Sage Journals: Discover world-class research

Abstract

French

Background: Artificial intelligence (AI) has significantly influenced various sectors, including healthcare, by enhancing machine capabilities in assisting with human tasks. In surgical fields, where precision and timely decision-making are crucial, AI's integration could revolutionize clinical quality and health resource optimization. This study explores the current and future applications of AI technologies in reconstructive breast surgery, aiming for broader implementation. Methods: We conducted systematic reviews through PubMed, Web of Science, and Google Scholar using relevant keywords and MeSH terms. The focus was on the main AI subdisciplines: machine learning, computer vision, natural language processing, and robotics. This review includes studies discussing AI applications across preoperative, intraoperative, postoperative, and academic settings in breast plastic surgery. Results: AI is currently utilized preoperatively to predict surgical risks and outcomes, enhancing patient counseling and informed consent processes. During surgery, AI supports the identification of anatomical landmarks and dissection strategies and provides 3-dimensional visualizations. Robotic applications are promising for procedures like microsurgical anastomoses, flap harvesting, and dermal matrix anchoring. Postoperatively, AI predicts discharge times and customizes follow-up schedules, which improves resource allocation and patient management at home. Academically, AI offers personalized training feedback to surgical trainees and aids research in breast reconstruction. Despite these advancements, concerns regarding privacy, costs, and operational efficacy persist and are critically examined in this review. Conclusions: The application of AI in breast plastic and reconstructive surgery presents substantial benefits and diverse potentials. However, much remains to be explored and developed. This study aims to consolidate knowledge and encourage ongoing research and development within the field, thereby empowering the plastic surgery community to leverage AI technologies effectively and responsibly for advancing breast reconstruction surgery.

Keywords

artificial intelligence innovation plastic surgery breast reconstruction

Introduction

The modern world is at an apogee of technological advances. Machines are becoming more capable than ever through novel computing paradigms, with a noteworthy one being artificial intelligence (AI). AI may be best understood as the emulation of human intelligence and cognitive processes by computer systems, an idea incepted in the mid-20th century as Turing famously questioned: “Can machines think?”¹ AI-powered machines leverage autonomous perception, synthesis, and inference of information in assisting with and accomplishing real-world tasks. Recently, the unveiling of ChatGPT (OpenAI), an AI-powered chatbot, represented yet another big step forward and only serves as a contemporary testament to the rapidly evolving nature of this field.

In healthcare, AI holds a prominent and promising role that has the potential to drastically improve care.² Surgical specialties are unique in that they place great emphasis on hands-on manipulation, technical minutiae, and preoperative guidelines to assess risk factors and predict outcomes, making them potentially suitable candidates for incorporation of AI processes. Breast surgery is an especially diverse subfield, situated at the intersection of multiple surgical specialities who collaborate in a common, synergistic manner aiming to provide the best possible care for breast cancer patients. Trends in recent years depict increasing numbers of breast cancer diagnoses and breast reconstructions alike, making it an unequivocally key health service moving forward.^3,4

Previous investigations have looked at AI in breast surgery but were mainly focused on breast cancer diagnosis and management, with little consideration to the reconstructive component.⁵ While the role of AI specifically to plastic surgery has been examined, breast reconstruction did not figure as a focal discussion point.⁶ In this context, it is the authors’ aim in the present study to scope the current literature in order to present a comprehensive review of applications of AI-based technologies on the plastic and reconstructive front of breast surgery. Modern examples, as well as perspectives on future directions, will be incorporated to streamline, bolster, and concretize theoretical and conceptual frameworks presented.

Methods

A literature search of the PubMed database was performed using keywords and MeSH terms. AI-related terms included permutations of “artificial intelligence,” “machine learning,” “computer vision,” “natural language processing,” and “robotics.” These terms were searched in each of the following contexts: “preoperative,” “intraoperative,” “postoperative,” “education,” or “research.” Complementary searches using the same strategy were subsequently reproduced on Google Scholar and Web of Science for widened coverage. On top of systematic searches, cross-referencing allowed to uncover additional applications of AI, as well as applications in other fields that are of interest to breast reconstruction. Original and review articles pertaining to demonstrated applications of AI in breast reconstruction were considered; studies in other specialties were referenced in the discussion of future directions. We excluded opinion-based articles without original or demonstrated findings.

AI Lexicology and Main Branches

It is worthwhile to lay out selected fundamental knowledge and clarify terminology to homogenize understanding of key points before delving into technical discussions. Machine learning, often mixed interchangeably with AI, is a subdiscipline that enables improvement of computer decision-making based on learning experience gained from vast amounts of data.^7,8 Besides machine learning, AI also manifests within other frameworks. Through computer vision, computers can interact with the visual world by perceiving and processing inputs such as images and videos.⁹ Natural language processing (NLP), on the other hand, allows computers to understand human language in its written and/or spoken forms.¹⁰ Robotics provides computers with a tangible outlet to human reality, enabling them to manipulate physical objects by means of robots.¹¹

These individual concepts should not be viewed as disconnected entities; in reality, they interact in complementary and synergistic fashions to achieve powerful results. Computer vision and NLP may be cross-integrated to enhance input perception capabilities of AI-powered agents and empower them to tackle increasingly complex tasks. Both technologies may be paired with robots for enhanced functionalities.¹² The distribution of AI-related research is reflective of the high degree of interaction surrounding AI, as a preponderant body of studies are cross-disciplinary in nature.¹³ Figure 1 illustrates the dynamics between different branches of AI.

Figure 1.

Artificial intelligence and its main subdisciplines.

Preoperative Applications

Breast reconstructive surgery begins well before the surgical act itself. Preoperative patient evaluation and counselling is essential for operative success, as diverging patient characteristics may dictate the plastic surgeon's choice of technique employed.¹⁴ To this end, O’Neill et al¹⁵ have developed a machine learning-powered prediction model to assess patients’ risk of experiencing free-flap failure following microsurgical anastomosis. Based on patient and procedural characteristics, the model was able to predict whether deep inferior epigastric perforator (DIEP) reconstruction would be complicated by flap failure. Myung et al¹⁶ have similarly utilized machine learning technology to predict donor site complications in free-flap breast reconstruction. Insights derived from these models may assist in the surgeon's choice of procedures by predicting postoperative morbidity given a patient's holistic profile.

