled	6/0	Signature; Biomet	Comprehensive shoulder; Biomet	−1.6° ± 2.48°	2.45° ± 2.9°	Uncontrolled study
Hendel⁹	2012	In vivo	31	Standard instrument	15/16	Arthroplan	Depuy	2.9° ± 3.4°	4.3° ± 4.5°	Significant in inclination and medial-lateral offset
Suero¹⁰	2012	In vivo	6	Uncontrolled	6/0	Custom	Comprehensive shoulder; Biomet	NA	NA	Uncontrolled study
Heylen¹¹	2016	In vivo	12	Standard instrument	6/6	Custom	Biomet T.E.S.S anatomic/Zimmer Anatomical	NA	NA	Not significant
Gauci¹²	2016	In vivo	17	Uncontrolled	17/0	Tornier	NA	1.8° ± 5.3°	3.4° ± 5.1°	Uncontrolled study
Lau and Keith¹³	2017	In vivo	7	Uncontrolled	7/0	Zimmer-Biomet	Comprehensive shoulder; Biomet	1° ± 4°	8° ± 10°	Uncontrolled study
Vervaecke¹⁴	2021	In vivo	22	Uncontrolled	22/0	Zimmer-Biomet	Sidus+ Bigliani/Flatow; Zimmer-Biomet	2° ± 2°	3° ± 3°	Uncontrolled study
Iannotti¹⁵	2017	In vivo	32	Standard instrument	16/16	NA	NA	2.21° ± 1.81°	4.49° ± 1.46°	Significant in inclination
Dallalana¹⁶	2016	In vivo	10	Uncontrolled	10/0	DJO Surgical Match Point	DJO Surgical Turon Modular Shoulder	1.0° ± 1.9°	2.6° ± 2.2°	Uncontrolled study

^aNote: negative and positive values reflect inferior and superior tilts, respectively.

Table 2.

Results in Reverse Total Shoulder Arthroplasty using patient-specific instrumentation.

Author	Year	Study design	Participants	Control group	PSI/SI	PSI system	Arthroplasty system	Variation in inclination(°)^a	Variation in retroversion(°)	Significance of outcome(VS control group)
Levy¹⁷	2014	Cadaveric	14	Uncontrolled	14/0	Surgicase Connect	DJO Surgical Reverse Shoulder Prosthesis	1.2° ± 1.2°	2.6° ± 1.7°	Uncontrolled study
Throckmorton⁶	2015	Cadaveric	34	Standard instrument	17/17	Signature;Biomet	Comprehensive shoulder; Biomet	4.0° ± 4.6°	6.0° ± 7.0°	Not significant
Pietrzak⁸	2013	Cadaveric	6	Uncontrolled	6/0	Signature; Biomet	Comprehensive shoulder; Biomet	3.4° ± 1.69°	0.77° ± 4.0°	Uncontrolled study
Eraly¹⁸	2016	Cadaveric	10	Standard instrument	5/5	Custom	Custom	1.2° ± 1.2°	1.8° ± 1.2°	Not significant
Suero¹⁰	2013	In vivo	4	Uncontrolled	4/0	Custom	Comprehensive shoulder; Biomet Or DELTA XTEND reverse total system; Depuy	NA	NA	Uncontrolled study
Heylen¹¹	2016	In vivo	24	Standard instrument	12/12	Surgicase Connect	Biomet T.E.S.S reverse or the Zimmer TM reverse	NA	NA	Not significant
Lau and Keith¹³	2017	In vivo	4	Uncontrolled	4/0	Zimmer-Biomet	Comprehensive shoulder; Biomet	−1° ± 5°	10° ± 10°	Uncontrolled study
Dallalana¹⁶	2016	In vivo	10	Uncontrolled	10/0	DJO Surgical Match Point	DJO Surgical Turon Modular Shoulder	1.6° ± 1.1°	1.1° ± 1.1°	Uncontrolled study

^aNote: negative and positive values reflect inferior and superior tilts, respectively.

Computer-assisted navigation for shoulder surgery

The use of computer-assisted navigation has led to a substantial increase in the demand for both total knee arthroplasty (TKA) and total hip arthroplasty (THA) .¹⁹ However, in the field of shoulder surgery, computer navigation is at an early stage, and there is a lack of clinical data supporting its use in this field.

