Skip to main content
NCBI home page
JPRAS Open logoLink to JPRAS Open
. 2024 Sep 14;42:234–243. doi: 10.1016/j.jpra.2024.09.003

Artificial intelligence in plastic surgery, where do we stand?

Omar Kiwan b, Mohammed Al-Kalbani b, Arash Rafie a, Yasser Hijazi a,⁎
PMCID: PMC11491964  PMID: 39435018

Abstract

Since the pandemic, artificial intelligence (AI) has been integrated into several fields and everyday life as well. Healthcare is not an exception. Plastic surgery is a key focus area of this technological revolution, with hundreds of studies and reviews already published on the use of AI in plastics. This review summarizes the entirety of the available literature from 2020 to provide a comprehensive overview on AI innovation in plastic surgery.

A systematic literature review (following the PRISMA guidelines) of all studies and papers that examined the application of AI in plastic surgery was carried out using Medline, Cochrane, Embase, and Google Scholar.

Outcomes of interest included the growing role of AI in clinical consultations, diagnosing potentials, surgical planning, intraoperative, and post-operative uses. Ninety-six studies were included in this review; six examined the role of AI in consultations, fifteen used AI in diagnoses and assessments, seventeen involved AI in surgical planning, fifteen reported on AI use in post-operative predictions and management, and nine involved administrations and documentation.

This comprehensive review of available literature found AI to be capable of transforming care throughout the entire patient journey. Certain challenges and concerns persist, but a collaborative effort can solve these issues to bring about a new era of medicine, where AI aids doctors in the pursuit of optimal patient care.

Keywords: Artificial intelligence, Plastic surgery, Machine learning, Aesthetic surgery

Introduction

Since the pandemic, artificial intelligence (AI) has been integrated into several fields and everyday life as well. Healthcare is not an exception. Organizations such as the United Kingdom's National Health Service have invested large sums into Healthcare AI development. It is expected that the NHS’ 21-million-pound investment on AI tools will result in economic gains of 235 million pounds over the next 5 years.1 AI has the potential to provide a creative solution to significant issues in the NHS caused by the lack of funding,2 such as the staffing crisis.3

Plastic surgery is a key focus area of this technological revolution, with hundreds of studies and reviews already published on AI use in the field. Integrating technology has long been a focus of plastic surgery. Robotic surgery, for example, is being established in plastics, with several studies demonstrating the improved safety and outcomes.4,5 The scope and potential benefits of AI are much more widespread, as it could impact the entire patient journey from the initial assessment to post-op monitoring. This review looked into the growing role of AI in clinical consultation, diagnostic potentials, surgical planning, intraoperative aid, and post-operative monitoring in the field of plastic surgery.

Methods

A systematic literature review (following the PRISMA guidelines) of all studies and papers that examined AI in plastic surgery was performed using Medline, Cochrane, Embase, and Google Scholar. Outcomes of interest included the growing role of AI in clinical consultations, diagnosing potentials, surgical planning, intraoperative, and post-operative uses.

Results

Following the identification of 812 studies that involved AI in surgery, 716 studies were excluded so that only those related to plastic surgery were included (Figure 1). Among the 96 remaining studies, six examined the role of AI in consultations, fifteen used AI in diagnoses and assessments, seventeen involved AI in surgical planning, fifteen checked AI in post-operative predictions and management, and nine involved administration and documentation (Figure 2). In addition, four were related to aesthetic surgery, 5 to breast surgery, six to burns, two to hand surgery, fourteen to head and neck, eight to microsurgery, seven to oculoplastics, and seven to skin and wounds (Figure 3). The reasons for exclusion were that the study is not relevant, is a duplicate, is an opinion, has no clinical role, is an animal study, or that the translation could not be found.

Figure 1.

Figure 1

Open in a new tab

Flow-gram of study selection.

Figure 2.

Figure 2

Open in a new tab

Categories of the assorted studies used. Studies categorized as “Other” include those in education, research, and imaging.

Figure 3.

Figure 3

Open in a new tab

Subspecialty breakdown in different aspects of plastic surgery.