Alternatively, even for a given surgical modality, machine learning prediction models can contribute to the informed consent process by providing patients with superior outcome forecasts than traditional methods.¹⁷ It is believed that machine learning is better situated than regression models to embrace the interconnectedness between individual risk factors for postoperative complications.¹⁸ A key distinction between the two is machine learning's ability to uncover trends and associations through autonomous learning, whereas regression models require prior subject knowledge for model specification.¹⁹ Indeed, Montemurro et al²⁰ utilized machine learning to decipher risk factors for complications ensuing breast augmentation that were beforehand unknown. A recent study by Didzbalis et al²¹ demonstrated an alternative role of machine learning, whereby it analyzed online patient inquiries regarding mastopexy to better understand concerns surrounding the procedure. Likewise, Chartier et al²² designed an AI-based algorithm capable of simulating surgical results of breast augmentation using preoperative photographs. Ultimately, machine learning holds promise for improving preoperative patient counselling and thus expectation management, which alone is correlated with higher levels of satisfaction postoperatively.^23,24

Future Directions

In breast reconstruction, preoperative models remain mostly tailored towards predicting outcomes based on patient data. With algorithmic refinement and sustained mass data collection, they could evolve into powerful tools paving way for precision medicine. From input of patient-specific information, algorithms can risk-stratify patients and propose tailored, individualized surgical management plans as well as testing/follow-up recommendations based on up-to-date scientific evidence and real-world data.²⁵ In so doing, integrating other aspects of AI to machine learning, such as NLP, will allow algorithms to access vaster information, such as past health records and other databases, to perform big data analytics.²⁶ By being integrated to major plastic surgery databases such as the Tracking Operations and Outcomes for Plastic Surgeons (TOPS) database, AI may help streamline data collection, organization, and analysis alike, overcoming current limitations of data registries and elevating evidence-based rigor in breast reconstructive care.²⁷ The resultant is enhanced patient medical history consideration, risk mitigation, and individualized need identification,²⁸ with modern AI paradigms demonstrating potential in uncovering social determinants of health within electronic medical records.²⁹ Ultimately, based on a patient's holistic makeup and personal preferences, AI can be expected to comment on the optimal reconstructive modality (eg, autologous or alloplastic), fine-tune settings within a chosen modality (eg, flap/implant choice, incision type, anesthesia strategy, etc), as well as recommend custom follow-up plans according to personalized risk for complications.³⁰

Intraoperative Applications

The surgical act is akin to a well-choreographed dance, requiring careful planning before physically intervening on the patient. Even after the initial incision, every gesture remains intentional and calculated, rooted in pre-established protocols and clinical flair. However, anatomical variations and human imprecision present a challenge to the surgeon's ability to navigate the often-unpredictable operative environment. In response, AI may help elucidate surgical anatomy through storage and processing of large quantities of patient-specific data from preoperative imaging beyond human capacities. As an example, Mavioso et al³¹ introduced computer-assisted detection of vessel in free-flap autologous breast reconstruction, outperforming manual detection by the human eye. Likewise, machine-assisted operative agents, such as robots, may minimize, nay eliminate, intrinsic flaws of human operators during surgery, with the potential to better surgical results.

Robotic Surgery

Robotic surgery has also been gaining increasing traction. Great leaps have been made since the performance of stereotactic brain surgery by the PUMA 200 robot and laparoscopic cholecystectomy using the da Vinci system, both landmark events of the field.^32,33 Noteworthily, the first robotic microsurgical anastomosis took place in the context of breast reconstruction.³⁴ A 2017 systematic review by Dobbs et al³⁵ identified microsurgery and flap harvest as the 2 aspects of breast surgery where robotic intervention was seen, though a significant proportion of related studies were constrained to the preclinical phase, suggesting nascency.³⁵ A 2020 systematic review of robots in breast surgery revealed superposable findings while adding nipple-sparing mastectomy to the scope of application.³⁶ More recently, a review by Chen et al³⁷ identified a role for robotic assistance in implant-based reconstruction, where the da Vinci system was used to anchor the acellular dermal matrix to the chest wall.³⁸ FDA approval of the first surgical robot dates back to 2000,³⁹ and robot assistance has become the gold standard for selected procedures within certain specialties such as urology.⁴⁰ In contrast to traditional human surgery, robotic surgery bears ergonomic benefits for surgeons, in addition to providing greater technical finesse by eliminating fundamental human flaws such as tremor and fatigue, leading to better postoperative outcomes.^41,42 Nevertheless, there remains to date no FDA-approved robotic-assisted plastic surgery applications, in part attributable to the specialty's procedural variety and infrequent cavitary access.⁴³ With significant foreshadowed expansion of the surgical robot market in coming years,⁴⁴ maintenance of the status quo will likely be short-lived. Joint efforts with the FDA have already been undertaken for approval of robotic-assisted flap harvest for breast reconstruction, showing favourable outcomes.⁴³ Along with preliminary data supporting long-term safety of robotic oncologic surgery, consensus from expert panels is starting to take form.^45,46 Innovative microsurgical robots are also being pushed out, namely, MicroSure's MUSA (Eindhoven, Netherlands) and the MMI's Symani surgical system (Calci, Italy), both holding preliminary clinical promise for supermicrosurgical manipulations such as lymphatic anastomoses and with green light for clinical application in Europe.^47,48 The additional precision conferred by robots becomes exponentially impactful as operative structures diminish in size, making them a natural fit for the microsurgical niche. Surgical robots can be expected to be made intelligent, as they grow equipped with the capacity to see (computer vision) and converse with the human surgeon (natural language processing), all while constantly self-adapting and self-improving from feedback (machine learning). Nevertheless, lingering cost barriers must be overcame,⁴⁹ and further multicentric evaluations remain necessary.^47,48