Kircher et al. conducted a study with a limited number of patients. Results showed that intraoperative navigation can reduce glenoid wear and enhance the implantation of glenoid components in total anatomic shoulder arthroplasty.²⁰ Colasanti et al. performed a study using a preclinical cadaveric reverse TSA model. Their study showed that GPS navigation significantly improved the efficiency of baseplate and screw placement, thereby leading to a reduction in intra-/postoperative complications.²¹

Robotic-assisted surgery

There has been a substantial progress in the advancement of orthopedic robotic platforms in recent times, with different commercial systems currently in operation, particularly TKA and THA.²² For example, among robotic arm-assisted systems in orthopedic surgery, MAKO is the most extensively adopted platform. The MAKO enables the surgeon to enhance their preoperative assessment through the utilization of a CT scan, providing improved visualization of the joint, alignment, and deformities prior to surgery. This 3D perspective, available both before and during the procedure, allows for the tailoring of implant placement to the patient’s anatomical specifics and virtual adjustments to ensure balanced knee ligaments.²³

This system offers real-time feedback and effectively reduces deviations from preoperative planning, which are beneficial for both TKA and THA procedures. In a systematic review that examined all clinical and radiological studies investigating the use of the MAKO for TKA, 14 studies showed that the system achieved superior precision in component positioning. Furthermore, compared with conventional TKA, it reduced postoperative pain levels and length of hospital stays and enhanced functional scores and patient-reported outcomes.²⁴

Pierre St Mart et al. performed a systematic literature review to assess the outcomes of the MAKO in THA. Results revealed that the MAKO achieved more favorable outcomes while maintaining comparable complication rates compared with traditional THA.²⁵ According to the findings of Domb et al., patients who underwent robotic THA exhibited superior patient-reported outcomes and a decreased risk of implant malpositioning during a follow-up period of at least 5 years compared with conventional THA.²⁶

According to the abovementioned data, robot assistance has proven to be a valuable tool in operative treatment, offering several advantages over conventional TKA and THA, including improved implant position and enhanced clinical outcomes. However, despite the anticipated advantages of robotic TKA and THA, current literature regarding the application of robotics in shoulder surgery is limited.²⁷ Several studies have focused on the use of navigation systems in the placement of the glenoid component during TSA.^28–30 Nevertheless, only one study has specifically addressed the utilization of robotics in this field. Bozkurt et al. used a four-armed da Vinci surgical system to achieve arthroscopic control of various anatomic structures. This study utilized the robot in both the beach-chair and lateral decubitus shoulder positions, thereby exploring its capabilities and applications. However, the current large sized robotic body limits its application, indicating the need for further research and development in this area.³¹ Additional advancements are required in this field to determine whether the integration of robotic assistance can be effectively applied in clinical settings to enhance the outcomes of shoulder arthroscopy and total shoulder arthroplasty.

Virtual, augmented, and mixed reality

Currently, virtual reality (VR), augmented reality (AR), and mixed reality (MR) are increasingly adopted as training and operative tools in the field of surgery. The utilization of VR and AR in orthopedic surgery has gained significant popularity across various domains, including preoperative planning, intraoperative implementation, and educational and training purposes.^32–34 With these two technologies, surgeons can work swiftly and accurately during preoperative planning, thereby offering an extra level of safety while approaching the surgical phase. In particular, AR was found to be beneficial in visualizing preoperative planning images by directly overlaying them onto the patient. In shoulder surgery, AR may be a promising novel technology for a highly precise surgical execution of three-dimensional (3D) preoperative planning in reverse shoulder arthroplasty. AR can have the combined advantages of both technologies at a low cost. The next step can involve the addition of screw placement and the transfer of its application to human cadavers.³⁵ During intraoperative use, AR was found to be a valuable tool for assisting surgeons during surgical procedures. In addition, it offered comprehensive support to surgeons, thereby facilitating a deeper understanding of the 3D anatomy, delivering highly precise guidance, and simultaneously reducing surgical time and radiation exposure. In terms of surgical training, VR had promising outcomes, leading to a substantial enhancement of skills among trainees and residents. Research revealed that VR-trained residents conducted surgeries at a notably faster pace and fewer errors than conventionally trained individuals. Furthermore, VR-trained residents had a greater proficiency in executing surgical tasks compared with controls, even with minimal guidance, resulting in a superior overall performance.³⁶

Artificial intelligence and deep learning: diagnostic model

Currently, healthcare facilities have been utilizing digital medical imaging systems, which address the time and space constraints associated with accessing image data.³⁷ Furthermore, with the help of computer applications leveraging AI or machine learning (ML), diagnoses can now be conducted with ease and rapidity.