AI in clinical consultations

Consultations are essential in formulating the right differentials and management plan for a patient. They also help build patient rapport and trust in the medical team. Having AI take over consultations is ambitious and difficult to accept. When it comes to knowledge, the popular AI chatbot chat generative pre-trained transformer (ChatGPT) has been shown to perform on a similar level to a first-year plastics trainee on the in-service exam, achieving a score in the 49th percentile.6 It is likely that AI trained in plastic surgery would achieve a much higher score. A study using ChatGPT for blepharoptosis consultations found that it provided better information than experienced plastic surgeons.7 Furthermore, ChatGPT was found to provide better responses to microsurgery-related questions than the website of the American society of reconstructive microsurgery, according to plastic surgeons and non-medical individuals.8

Two studies demonstrated the ability of AI to provide objective feedback,9,10 and one study found that ChatGPT can demonstrate empathy11 meaning with the right knowledge, it might provide accurate diagnoses and management of various conditions. However, there are also examples of ChatGPT being poor at consultations; a study asking ChatGPT to gain informed consent for surgery found it to be inaccurate and not informative enough to gain consent.12

Overall, complete AI takeover in consultations is hard to perceive. It would need to pass an excruciating number of trials to be deemed safe and acceptable. A supportive role for AI in consultations is much more likely. AI has been shown to provide more accurate predictions of post-op morbidity and mortality than the widely used predictors, such as the American society of anesthesiologists (ASA) score, to patients, which augments the process of obtaining surgical consent.13

AI systems, such as data analysis expressions (DAX) copilot, have been shown to automatically and efficiently document patient encounters.14 DAX copilot has been shown to improve clinician and patient satisfaction,15 likely because doctors can focus more on patient centered encounters without the need to look at a screen. It would also give doctors time to see more patients without needing to document the previous consultation first, making the outpatient service more efficient.

Diagnostic potential of AI

Training AI to identify diagnoses can help speed up assessments of patients and allow doctors to produce a management plan while waiting for the test results. Some surgical specialties have begun using AI to assess patients. In colorectal surgery, AI is used with colonoscopies to detect polyps and adenomas. A meta-analysis of 48 studies found that AI use significantly increased the detection rates.16 In plastic surgery, studies have found AI to be capable of diagnosing skin cancers,17 lagophthalmos,18 frostbite,19 and velopharyngeal insufficiency.20 AI can diagnose these conditions using images, indicating that smartphone applications should be capable of diagnosis without the need for complex, expensive machinery. A prospective study developed an AI integrated smartphone app that was 87.5 % sensitive in automated diagnosis of positional plagiocephaly in infants.21 In addition, AI use in elastic-scattering spectroscopy has been shown to be highly sensitive in detecting different skin cancers, although the device's specificity is very low.22

Furthermore, AI can assess the severity of different conditions. In burn injuries, for instance, a deep learning software was developed to classify wounds and was found to do so more precisely than specialists.23 AI predicted mortality following a burn as accurately as the original and revised Baux score.24 A second study demonstrated that AI could predict numerous adverse effects in burn patients, such as the need for extended hospital stay and skin graft survival.25 A systematic review found that AI has the potential to transform burn care, and can advance diagnostic accuracy, management, and care efficiency.26

In the head and neck, an AI algorithm showed 100 % accuracy in grading facial palsy using the House and Brackmann Scale,27 and eight different AI networks were trialed to evaluate the severity of microtia and found all of them to be over 80 % accurate.28

Overall, AI has shown success in accurately diagnosing patients rapidly and without the need for any additional materials. However, most of these studies trained an AI to diagnose a specific condition. Practically, this would only be used to help confirm an already suspected diagnosis. AI needs to be trained to diagnose a wide range of conditions for it to diagnose independently.

AI in surgical planning

Surgical planning takes time and requires accurate analyses of imaging, tests, and patient-specific characteristics and comorbidities. AI can segment bones and tissues on scans, allowing for the identification and detailed analysis of body landmarks needed for the surgery. Moreover, AI can segment ultrasound scans of adipose tissue prior to liposuction29 and the carpal tunnel to identify the median nerve.30 One study investigated the role of AI in deep inferior epigastric artery perforator (DIEP) flap execution.31 The anatomy of the DIEP is complex, and consequently, surgical planning using computed tomography (CT) angiograms is needed to select suitable perforators. AI could enhance the acquisition, processing, and interpretation of CT angiograms in mapping the course of the perforators, which would save valuable time. In addition to this, AI can identify surgically important anatomical landmarks, such as cleft lip and nasal deformity,32 from photographs and videos to further augment its potential role in surgical planning. A deep learning program automatically segmented the mandible more accurately than semi-automatic segmentation, which is the present clinical standard, and in a fraction of the time.33