Intraoperative Guidance

AI's role in the intraoperative arena spans beyond robotic assistance. Novel research has been able to marry machine learning algorithms and ultrasound-based navigation to segmentate healthy and malignant tissue in real time, enhancing tumor resection.^50,51 Augmented reality (AR), though technically not encompassed by the AI umbrella, is a complementary technology whereby digital information is superimposed onto one's vision of the real world.⁵² It was first brought into the operating room in the context of orthopaedic, craniofacial, and spine surgeries.^53–56 AR headsets are slowly making their entry for breast surgery, where they have been employed for intraoperative tumor localization⁵⁷ and 3-dimensional visualization.^58,59 Interviews with plastic surgeons highlighted real-time anatomical visualization as the focal interest point for AR.⁵⁹ With a myriad of AR tools being currently developed—Holosurgical's ARAI, the VOSTARS system, Augmedics, Microsoft HoloLens, Google Glass, Magic Leap goggles, Apple's newly released Vision Pro, among others—more applications are expected to arise moving forwards. Recently, HoloLens’ role in breast reconstruction has been demonstrated—it superimposed computed tomography angiography imaging onto patients’ physical bodies, facilitating identification and dissection of perforators.⁶⁰

Future Directions

Intraoperatively, robotic breast surgery has huge untapped potential. A wider diversity of robotic machinery is being designed and tested, such as robotic microscopes, with or without integrated AR capabilities.⁶¹ The RoboticScope by BHS, approved for clinical use in Europe, has applications in both lymphatic and vascular anastomoses.^62,63 There has also been notions of robotic scrub nurses which can potentially optimize operating room workflow.⁶⁴ It is also prudent to suggest a future potential to equip surgical robots with computer vision or autonomous learning technologies, which would unlock higher levels of intelligence and autonomy, making robots able to perceive and adapt in real-time to the dynamic surgical environment.⁶⁵ To this end, there is a definitive need for unified data efforts to make available robust and standardized surgical data to facilitate and streamline training of intelligent surgical machinery.⁶⁶ With compelling success stories in other surgical specialties,⁶⁷ advancement of robotics and AR in breast surgery is possible, requiring interdisciplinary and cross-disciplinary collaboration between surgeons, radiologists, and scientists/engineers to push bio-entrepreneurial frontiers.^68,69 Though autonomous robotic surgery has been reported,⁷⁰ it is prudent to suggest that current focus be concentrated on consolidating evidence on robotic assistance before delving into robotic autonomy, which entails additional ethical considerations.

Postoperative Applications

Though specific postoperative applications of AI in breast reconstruction were absent from the literature, AI-powered chatbots have recently been investigated in the context of diagnosing, triaging, and managing complications following aesthetic breast plastic surgery.⁷¹ In orthopaedics, AI was used to develop an agent capable of selecting personalized follow-up times based on individual needs and vocally communicating them to patients in a humanly manner.⁷² Similar agents have been designed with the ability to estimate a patient's likelihood to be discharged given perioperative data.^73,74 With incorporation of NLP and other complementary functions, these agents may be further able to perceive and address patient concerns. Other directions of AI applications further down the postoperative course have been proposed, whereby researchers commented on the potential of AI involvement in assisting with at-home patient care following discharge.^75,76 Moving forwards, AI may grow into a key player in accompanying patients through their postoperative journey, simultaneously improving outcomes and alleviating utilization of finite healthcare resources.

Educational Applications

AR, together with virtual reality (VR), also holds great benefits for medical trainees. Indeed, AR was first introduced as a teaching tool for penile implant placement among urology residents.⁷⁷ By connecting real-world human gestures to the digital world, AR and VR are ideal channels for surgical education. Indeed, academic institutions such as the Mayo Clinic have already incorporated VR technologies into real-world surgical education.⁷⁸ A review by Bilgic et al⁷⁹ looked at the roles of AI in surgical education and highlighted a rising role of AI for the assessment and classification of surgical mastery, which may lead to the establishment of more objective competency metrics pertaining to breast reconstruction surgical techniques. Indeed, by being integrated into VR, AR, and/or robotic surgical simulators, AI may perform detailed analysis of kinematic information generated by the operator and return insightful feedback to improve surgical performance.⁸⁰ This might of particular benefit to technically intricate areas such as microvascular breast reconstruction by expediting resident operative exposure and growth, especially with the recent advent of AR therewithin.⁶⁰ Finally, plastic surgeons have demonstrated the potential of AI in contributing to scientific research,^81–84 as well as performing on plastic surgery in-service examinations.^85,86 Despite lingering ethical controversies, AI may evolve into a powerful scholarly adjunct to trainees in acquiring breast reconstruction knowledge and scientists in conducting breast reconstruction research, especially with active topics in need of further evidence (eg, BIA-ALCL, BIA-SCC, BII).^87–89

Discussion, Current Shortcomings, and Future Directions

Previous reviews of AI within breast surgery exist^5,90; the present study actualizes and comprehensively synthesizes knowledge in this nascent field to provide breast reconstruction surgeons and researchers with a primer for subsequent endeavours. Although AI is a well-established scientific discipline, its integration within healthcare is a recent movement. As such, there is a dire need for further work, starting from proofs of concepts, to in vivo evaluations, to eventual clinical translation. As with any novel scientific field, time will be required to gather and synthesize evidence and progressively climb up the evidence pyramid. Moreover, in this field where new findings embody a high degree of inventiveness, the optimal medium of communicating novelty may need to be revisited. Patents may constitute appropriate and suitable complements to scientific publications, and their basic principles may be worth understanding.⁹¹ Indeed, premature publication strips the possibility for patent protection of potentially deserving intellectual property.⁹¹

Incorporation of AI technologies should be done earlier than later, as harsh learning curves will need to be tamed before the full potential and benefits of AI can be appreciated, as seen in robotic surgery.⁹² In so doing, awareness of the existence of assessment tools is crucial to ensure consistent progress.^93,94 Once integral to the surgical workflow, AI has the potential to spur a veritable metamorphosis of current breast reconstruction care delivery and the healthcare system as a whole. By amping efficiency and bettering outcomes, greater numbers of patients in need could be seen, all the while maintaining high-quality standards. With breast reconstruction being a clear hotspot for health disparities,⁹⁵ AI could constitute an elegant solution in flattening currently observed inequities.