Diagnosis is the process of identifying the causes and attributes of a patient’s illness, and classification primarily aims to group patients into relatively homogeneous populations using standardized criteria. This classification process plays an important role in disease research. Moreover, the classification of fractures plays an essential role in selecting the appropriate surgical technique and facilitating the patient’s mobility restoration. Kuo et al. reported that the addition of AI assistance further improved the clinician’s performance in fracture detection. Moreover, clinicians made a diagnosis within a shorter time with AI assistance.³⁸ Currently, AI is used as a diagnostic adjunct and may improve workflow by screening or prioritizing images on worklists and highlighting the regions of interest for a reporting radiologist. In addition, AI may improve diagnostic certainty by acting as a “second reader” for clinicians or as an interim report prior to radiologist interpretation. Cha et al. found that the accuracy rate of hip fracture diagnosis by AI was 79.3%–98%. Further, the accuracy rate of fracture diagnosis by AI-assisted humans was 90.5%–97.1%, and the accuracy rate of human fracture diagnosis was 77.5%–93.5%. Finally, it revealed that the addition of AI assistance can further increase the accuracy of fracture diagnosis.³⁹

In shoulder disease, rotator cuff tear (RCT) is one of the most common shoulder injuries. When diagnosing RCT, skilled orthopedists visually interpret magnetic resonance imaging (MRI) data. Shim et al. reported about the deep learning system based on the 3D convolutional neural network (CNN) for the automated and accurate diagnosis of RCT. Moreover, 3D CNN automatically diagnoses the presence or absence of an RCT, classifies the tear size, and provides 3D visualization of the tear location. Considering these results, the proposed method shows the feasibility of AI, which can be used to assist in clinical RCT diagnosis.⁴⁰ Kim et al. also reported about automatic muscle atrophy-measuring algorithm to calculate the ratio of supraspinatus in the supraspinous fossa using deep learning. Thus, AI can analyze MRI data to predict the reparability of massive RCTs. CNN can improve the efficiency and objectiveness of reparability of massive RCTs by quantifying various indexes including the supraspinatus muscle occupation ratio, which predicts rotator cuff reparability used in the orthopedic rotator cuff tear.⁴¹

Prognostic prediction model

Machine learning is the science of utilizing computerized neural networks to adapt to complicated data. As mentioned earlier, it can also be used for diagnostic purposes. Recently, this technology is applied in orthopedic surgery for predicting complications.⁴² Regression algorithms can be optimized to create predictive algorithms based on collected variables. Gowd et al. showed that the supervised ML models outperformed comorbidity indices in accurately predicting postoperative complications after TSA. Supervised ML algorithms outperformed the American Society of Anesthesiologists classification models for predicting any adverse event, transfusion, extended length of hospital stay, surgical site infection, return to the operating room, and readmission.⁴³

Arvind et al. used 9043 patients who underwent primary TSA from the ACS-NSQIP database to evaluate five different AI algorithms for predicting 30-days readmission postoperatively.⁴⁴

In addition, Karnuta et al. evaluated 111,147 patients who underwent TSA and RTSA from the National Inpatient Sample database and used artificial neural networks for predicting length of hospital stay, discharge disposition, and inpatient costs. Results showed fair to good accuracy and reliability for predicting inpatient costs, length of hospital stay, and discharge disposition in shoulder arthroplasty. Based on these research findings, ML can preoperatively predict medical costs, length of hospital stay, and disposition using patient-specific data for expectation management between health care providers, patients, and payers.⁴⁵ Gowd et al. queried data for 49,354 primary shoulder arthroplasty patients from the Nationwide Readmissions Database. Machine learning algorithms were used to predict patients with immediate postoperative costs. The average perioperative cost of care was $18,843 ± $10,165. The wage index, hospital volume, patient age, readmissions, and the severity of the diagnosis-related group were the factors most correlated with the total cost of care. Considering these factors, after shoulder arthroplasty, there is significant variability in cumulative hospital costs; machine learning algorithms may predict cases with a high likelihood of increased resource utilization and readmission.⁴⁶

Application of AI and deep learning at different medical fields

The use of AI and deep learning systems (e.g., Lunit INSIGHT CXR [Luni]) is actively advancing in various medical fields beyond orthopedic surgery. Lunit is a commercially available computer-aided diagnosis system that utilizes deep learning algorithms to automatically detect thoracic abnormalities on chest X-ray images.⁴⁷ Previous research has revealed that Lunit had outstanding diagnostic capabilities compared with expert radiologists. Further, it enhanced the diagnostic performance of physicians for conditions such as pneumonia, lung cancer, tuberculosis, and other abnormal findings. Kim et al. found that the real-world multicenter health screening cohort showed a high concordance of the chest X-ray and Lunit results under the clinical integration of the deep-learning solution.