In nerve histomorphometry analysis, AI was found to be more accurate and quicker than conventional methods.34 One study used the AI abilities to recognize facial expressions from a facial recognition software on iPad, to aid surgical reanimation planning.35 In burn injuries, the depth of the burn can be analyzed using AI by segmenting the burn area from the entire wound and using a pixel-to-pixel method to support excision planning.36 In oculoplastic, AI can also measure the marginal reflex distance1 accurately and rapidly to plan blepharoplasty.37

The use of three-dimensional (3D) printing is becoming more prevalent in plastic surgery. 3D printing has already been applied to the breast,38 ear,39 and nasal reconstruction40 and has improved surgical outcomes and satisfaction.41 3D printing can produce patient-specific implants, based on CT and magnetic resonance imaging,42 to rehabilitate function and aesthetics.43 Currently, 3D printing is only used on a small scale due to its complexity. The process is time consuming and involves digital reconstruction, optimization, geometrical support, and quality control.42 AI can help streamline this process by assisting in image segmentation, modifying designs, and automatically generating optimized support structures to produce high quality prosthetics in a cost effective and efficient manner.44

Intraoperative uses of AI

AI can play a productive role by providing accurate assessments of intraoperative situations. A study found that AI can recognize whether a wound bed is viable, to help determine when to stop excision.45 In fact, it also found that whenever a surgeon changed their mind following an AI input, they always changed from the incorrect decision to the correct one.45 AI can also provide solutions to certain concerns, such as the use of ChatGPT to correctly answer intraoperative questions on the DIEP flap procedure.46

Post-operative AI uses

Numerous studies have found AI to accurately assess surgical outcomes. An AI integrated smartphone app could determine rhinoplasty status as accurately as consultants.47 AI can objectively measure years regained after facial rejuvenation surgery10 and assess intervention success from a patient's perspective in aesthetic surgery.9 AI is capable of gauging free flap perfusion and viability using photoplethysmography.48,49

Moreover, AI has been used to predict post-operative complications. It was found to have a high accuracy in predicting outcomes and complications of free flaps following head and neck tumor surgery.50 Machine learning can predict infection and explantation of breast implants in reconstruction, it identified 9 and 12 significant predictors, respectively, and had an accuracy of over 80 %.51 MySurgeryRisk is an AI program developed to predict complications such as acute kidney injury, sepsis, and venous thromboembolism. It had higher accuracy in predicting complications than physicians. Physician accuracy also significantly improved following AI use.52 The machine learning risk calculator, Predictive OpTimal Trees in Emergency Surgery Risk (POTTER), was developed using data from over 380,000 emergency surgery patients. POTTER outperformed the widely used scoring systems, including ASA, in predicting post-surgical morbidity and mortality.13 AI could also detect post-operative complications of breast augmentation that were previously unknown; larger preoperative bra-cup sizes and increased height were found to increase the risk of complications in a study involving over 1600 patients.53 ChatGPT could come up with the most likely problem in 20 out of 22 post-operative aesthetic surgery presentations.54 Following the development of any complications, AI was shown to consistently manage them appropriately.55

Following surgery, resources and personnel are needed to continuously monitor the patient. Smartphones are readily available and their use in patient monitoring has been successful in conditions such as multiple sclerosis56 and COVID-19.57 In plastic surgery, a free heart rate app can be used to monitor fasciocutaneous perforator flap perfusion using its pulse.58 Continuous AI-based vital monitoring can also help reduce the risk of post-operative complications by alerting staff as soon as any issues arise.14 However, few AI integrated applications have been used in plastic surgery. A deep learning integrated app could predict free flap congestion with 95 % accuracy, it also achieved 95 % sensitivity and specificity.59 Overall, AI-based monitoring shows early promise but requires more studies to determine its viability.

Other uses of AI

AI can contribute to research in plastic surgery. It can assist researchers in projects such as systematic reviews60 and can automate critical appraisals,61 although the latter is limited to abstracts due to accessibility. The publicly available AI, ChatGPT can also draft research articles.62 However, it is also known to make up sources when writing,63 which is a cause for concern and hampers the integrity of research. The integration of AI into medical databases could be a solution for this in the long run.

The use of AI to streamline administrative work has also been trialed in plastic surgery. A hand and reconstructive microsurgery department used AI NUHS Russel-GPT for administration work. A survey found that the staff unanimously supported its use.64 AI integration into administrative work will provide the staff with more time to assess and support the patients.