That said, AI is not without its limitations, most of which are ethical and financial in nature. While the upfront cost of AI technologies has been brought up as a clear barrier,^49,96 AI may ultimately reduce overall healthcare costs by optimizing both educational and clinical workflows.^97–99 Moving forwards, the cost-effectiveness of AI—or lack thereof—will need to be ascertained through rigorous economic evaluations. As for ethics, access to sensitive health information by AI draws concerns related to patient privacy and confidentiality.⁸³ Recent cases of malicious use of AI have been reported, where it was used to produce fake jurisprudence in legal defenses, as well as to generate child abuse images.^100–102 In preventing against similar catastrophes of AI misuse in the healthcare setting, compliance to existing legislative frameworks such as the Health Insurance Portability and Accountability Act (HIPAA) in the United States, or General Data Protection Regulation (GDPR) in Europe, or the Personal Information Protection and Electronic Documents Act (PIPEDA) in Canada, and relevant regulations in other regions will be crucial to ensure responsible adoption of AI; de novo policymaking may also be warranted. With AI becoming increasingly authoritative with regard to clinical decision-making and surgical navigation, the incorporation of AI machinery as a proper member of the care team, and the resultant role of surgeons therein, will need to be revisited. Responsibility assumption in the occurrence of a medical error also becomes a subject of debate. Nevertheless, before all, it is prudent to suggest that the efficiency, efficacy, and reliability of AI be cemented with continued research and development to minimize the weight posed by current limitations. In so doing, collaborative efforts should aim to provide standardized and accessible AI training datasets,^66,90 as well as validated and objective evaluation metrics and scales.¹⁰³

Conclusions

The territory yet unchartered by AI remains vast. Crystallized in this article is a review and discussion of current applications of AI in key domains of plastic and reconstructive breast surgery. With AI becoming ubiquitous in many aspects of human civilization, now, more than ever, is a crucial time for breast reconstruction surgeons to embrace this technology so as to not fall behind of an exponentially growing field. Aspiring trainees should seek to gain early familiarity and exposure, whereas established veterans should exercise adaptability and meet AI with their clinical experience to spark unique and valuable insights for optimal implementation.

Footnotes

Author Contributions

AG contributed to the conceptualization and design of the study, data analysis, and drafting of the manuscript. HX assisted with the data collection, data analysis, and contributed to the drafting and revision of the manuscript. HH played a significant role in the data interpretation, manuscript revision, and provided substantial clinical insights that shaped the research focus. HN contributed to the research design and revising the manuscript critically for important intellectual content. JL oversaw the research project, contributed to the study's conception and design, and critically revised the manuscript for key intellectual content. JV the corresponding author who led the research project, coordinated the collaboration between authors, and took the lead in revising the manuscript, and ensured the accuracy and integrity of the work.

Declaration of Conflicting Interests

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

Funding

The authors received no financial support for the research, authorship, and/or publication of this article.

ORCID iDs

Andrew Gorgy

Hassan El Hawary

Joshua Vorstenbosch

References

Turing

. I.—computing machinery and intelligence. Mind. 1950;LIX(236):433-460. doi:https://doi.org/10.1093/mind/LIX.236.433

Topol

. High-performance medicine: The convergence of human and artificial intelligence. Nat Med. 2019;25(1):44-56. doi:https://doi.org/10.1038/s41591-018-0300-7

U.S. Cancer Statistics Working Group. United States Cancer Statistics: Data Visualizations. Centers for Disease Control and Prevention and National Cancer Institute. Updated November 2022. https://gis.cdc.gov/Cancer/USCS/#/Trends/.

American Society of Plastic Surgeons. 2020. Plastic Surgery Statistics Report. https://www.plasticsurgery.org/documents/News/Statistics/2020/plastic-surgery-statistics-full-report-2020.pdf .

Soh

Shah

Arjomandi Rad

, et al. Present and future of machine learning in breast surgery: Systematic review. Br J Surg. 2022;109(11):1053-1062. doi:https://doi.org/10.1093/bjs/znac224

Kanevsky

Corban

Gaster

Kanevsky

Lin

Gilardino

. Big data and machine learning in plastic surgery: A new frontier in surgical innovation. Plast Reconstr Surg. 2016;137(5):890e-897e. doi:https://doi.org/10.1097/prs.0000000000002088

Samuel

. Some studies in machine learning using the game of checkers. IBM J Res Dev. 1959;3(3):210-229. doi:https://doi.org/10.1147/rd.33.0210

Alzubi

Nayyar

Kumar

. Machine learning from theory to algorithms: An overview. J Phys: Conf Ser. 2018;1142(1):012012. doi:https://doi.org/10.1088/1742-6596/1142/1/012012

Russell

. Artificial intelligence: A modern approach. Pearson Education, Inc.; 2010.

10.

Esteva

Robicquet

Ramsundar

, et al. A guide to deep learning in healthcare. Nat Med. Jan 2019;25(1):24-29. doi:https://doi.org/10.1038/s41591-018-0316-z

11.

Lanfranco

Castellanos

Desai

Meyers

. Robotic surgery: A current perspective. Ann Surg. Jan 2004;239(1):14-21. doi:https://doi.org/10.1097/01.sla.0000103020.19595.7d

12.

Geiger

Lenz

Stiller

Urtasun

. Vision meets robotics: The kitti dataset. Int J Rob Res. 2013;32(11):1231-1237.

13.

Toney

. Defining computer vision, natural language processing, and robotics research clusters. CSET; 2021. https://cset.georgetown.edu/publication/defining-computer-vision-natural-language-processing-and-robotics-research-clusters/

14.

Zhong

McCarthy

Price

Pusic

. Evidence-based medicine: Breast reconstruction. Plast Reconstr Surg. 2013;132(6):1658-1669. doi:https://doi.org/10.1097/PRS.0b013e3182a80836

15.