ChatGPT can significantly affect the clinical and translational medicine fields by providing access to up-to-date information, thereby improving patient engagement and reducing workloads for healthcare providers. However, there are also challenges and disadvantages that should be considered and addressed. Moreover, continuous research and development are required to ensure that ChatGPT is used safely and effectively.

Conclusions

In the future, revolutionary advancements such as robotic-assisted surgeries, AR, AI, PSI, and other peri-/preoperative planning tools will further transform the landscape of shoulder surgery. Moreover, the scope of application will continue to expand. The application of AI and CAS for shoulder surgery has considerable promising outcomes, as mentioned above. However, there are some challenges and disadvantages that should be resolved. Hence, further research on long-term clinical outcomes and other contributing factors should be performed.

Footnotes

Authors’ contributions

KSL: Main and review design, revision work and Interpretation of the results, SHJ: Main and review design, DHK: Reviewed the selected references, SWJ: Revision work, JPY: Manuscript writing and corresponding author. All authors read and approved the final manuscript.

Declaration of conflicting interests

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

Funding

The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by Kyungpook National University Hospital (2021).

ORCID iDs

Kang-San Lee

Jong Pil Yoon

Data availability statement

The datasets used and/or analyzed during the current

Appendix

References

Kim

. Evaluation of accuracy and reproducibility of patient-specific guides using 3-dimensional reconstruction in reverse total shoulder arthroplasty. Clin Shoulder Elb 2019; 22: 1–2. DOI: 10.5397/cise.2019.22.1.1

Ward

Dines

. Patient-specific guides/instrumentation in shoulder arthroplasty. Am J Orthop (Belle Mead NJ) 2018; 47. DOI: 10.12788/ajo.2018.0013

Haikal

Fares

Abboud

. Patient-specific implants in reverse shoulder arthroplasty. Clin Shoulder Elb 2023; 21: 108. DOI: 10.5397/cise.2023.00038

Gregory

Sankey

Augereau

, et al. Accuracy of glenoid component placement in total shoulder arthroplasty and its effect on clinical and radiological outcome in a retrospective, longitudinal, monocentric open study. PLoS One 2013; 8: e75791. DOI: 10.1371/journal.pone.0075791

Villatte

Muller

Pereira

, et al. Use of Patient-Specific Instrumentation (PSI) for glenoid component positioning in shoulder arthroplasty. A systematic review and meta-analysis. PLoS One 2018; 13: e0201759. DOI: 10.1371/journal.pone.0201759

Throckmorton

Gulotta

Bonnarens

, et al. Patient-specific targeting guides compared with traditional instrumentation for glenoid component placement in shoulder arthroplasty: a multi-surgeon study in 70 arthritic cadaver specimens. J Shoulder Elbow Surg 2015; 24: 965–971. DOI: 10.1016/j.jse.2014.10.013

Walch

Vezeridis

Boileau

, et al. Three-dimensional planning and use of patient-specific guides improve glenoid component position: an in vitro study. J Shoulder Elbow Surg 2015; 24: 302–309. DOI: 10.1016/j.jse.2014.05.029

Pietrzak

. Shoulder alignment obtained with the signature glenoid guide system: a cadaver study. Biomet Orthop 2013; 1–3.

Hendel

Bryan

Barsoum

, et al. Comparison of patient-specific instruments with standard surgical instruments in determining glenoid component position: a randomized prospective clinical trial. J Bone Joint Surg Am 2012; 94: 2167–2175. DOI: 10.2106/JBJS.K.01209

10.

Suero

Citak

, et al. Use of a custom alignment guide to improve glenoid component position in total shoulder arthroplasty. Knee Surg Sports Traumatol Arthrosc 2013; 21: 2860–2866. DOI: 10.1007/s00167-012-2177-1

11.