Limitations of AI

Despite the numerous advancements in AI, several ethical concerns must be tackled before it can safely be integrated into healthcare. In plastic surgery, data protection and privacy are the main concern according to a systematic review,65 as any AI integration would likely require providing confidential patient information to a third party that creates and regulates the software. AI can also worsen healthcare inequality and exhibit patient bias, as data for machine learning software would come from a specific population group, likely younger and better off individuals. This has been showcased in a systematic review involving 86 publications.66 The review also found that AI could shift care to a profit-based system.

In addition to bias against the patients, AI was also found to exhibit bias against doctors. A study analyzing three commonly used AI software reported that AI recommends far fewer female doctors than the national proportion.67 Moreover, AI has been found to under-skill and over-skill different surgeons at different rates. However, this can be mitigated by teaching the AI to provide visual explanations for its assessments.68 Protocols such as PROBAST are also being developed to assess for biases in AI.69 In addition, plastics staff are largely inexperienced with AI70 and may require comprehensive training prior to utilization.

Ongoing AI projects in plastic surgery

This section provides an overview of the ongoing projects that could contribute to innovation in plastic surgery. A randomized controlled trial is expected to start this year on an AI virtual assistant app that can help support patients before their plastic surgery. The results will be compared to a call group, which will require phoning a call center to ask questions.71 Trials are ongoing for the development of a machine learning algorithm that can predict and prevent intraoperative hypotension.72 Smart monitoring devices are also being trialed forward73- and home-based74 monitoring. The latter could decrease the need for surgical follow-ups and hospital stay.

Discussion

The integration of AI into plastic surgery heralds an exciting new era of patient care. Comprehensive literature analysis has shown its ability to improve outcomes in each step of the patient journey.

The use of AI in supporting doctors, owing to its ability to assess medical imaging accurately and rapidly and to predict outcomes have been key features of this review and are likely the way forward. Automatic dictation would help doctors dedicate more attention to patients in consultations. The ability of AI to segment scans and identify key landmarks can take preoperative planning to a new level. Its prediction of post-operative complications can improve surgical decision making and provide patients with the most accurate information while obtaining informed consent. These developments would expedite and improve management and mitigate the risk of human error, thus improving patient safety and reducing costs.

Despite the remarkable progress within AI developments in plastic surgery, several challenges remain. Moreover, concerns on data privacy and algorithmic bias must be addressed. A robust authentication and regulation process must also be developed to ensure patient safety.

AI has the potential to reshape plastic surgery in previously unimaginable ways. Further research, regulation, and work on upholding the ethical standards can allow plastic surgeons to harness the power of AI to provide new and high standards of patient care.

To conclude, the comprehensive review of available literature found AI to be capable of transforming care throughout the entire patient journey. Certain challenges and concerns persist, but a collaborative effort can help solve these issues to bring about a new era of medicine, where AI aids doctors in the pursuit of optimal patient care.

Ethical approval

Not required.

Author contributions

All authors have participated in the conception and design of the study, acquisition of data, analysis, and interpretation of data, and drafting the article.

Conflict of interest

The authors have nothing to disclose.

Acknowledgments

Funding source

There was no funding required for this study.

Declaration of generative AI and AI-assisted technologies in the writing process

Generative AI and AI-assisted technologies were not used in the writing process.