O'Neill

Yang

Roy

Sebastiampillai

Hofer

SOP

. Development and evaluation of a machine learning prediction model for flap failure in microvascular breast reconstruction. Ann Surg Oncol. Sep 2020;27(9):3466-3475. doi:https://doi.org/10.1245/s10434-020-08307-x

16.

Myung

Jeon

Heo

, et al. Validating machine learning approaches for prediction of donor related complication in microsurgical breast reconstruction: A retrospective cohort study. Sci Rep. 2021;11(1):5615. doi:https://doi.org/10.1038/s41598-021-85155-z

17.

Kruppa

Ziegler

König

. Risk estimation and risk prediction using machine-learning methods. Hum Genet. 2012;131(10):1639-1654. doi:https://doi.org/10.1007/s00439-012-1194-y

18.

Roy

Sebastiampillai

Zhong

Hofer

SOP

O'Neill

. Synergistic interaction increases complication rates following microvascular breast reconstruction. Plast Reconstr Surg. Jul 2019;144(1):1e-8e. doi:https://doi.org/10.1097/prs.0000000000005695

19.

Breiman

. Statistical modeling: The two cultures (with comments and a rejoinder by the author). Stat Sci. 2001;16(3):199-231.

20.

Montemurro

Lehnhardt

Behr

Wallner

. A machine learning approach to identify previously unconsidered causes for complications in aesthetic breast augmentation. Aesthetic Plast Surg. Dec 2022;46(6):2669-2676. doi:https://doi.org/10.1007/s00266-022-02997-2

21.

Didzbalis

Tseng

Weisberger

Gama

Lee

. A machine learning analysis of patient concerns regarding mastopexy. J Plast Reconstr Aesthet Surg. Jan 2023;76:71-75. doi:https://doi.org/10.1016/j.bjps.2022.10.007

22.

Chartier

Watt

Lin

Chandawarkar

Lee

Hall-Findlay

. BreastGAN: Artificial intelligence-enabled breast augmentation simulation. Aesthet Surg J Open Forum. 2022;4:ojab052. doi:https://doi.org/10.1093/asjof/ojab052

23.

Noble

Conditt

Cook

Mathis

. The John Insall Award: Patient expectations affect satisfaction with total knee arthroplasty. Clin Orthop Relat Res. Nov 2006;452:35-43. doi:https://doi.org/10.1097/01.blo.0000238825.63648.1e

24.

Waljee

McGlinn

Sears

Chung

. Patient expectations and patient-reported outcomes in surgery: A systematic review. Surgery. May 2014;155(5):799-808. doi:https://doi.org/10.1016/j.surg.2013.12.015

25.

Kim

Kelley

Nasser

Chung

. Implementing precision medicine and artificial intelligence in plastic surgery: Concepts and future prospects. Plast Reconstr Surg Glob Open. 2019;7(3):e2113. doi:https://doi.org/10.1097/gox.0000000000002113

26.

Cheng

Kaddi

Venugopalan

Hoffman

Wang

. Omic and electronic health record big data analytics for precision medicine. IEEE Trans Biomed Eng. 2017;64(2):263-273. doi:https://doi.org/10.1109/tbme.2016.2573285

27.

Abi-Rafeh

Davison

Winocour

Reece

Vorstenbosch

. Prompting rigor in database reporting: Working towards higher quality plastic surgery database research. Plast Reconstr Surg. 2021;153. doi:https://doi.org/10.1097/prs.0000000000011157

28.

Ren

Loftus

Datta

, et al. Performance of a machine learning algorithm using electronic health record data to predict postoperative complications and report on a Mobile platform. JAMA Network Open. 2022;5(5):e2211973-e2211973. doi:https://doi.org/10.1001/jamanetworkopen.2022.11973

29.

Guevara

Chen

Thomas

, et al. Large language models to identify social determinants of health in electronic health records. npj Digital Medicine. 2024;7(1):6. doi:https://doi.org/10.1038/s41746-023-00970-0

30.

Lambrechts

Wirix-Speetjens

Maes

Van Huffel

. Artificial intelligence based patient-specific preoperative planning algorithm for total knee arthroplasty. Front Robot AI. 2022;9:840282. doi:https://doi.org/10.3389/frobt.2022.840282

31.

Mavioso

Araújo

Oliveira

, et al. Automatic detection of perforators for microsurgical reconstruction. Breast. 2020;50:19-24. doi:https://doi.org/10.1016/j.breast.2020.01.001

32.

Kwoh

Hou

Jonckheere

Hayati

. A robot with improved absolute positioning accuracy for CT guided stereotactic brain surgery. IEEE Trans Biomed Eng. 1988;35(2):153-160. doi:https://doi.org/10.1109/10.1354

33.

Ballantyne

. Robotic surgery, telerobotic surgery, telepresence, and telementoring. Review of early clinical results. Surg Endosc. Oct 2002;16(10):1389-1402. doi:https://doi.org/10.1007/s00464-001-8283-7

34.

van der Hulst

Sawor

Bouvy

. Microvascular anastomosis: Is there a role for robotic surgery? J Plast Reconstr Aesthet Surg. 2007;60(1):101-102. doi:https://doi.org/10.1016/j.bjps.2006.05.011

35.

Dobbs

Cundy

Samarendra

Khan

Whitaker

. A systematic review of the role of robotics in plastic and reconstructive surgery-from inception to the future. Front Surg. 2017;4:66. doi:https://doi.org/10.3389/fsurg.2017.00066

36.

Donnely

Griffin

Butler

. Robotic surgery: A novel approach for breast surgery and reconstruction. Plast Reconstr Surg Glob Open. Jan 2020;8(1):e2578. doi:https://doi.org/10.1097/gox.0000000000002578

37.

Chen

Zhang

Beeraka

, et al. Robot-Assisted minimally invasive breast surgery: Recent evidence with comparative clinical outcomes. J Clin Med. 25 2022;11(7):1827. doi:https://doi.org/10.3390/jcm11071827

38.

Parcells

Spiro

. Exploration of robotic direct to implant breast reconstruction. Plast Reconstr Surg Glob Open. Jan 2020;8(1):e2619. doi:https://doi.org/10.1097/gox.0000000000002619

39.