Heylen

Van Haver

Vuylsteke

, et al. Patient-specific instrument guidance of glenoid component implantation reduces inclination variability in total and reverse shoulder arthroplasty. J Shoulder Elbow Surg 2016; 25: 186–192. DOI: 10.1016/j.jse.2015.07.024

12.

Gauci

Boileau

Baba

, et al. Patient-specific glenoid guides provide accuracy and reproducibility in total shoulder arthroplasty. Bone Joint Lett J 2016; 98-B: 1080–1085. DOI: 10.1302/0301-620X.98B8.37257

13.

Lau

Keith

PPA

. Patient-specific instrumentation for total shoulder arthroplasty: not as accurate as it would seem. J Shoulder Elbow Surg 2018; 27: 90–95. DOI: 10.1016/j.jse.2017.07.004

14.

AlexanderVervaecke

JLBW

Van Haver

Verborgt

. Clinical and radiographic results of eccentric glenoid reaming in anatomical total shoulder arthroplasty using 3D planning and PSI. Semin Arthroplasty: JSES 2021; 31: 587–595. DOI: 10.1053/j.sart.2021.03.009

15.

Iannotti

JPIUD

Ricchetti

. Three-dimensional preoperative planning and patient-specific instrumentation for total shoulder arthroplasty. Semin Arthroplasty: JSES 2017; 28: 25–29. DOI: 10.1053/j.sart.2017.05.005

16.

Dallalana

McMahon

East

, et al. Accuracy of patient-specific instrumentation in anatomic and reverse total shoulder arthroplasty. Int J Shoulder Surg 2016; 10: 59–66. DOI: 10.4103/0973-6042.180717

17.

Levy

Everding

Frankle

, et al. Accuracy of patient-specific guided glenoid baseplate positioning for reverse shoulder arthroplasty. J Shoulder Elbow Surg 2014; 23: 1563–1567. DOI: 10.1016/j.jse.2014.01.051

18.

Eraly

Stoffelen

Vander Sloten

, et al. A patient-specific guide for optimizing custom-made glenoid implantation in cases of severe glenoid defects: an in vitro study. J Shoulder Elbow Surg 2016; 25: 837–845. DOI: 10.1016/j.jse.2015.09.034

19.

Hernandez

Garimella

Eltorai

AEM

, et al. Computer-assisted orthopaedic surgery. Orthop Surg 2017; 9: 152–158. DOI: 10.1111/os.12323

20.

Kircher

Wiedemann

Magosch

, et al. Improved accuracy of glenoid positioning in total shoulder arthroplasty with intraoperative navigation: a prospective-randomized clinical study. J Shoulder Elbow Surg 2009; 18: 515–520. DOI: 10.1016/j.jse.2009.03.014

21.

Colasanti

Moreschini

Cataldi

, et al. GPS guided reverse shoulder arthroplasty. Acta Biomed 2020; 91: 204–208. DOI: 10.23750/abm.v91i4-S.9377

22.

Banerjee

Cherian

Elmallah

, et al. Robot-assisted total hip arthroplasty. Expet Rev Med Dev 2016; 13: 47–56. DOI: 10.1586/17434440.2016.1124018

23.

Roche

. The MAKO robotic-arm knee arthroplasty system. Arch Orthop Trauma Surg 2021; 141: 2043–2047. DOI: 10.1007/s00402-021-04208-0

24.

Batailler

Fernandez

Swan

, et al. MAKO CT-based robotic arm-assisted system is a reliable procedure for total knee arthroplasty: a systematic review. Knee Surg Sports Traumatol Arthrosc 2021; 29: 3585–3598. DOI: 10.1007/s00167-020-06283-z

25.

St Mart

Goh

Shah

. Robotics in total hip arthroplasty: a review of the evolution, application and evidence base. EFORT Open Rev 2020; 5: 866–873. DOI: 10.1302/2058-5241.5.200037

26.

Domb

Chen

Lall

, et al. Minimum 5-year outcomes of robotic-assisted primary total hip arthroplasty with a nested comparison against manual primary total hip arthroplasty: a propensity score-matched study. J Am Acad Orthop Surg 2020; 28: 847–856. DOI: 10.5435/JAAOS-D-19-00328

27.