References

  • 1.The NHS has Spent £21m on AI tools. Will They Be Worth It? Frontier Economics. Accessed 5.05.24. https://www.frontier-economics.com/uk/en/news-and-insights/news/news-article-i20547-the-nhs-has-spent-21m-on-ai-tools-will-they-be-worth-it/
  • 2.Health Funding Data Analysis. The British Medical Association is the Trade Union and Professional Body for Doctors in the UK. Accessed 5.05.24. https://www.bma.org.uk/advice-and-support/nhs-delivery-and-workforce/funding/health-funding-data-analysis
  • 3.NHS Medical Staffing Data Analysis. The British medical association is the trade union and professional body for doctors in the UK. Accessed 5.05.24. https://www.bma.org.uk/advice-and-support/nhs-delivery-and-workforce/workforce/nhs-medical-staffing-data-analysis
  • 4.Baldini N., Discepoli N., Tortoriello M., Viviano M., Giammarinaro E., Ferrari M. Accuracy and security analysis of a cranio-maxillofacial plastic surgery robot equipped with piezosurgery in genioplasty. J Craniofac Surg. 2022;33(5):2235–2239. doi: 10.1097/SCS.0000000000008617. [DOI] [PubMed] [Google Scholar]
  • 5.Lin L., Sun M., Xu C., et al. Assessment of robot-assisted mandibular contouring surgery in comparison with traditional surgery: a prospective, single-center, randomized controlled trial. Aesthet Surg J. 2022;42(6):567–579. doi: 10.1093/asj/sjab392. [DOI] [PubMed] [Google Scholar]
  • 6.Humar P., Asaad M., Bengur F.B., Nguyen V. ChatGPT Is equivalent to first-year plastic surgery residents: evaluation of ChatGPT on the plastic surgery in-service examination. Aesthet Surg J. 2023;43(12):NP1085–NP1089. doi: 10.1093/asj/sjad130. [DOI] [PubMed] [Google Scholar]
  • 7.Blepharoptosis consultation with artificial intelligence: aesthetic surgery advice and counseling from chat generative pre-trained transformer (ChatGPT) - PubMed. Accessed 5.05.24. https://pubmed.ncbi.nlm.nih.gov/38589561/ [DOI] [PubMed]
  • 8.Berry C.E., Fazilat A.Z., Lavin C., et al. Both patients and plastic surgeons prefer artificial intelligence-generated microsurgical information. J Reconstr Microsurg. 2024 doi: 10.1055/a-2273-4163. Published online March 26. [DOI] [PubMed] [Google Scholar]
  • 9.Atiyeh B., Emsieh S., Hakim C., Chalhoub R. A narrative review of artificial intelligence (AI) for objective assessment of aesthetic endpoints in plastic surgery. Aesthetic Plast Surg. 2023;47(6):2862–2873. doi: 10.1007/s00266-023-03328-9. [DOI] [PubMed] [Google Scholar]
  • 10.Elliott Z.T., Bheemreddy A., Fiorella M., et al. Artificial intelligence for objectively measuring years regained after facial rejuvenation surgery. Am J Otolaryngol. 2023;44(2) doi: 10.1016/j.amjoto.2022.103775. [DOI] [PubMed] [Google Scholar]
  • 11.Al-Sharif E.M., Penteado R.C., Dib El Jalbout N., et al. Evaluating the accuracy of ChatGPT and Google BARD in fielding oculoplastic patient queries: a comparative study on artificial versus human intelligence. Ophthal Plast Reconstr Surg. 2024;40(3):303–311. doi: 10.1097/IOP.0000000000002567. [DOI] [PubMed] [Google Scholar]
  • 12.Shiraishi M., Tomioka Y., Miyakuni A., et al. Generating informed consent documents related to blepharoplasty using ChatGPT. Ophthal Plast Reconstr Surg. 2024;40(3):316–320. doi: 10.1097/IOP.0000000000002574. [DOI] [PubMed] [Google Scholar]
  • 13.Bertsimas D., Dunn J., Velmahos G.C., Kaafarani H.M.A. Surgical Risk is not linear: derivation and validation of a novel, user-friendly, and machine-learning-based predictive optimal trees in emergency surgery risk (POTTER) calculator. Ann Surg. 2018;268(4):574–583. doi: 10.1097/SLA.0000000000002956. [DOI] [PubMed] [Google Scholar]
  • 14.Bajwa J., Munir U., Nori A., Williams B. Artificial Intelligence in healthcare: transforming the practice of medicine. Future Healthc J. 2021;8(2):e188–e194. doi: 10.7861/fhj.2021-0095. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 15.Automatically Document Care with DAX Copilot | Nuance. Accessed 5.05.24. https://www.nuance.com/healthcare/dragon-ai-clinical-solutions/dax-copilot.html
  • 16.Nazarian S., Glover B., Ashrafian H., Darzi A., Teare J. Diagnostic accuracy of artificial intelligence and computer-aided diagnosis for the detection and characterization of colorectal polyps: systematic review and meta-analysis. J Med Internet Res. 2021;23(7):e27370. doi: 10.2196/27370. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 17.Brancaccio G., Balato A., Malvehy J., Puig S., Argenziano G., Kittler H. Artificial intelligence in skin cancer diagnosis: a reality check. J Invest Dermatol. 2024;144(3):492–499. doi: 10.1016/j.jid.2023.10.004. [DOI] [PubMed] [Google Scholar]