Food And Drug Administration. FDA Approves New Robotic Surgery Device. ScienceDaily. https://www.sciencedaily.com/releases/2000/07/000717072719.htm.

40.

Ramsay

Pickard

Robertson

, et al. Systematic review and economic modelling of the relative clinical benefit and cost-effectiveness of laparoscopic surgery and robotic surgery for removal of the prostate in men with localised prostate cancer. Health Technol Assess. 2012;16(41):1-313. doi:https://doi.org/10.3310/hta16410

41.

Hussain

Malik

Halim

Ali

. The use of robotics in surgery: A review. Int J Clin Pract. Nov 2014;68(11):1376-1382. doi:https://doi.org/10.1111/ijcp.12492

42.

Wee

IJY

Kuo

Ngu

. A systematic review of the true benefit of robotic surgery: Ergonomics. Int J Med Robot. Aug 2020;16(4):e2113. doi:https://doi.org/10.1002/rcs.2113

43.

Shuck

Asaad

Liu

Clemens

Selber

. Prospective pilot study of robotic-assisted harvest of the Latissimus dorsi muscle: A 510(k) approval study with U.S. Food and drug administration investigational device exemption. Plast Reconstr Surg. 2022;149(6):1287-1295. doi:https://doi.org/10.1097/prs.0000000000009086

44.

MarketResearch.com. Micro Surgical Robot Market Analysis and Forecast to 2031: By Application (Urology Surgery, Plastic Reconstructive Surgery, Ophthalmic Surgery, Neurosurgery, Lymphatic Surgery, ENT Surgery, Others), End User (Hospitals & Clinics, Ambulatory Surgical Centers, Research Institutes, Others), and Region. https://www.marketresearch.com/Global-Insight-Services-v4248/Micro-Surgical-Robot-Forecast-Application-32810592/.

45.

Wan

Liang

Chen

, et al. Association of long-term oncologic prognosis with minimal access breast surgery vs conventional breast surgery. JAMA Surg. Dec 1 2022;157(12):e224711. doi:https://doi.org/10.1001/jamasurg.2022.4711

46.

Lai

Toesca

Sarfati

, et al. Consensus statement on robotic mastectomy-expert panel from international endoscopic and robotic breast surgery symposium (IERBS) 2019. Ann Surg. 2020;271(6):1005-1012. doi:https://doi.org/10.1097/sla.0000000000003789

47.

van Mulken

TJM

Schols

Scharmga

AMJ

, et al. First-in-human robotic supermicrosurgery using a dedicated microsurgical robot for treating breast cancer-related lymphedema: A randomized pilot trial. Nat Commun. Feb 11 2020;11(1):757. doi:https://doi.org/10.1038/s41467-019-14188-w

48.

Lindenblatt

Grünherz

Wang

, et al. Early experience using a new robotic microsurgical system for lymphatic surgery. Plast Reconstr Surg Glob Open. Jan 2022;10(1):e4013. doi:https://doi.org/10.1097/gox.0000000000004013

49.

Tsakonas

Tran

, et al. CADTH Health Technology Assessments. Robot-Assisted Surgery Compared with Open Surgery and Laparoscopic Surgery: Clinical Effectiveness and Economic Analyses. Canadian Agency for Drugs and Technologies in Health. Copyright © CADTH September 2011.; 2011.

50.

Nasute Fauerbach

Yeung

, et al. Real-time automatic tumor segmentation for ultrasound-guided breast-conserving surgery navigation. Int J Comput Assist Radiol Surg. Sep 2022;17(9):1663-1672. doi:https://doi.org/10.1007/s11548-022-02658-4

51.

Alqaoud

Plemmons

Feliberti

, et al. nnUNet-based multi-modality breast MRI segmentation and tissue-delineating phantom for robotic tumor surgery planning. Annu Int Conf IEEE Eng Med Biol Soc. Jul 2022;2022:3495-3501. doi:https://doi.org/10.1109/embc48229.2022.9871109

52.

Lee

Moshrefi

Fuertes

Veeravagu

Nazerali

Lin

. What is your reality? Virtual, augmented, and mixed reality in plastic surgery training, education, and practice. Plast Reconstr Surg. 2021;147(2):505-511. doi:https://doi.org/10.1097/prs.0000000000007595

53.

Cercenelli

Carbone

Condino

, et al. The wearable VOSTARS system for augmented reality-guided surgery: Preclinical phantom evaluation for high-precision maxillofacial tasks. J Clin Med. Nov 5 2020;9(11):3562. doi:https://doi.org/10.3390/jcm9113562

54.

Molina

Theodore

Ahmed

, et al. Augmented reality-assisted pedicle screw insertion: A cadaveric proof-of-concept study. J Neurosurg Spine. Mar 29 2019;31:1-8. doi:https://doi.org/10.3171/2018.12.Spine181142

55.

Siemionow

Katchko

Lewicki

Luciano

. Augmented reality and artificial intelligence-assisted surgical navigation: Technique and cadaveric feasibility study. J Craniovertebr Junction Spine. Apr‐Jun 2020;11(2):81-85. doi:https://doi.org/10.4103/jcvjs.JCVJS_48_20

56.

Ponce

Menendez

Oladeji

Fryberger

Dantuluri

. Emerging technology in surgical education: Combining real-time augmented reality and wearable computing devices. Orthopedics. Nov 2014;37(11):751-757. doi:https://doi.org/10.3928/01477447-20141023-05

57.

Gouveia

Costa

Morgado

, et al. Breast cancer surgery with augmented reality. Breast. 2021;56:14-17. doi:https://doi.org/10.1016/j.breast.2021.01.004

58.

Khang

Park

Lee

Kim

Song

Lee

. Computer-Aided breast surgery framework using a markerless augmented reality method. Diagnostics (Basel). Dec 11 2022;12(12):3123. doi:https://doi.org/10.3390/diagnostics12123123

59.

Nicklaus

Wang

Bordes

, et al. Potential of intraoperative 3D photography and 3D visualization in breast reconstruction. Plast Reconstr Surg Glob Open. Oct 2021;9(10):e3845. doi:https://doi.org/10.1097/gox.0000000000003845

60.