Twomey-Kozak

Hurley

Levin

, et al. Technological innovations in shoulder replacement: current concepts and the future of robotics in total shoulder arthroplasty. J Shoulder Elbow Surg 2023; 32: 2161–2171. DOI: 10.1016/j.jse.2023.04.022

28.

Sadoghi

Vavken

Leithner

, et al. Benefit of intraoperative navigation on glenoid component positioning during total shoulder arthroplasty. Arch Orthop Trauma Surg 2015; 135: 41–47. DOI: 10.1007/s00402-014-2126-1

29.

Wang

Hayes

Gibbons

, et al. Computer navigation of the glenoid component in reverse total shoulder arthroplasty: a clinical trial to evaluate the learning curve. J Shoulder Elbow Surg 2020; 29: 617–623. DOI: 10.1016/j.jse.2019.08.012

30.

Nascimento

LGP

Ikemoto

Wright

. Navigation in shoulder arthroplasty surgery. Rev Bras Ortop (Sao Paulo) 2022; 57: 540–545. DOI: 10.1055/s-0040-1712989

31.

Bozkurt

Apaydin

Isik

, et al. Robotic arthroscopic surgery: a new challenge in arthroscopic surgery Part-I: robotic shoulder arthroscopy; a cadaveric feasibility study. Int J Med Robot 2011; 7: 496–500. DOI: 10.1002/rcs.436

32.

Abdic

Van Osch

Langohr

, et al.

Mixed reality visualization in shoulder arthroplasty: is it better than traditional preoperative planning software?

Clin Shoulder Elb 2023; 26: 117–125. DOI: 10.5397/cise.2022.01326

33.

Lohre

Warner

JJP

Athwal

, et al. The evolution of virtual reality in shoulder and elbow surgery. JSES Int 2020; 4: 215–223. DOI: 10.1016/j.jseint.2020.02.005

34.

Hasan

Haratian

Kim

, et al. Virtual reality in orthopedic surgery training. Adv Med Educ Pract 2021; 12: 1295–1301. DOI: 10.2147/AMEP.S321885

35.

Kriechling

Roner

Liebmann

, et al. Augmented reality for base plate component placement in reverse total shoulder arthroplasty: a feasibility study. Arch Orthop Trauma Surg 2021; 141: 1447–1453. DOI: 10.1007/s00402-020-03542-z

36.

Longo

UGDSS

Candela

Zollo

, et al. Augmented reality, virtual reality and artificial intelligence in orthopedic surgery: a systematic review. Appl Sci 2021; 11: 3253. DOI: 10.3390/app11073253

37.

Liu

Zhang

, et al. Application of artificial intelligence in medicine: an overview. Curr Med Sci 2021; 41: 1105–1115. DOI: 10.1007/s11596-021-2474-3

38.

Kuo

RYL

Harrison

Curran

, et al. Artificial intelligence in fracture detection: a systematic review and meta-analysis. Radiology 2022; 304: 50–62. DOI: 10.1148/radiol.211785

39.

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. DOI: 10.1186/s13018-022-03408-7

40.

Shim

Kim

Yoon

, et al. Author Correction: automated rotator cuff tear classification using 3D convolutional neural network. Sci Rep 2021; 11: 15996. DOI: 10.1038/s41598-021-95469-7

41.

Kim

You

, et al. Development of an automatic muscle atrophy measuring algorithm to calculate the ratio of supraspinatus in supraspinous fossa using deep learning. Comput Methods Progr Biomed 2019; 182: 105063. DOI: 10.1016/j.cmpb.2019.105063

42.

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. DOI: 10.1002/jor.25036

43.

Gowd

Agarwalla

Amin

, et al. Construct validation of machine learning in the prediction of short-term postoperative complications following total shoulder arthroplasty. J Shoulder Elbow Surg 2019; 28: e410-e421. DOI: 10.1016/j.jse.2019.05.017

44.

Arvind

London

Cirino

, et al. Comparison of machine learning techniques to predict unplanned readmission following total shoulder arthroplasty. J Shoulder Elbow Surg 2021; 30: e50-e59. DOI: 10.1016/j.jse.2020.05.013

45.

Karnuta

Churchill

Haeberle

, et al. The value of artificial neural networks for predicting length of stay, discharge disposition, and inpatient costs after anatomic and reverse shoulder arthroplasty. J Shoulder Elbow Surg 2020; 29: 2385–2394. DOI: 10.1016/j.jse.2020.04.009

46.