Masterton

Miller

Patel

Pratt

Gosling

Saour

. Hololens in breast reconstruction: What is the future? Plast Reconstr Surg. 2023;151(6):915e-917e. doi:https://doi.org/10.1097/prs.0000000000010158

61.

Aitzetmüller

Klietz

Dermietzel

Hirsch

Kückelhaus

. Robotic-Assisted microsurgery and its future in plastic surgery. J Clin Med. Jun 13 2022;11(12):3378. doi:https://doi.org/10.3390/jcm11123378

62.

Boehm

Schuler

Riepl

Schild

Hoffmann

Greve

. Performance of microvascular anastomosis with a new robotic visualization system: Proof of concept. J Robot Surg. 2022;16(3):705-713. doi:https://doi.org/10.1007/s11701-021-01294-5

63.

Scaglioni

Meroni

Fritsche

Linder

Rajan

. Use of the BHS robotic scope to perform lymphovenous anastomosis. Microsurgery. 2021;41(3):298-299. doi:https://doi.org/10.1002/micr.30704

64.

Jacob

Akingba

Wachs

. Gestonurse: A robotic surgical nurse for handling surgical instruments in the operating room. J Robot Surg. 2012;6(1):53-63. doi:https://doi.org/10.1007/s11701-011-0325-0

65.

Kober

Bagnell

Peters

. Reinforcement learning in robotics: A survey. Int J Rob Res. 2013;32(11):1238-1274. doi:https://doi.org/10.1177/0278364913495721

66.

Ahmidi

Tao

Sefati

, et al. A dataset and benchmarks for segmentation and recognition of gestures in robotic surgery. IEEE Trans Biomed Eng. Sep 2017;64(9):2025-2041. doi:https://doi.org/10.1109/tbme.2016.2647680

67.

Chang

Wagner

Regan

, et al. Prospective multicenter comparison of open and robotic radical prostatectomy: The PROST-QA/RP2 consortium. J Urol. Jan 2022;207(1):127-136. doi:https://doi.org/10.1097/ju.0000000000002176

68.

Bhandari

Zeffiro

Reddiboina

. Artificial intelligence and robotic surgery: Current perspective and future directions. Curr Opin Urol. Jan 2020;30(1):48-54. doi:https://doi.org/10.1097/mou.0000000000000692

69.

Panesar

Cagle

Chander

Morey

Fernandez-Miranda

Kliot

. Artificial intelligence and the future of surgical robotics. Ann Surg. 2019;270(2):223-226. doi:https://doi.org/10.1097/sla.0000000000003262

70.

Shademan

Decker

Opfermann

Leonard

Krieger

Kim

. Supervised autonomous robotic soft tissue surgery. Sci Transl Med. May 4 2016;8(337):337ra64. doi:https://doi.org/10.1126/scitranslmed.aad9398

71.

Abi-Rafeh

Henry

, et al. Utility and comparative performance of current artificial intelligence large language models as postoperative medical support chatbots in aesthetic surgery. Aesthetic Surg J. 2024. doi:https://doi.org/10.1093/asj/sjae025

72.

Bian

Xiang

Tong

Feng

Weng

. Artificial intelligence-assisted system in postoperative follow-up of orthopedic patients: Exploratory quantitative and qualitative study. J Med Internet Res. May 26 2020;22(5):e16896. doi:https://doi.org/10.2196/16896

73.

Safavi

Khaniyev

Copenhaver

, et al. Development and validation of a machine learning model to aid discharge processes for inpatient surgical care. JAMA Network Open. 2019;2(12):e1917221-e1917221. doi:https://doi.org/10.1001/jamanetworkopen.2019.17221

74.

van de Sande

van Genderen

Verhoef

, et al. Predicting need for hospital-specific interventional care after surgery using electronic health record data. Surgery. Sep 2021;170(3):790-796. doi:https://doi.org/10.1016/j.surg.2021.05.005

75.

Kim

Yefimova

Lin

Jopling

Hansen

. A home-recovery surgical care model using AI-driven measures of activities of daily living. NEJM Catalyst Innov Care Delivery. 2022. doi:https://doi.org/10.1056/CAT.22.0081

76.

Pathak

Marwaha

Tsai

. The role of digital technology in surgical home hospital programs. npj Digital Medicine. 2023;6(1):22. doi:https://doi.org/10.1038/s41746-023-00750-w

77.

Hakky

Daniel

Larry

Philippe

Rafael

. MP23-11 Augmented reality assisted urologic surgery (araus): A surgical training tool. J Urol. 2015;193(4S):e271-e271. doi:https://doi.org/10.1016/j.juro.2015.02.1254

78.

HMT Mag. Mayo Clinic becomes first U.S. institution to train surgeons with Fundamental Surgery VR haptic simulations. Healthcare Innovation. https://www.hcinnovationgroup.com/home/article/13011124/mayo-clinic-becomes-first-us-institution-to-train-surgeons-with-fundamental-surgery-vr-haptic-simulations .

79.

Bilgic

Gorgy

Yang

, et al. Exploring the roles of artificial intelligence in surgical education: A scoping review. Am J Surg. Jul 2022;224(1 Pt A):205-216. doi:https://doi.org/10.1016/j.amjsurg.2021.11.023

80.

Guerrero

Asaad

Rajesh

Hassan

Butler

. Advancing surgical education: The use of artificial intelligence in surgical training. Am Surgeon™. 2023;89(1):49-54. doi:https://doi.org/10.1177/00031348221101503

81.

van Dis

EAM

Bollen

Zuidema

van Rooij

Bockting

. ChatGPT: Five priorities for research. Nature. 2023;614:224-226. doi:https://doi.org/10.1038/d41586-023-00288-7

82.

ElHawary

Gorgy

Janis

. Large language models in academic plastic surgery: The way forward. Plast Reconstr Surg Glob Open. Apr 2023;11(4):e4949. doi:https://doi.org/10.1097/gox.0000000000004949

83.

Abi-Rafeh

Kazan

Tevlin

Furnas

. Large language models and artificial intelligence: A primer for plastic surgeons on the demonstrated & potential applications, promises, and limitations of ChatGPT. Aesthetic Surg J. 2023;44:329-343. doi:https://doi.org/10.1093/asj/sjad260

84.

Abi-Rafeh

Kazan

. Preservation of human creativity in plastic surgery research on ChatGPT. Aesthetic Surg J. 2023;43(9):NP726-NP727. doi:https://doi.org/10.1093/asj/sjad162

85.

Humar

Asaad

Bengur

Nguyen

. ChatGPT is equivalent to first-year plastic surgery residents: Evaluation of ChatGPT on the plastic surgery in-service examination. Aesthetic Surg J. 2023;43(12):NP1085-NP1089. doi:https://doi.org/10.1093/asj/sjad130

86.

Gupta

Herzog

Park

, et al. Performance of ChatGPT on the plastic surgery inservice training examination. Aesthet Surg J. 2023;43(12):Np1078-np1082. doi:https://doi.org/10.1093/asj/sjad128

87.

U.S. Food and Drug Administration. UPDATE: Reports of Squamous Cell Carcinoma (SCC) in the Capsule Around Breast Implants - FDA Safety Communication. https://www.fda.gov/medical-devices/safety-communications/update-reports-squamous-cell-carcinoma-scc-capsule-around-breast-implants-fda-safety-communication.

88.

U.S. Food and Drug Administration. Breast Implants: Reports of Squamous Cell Carcinoma and Various Lymphomas in Capsule Around Implants: FDA Safety Communication. https://www.fda.gov/medical-devices/safety-communications/breast-implants-reports-squamous-cell-carcinoma-and-various-lymphomas-capsule-around-implants-fda .

89.

U.S. Food and Drug Administration. Medical Device Reports of Breast Implant-Associated Anaplastic Large Cell Lymphoma. https://www.fda.gov/medical-devices/breast-implants/medical-device-reports-breast-implant-associated-anaplastic-large-cell-lymphoma .

90.

Seth

Bulloch

Joseph

Hunter-Smith

Rozen

. Use of artificial intelligence in the advancement of breast surgery and implications for breast reconstruction: A narrative review. J Clin Med. Aug 6 2023;12(15):5143. doi:https://doi.org/10.3390/jcm12155143

91.

Kazan

Zammit

, et al. Effective strategies to patent plastic surgery ideas and intellectual property. Plast Reconstr Surg. Dec 23 2022. doi:https://doi.org/10.1097/prs.0000000000010050

92.

White

Frederick

Zimmerman

Carroll

Magnuson

. Learning curve for transoral robotic surgery: A 4-year analysis. JAMA Otolaryngol Head Neck Surg. 2013;139(6):564-567. doi:https://doi.org/10.1001/jamaoto.2013.3007

93.

Alrasheed

Liu

Hanasono

Butler

Selber

. Robotic microsurgery: Validating an assessment tool and plotting the learning curve. Plast Reconstr Surg. Oct 2014;134(4):794-803. doi:https://doi.org/10.1097/prs.0000000000000550

94.

Selber

Alrasheed

. Robotic microsurgical training and evaluation. Semin Plast Surg. 2014;28(1):5-10. doi:https://doi.org/10.1055/s-0034-1368161

95.

Baxter

Howard

Chung

. A systematic review of health disparities research in plastic surgery. Plast Reconstr Surg. 2021;147(3):529-537. doi:https://doi.org/10.1097/prs.0000000000007682

96.

Jimenez

Stanton

Sung

Wong

. Does plastic surgery need a rewiring? A survey and systematic review on robotic-assisted surgery. JPRAS Open. Sep 2022;33:76-91. doi:https://doi.org/10.1016/j.jpra.2022.05.006

97.

Babineau

Becker

Gibbons

, et al. The “cost” of operative training for surgical residents. Arch Surg. Apr 2004;139(4):366-369. doi:https://doi.org/10.1001/archsurg.139.4.366

98.

Malloy

Sanchez

Cho

Mulcahy

Labow

. Hidden costs in resident training: Financial cohort analysis of first assistants in reduction mammaplasty. Plast Reconstr Surg Glob Open. Jan 2021;9(1):e3333. doi:https://doi.org/10.1097/gox.0000000000003333

99.

Lohre

Bois

Pollock

, et al. Effectiveness of immersive virtual reality on orthopedic surgical skills and knowledge acquisition among senior surgical residents: A randomized clinical trial. JAMA Netw Open. Dec 1 2020;3(12):e2031217. doi:https://doi.org/10.1001/jamanetworkopen.2020.31217

100.

Weiser

. Here’s What Happens When Your Lawyer Uses ChatGPT. The New York Times. https://www.nytimes.com/2023/05/27/nyregion/avianca-airline-lawsuit-chatgpt.html.

101.

Australian Federal Police. Victorian man jailed for producing almost 800 AI-generated child abuse images. https://www.afp.gov.au/news-centre/media-release/victorian-man-jailed-producing-almost-800-ai-generated-child-abuse-images .

102.

Thiel

. Investigation finds al image generation models trained on child abuse. Stanford Cyber Policy Center. https://cyber.fsi.stanford.edu/news/investigation-finds-ai-image-generation-models-trained-child-abuse .

103.

Abi-Rafeh

Kazan

Furnas

. Medical applications of artificial intelligence and large language models: Bibliometric analysis and stern call for improved publishing practices. Aesthetic Surg J. Aug 23 2023;43(12):NP1098-NP1100. doi:https://doi.org/10.1093/asj/sjad277

Integrating AI into Breast Reconstruction Surgery: Exploring Opportunities,Applications,and Challenges

Abstract

Keywords

Introduction

Methods

AI Lexicology and Main Branches

Preoperative Applications

Future Directions

Intraoperative Applications

Robotic Surgery

Intraoperative Guidance

Future Directions

Postoperative Applications

Educational Applications

Discussion, Current Shortcomings, and Future Directions

Conclusions

Footnotes

Author Contributions

Declaration of Conflicting Interests

Funding

ORCID iDs

References