  • 18.Knoedler L., Alfertshofer M., Simon S., et al. Diagnosing Lagophthalmos using artificial intelligence. Sci Rep. 2023;13(1):21657. doi: 10.1038/s41598-023-49006-3. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 19.Sun J., Fu L., Zhang W., et al. Convolutional neural network models for automatic diagnosis and graduation in skin frostbite. Int Wound J. 2023;20(4):910–916. doi: 10.1111/iwj.13937. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 20.Ha J.H., Lee H., Kwon S.M., et al. Deep learning-based diagnostic system for velopharyngeal insufficiency based on videofluoroscopy in patients with repaired cleft palates. J Craniofac Surg. 2023;34(8):2369–2375. doi: 10.1097/SCS.0000000000009560. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 21.Watt A., Lee J., Toews M., Gilardino M.S. Smartphone integration of artificial intelligence for automated plagiocephaly diagnosis. Plast Reconstr Surg Glob Open. 2023;11(5):e4985. doi: 10.1097/GOX.0000000000004985. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 22.Manolakos D., Patrick G., Geisse J.K., et al. Use of an elastic-scattering spectroscopy and artificial intelligence device in the assessment of lesions suggestive of skin cancer: a comparative effectiveness study. JAAD Int. 2024;14:52–58. doi: 10.1016/j.jdin.2023.08.019. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 23.Huang P.H., Pan Y.H., Luo Y.S., et al. Development of a deep learning-based tool to assist wound classification. J Plast Reconstr Aesthetic Surg. 2023;79:89–97. doi: 10.1016/j.bjps.2023.01.030. [DOI] [PubMed] [Google Scholar]
  • 24.Fransén J., Lundin J., Fredén F., Huss F. A proof-of-concept study on mortality prediction with machine learning algorithms using burn intensive care data. Scars Burns Heal. 2022;8 doi: 10.1177/20595131211066585. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 25.Yeh C.C., Lin Y.S., Chen C.C., Liu C.F. Implementing AI models for prognostic predictions in high-risk burn patients. Diagn Basel Switz. 2023;13(18):2984. doi: 10.3390/diagnostics13182984. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 26.E Moura F.S., Amin K., Ekwobi C. Artificial intelligence in the management and treatment of burns: a systematic review. Burns Trauma. 2021;9:tkab022. doi: 10.1093/burnst/tkab022. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 27.Knoedler L., Baecher H., Kauke-Navarro M., et al. Towards a reliable and rapid automated grading system in facial palsy patients: facial palsy surgery meets computer science. J Clin Med. 2022;11(17):4998. doi: 10.3390/jcm11174998. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 28.Wang D., Chen X., Wu Y., Tang H., Deng P. Artificial Intelligence for assessing the severity of microtia via deep convolutional neural networks. Front Surg. 2022;9 doi: 10.3389/fsurg.2022.929110. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 29.Cai R., Liu Y., Sun Z., et al. Deep-learning based segmentation of ultrasound adipose image for liposuction. Int J Med Robot. 2023;19(6):e2548. doi: 10.1002/rcs.2548. [DOI] [PubMed] [Google Scholar]
  • 30.Festen R.T., Schrier V.J.M.M., Amadio P.C. Automated Segmentation of the Median Nerve in the Carpal Tunnel using U-Net. Ultrasound Med Biol. 2021;47(7):1964–1969. doi: 10.1016/j.ultrasmedbio.2021.03.018. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 31.Cevik J., Seth I., Rozen W.M. Transforming breast reconstruction: the pioneering role of artificial intelligence in preoperative planning. Gland Surg. 2023;12(9):1271–1275. doi: 10.21037/gs-23-265. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 32.Sayadi L.R., Hamdan U.S., Zhangli Q., Vyas R.M. Harnessing the power of artificial intelligence to teach cleft lip surgery. Plast Reconstr Surg Glob Open. 2022;10(7):e4451. doi: 10.1097/GOX.0000000000004451. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 33.Verhelst P.J., Smolders A., Beznik T., et al. Layered deep learning for automatic mandibular segmentation in cone-beam computed tomography. J Dent. 2021;114 doi: 10.1016/j.jdent.2021.103786. [DOI] [PubMed] [Google Scholar]
  • 34.Daeschler S.C., Bourget M.H., Derakhshan D., et al. Rapid, automated nerve histomorphometry through open-source artificial intelligence. Sci Rep. 2022;12(1):5975. doi: 10.1038/s41598-022-10066-6. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 35.Hartmann T.J., Hartmann J.B.J., Friebe-Hoffmann U., Lato C., Janni W., Lato K. Novel method for three-dimensional facial expression recognition using self-normalizing neural networks and mobile devices. Geburtshilfe Frauenheilkd. 2022;82(9):955–969. doi: 10.1055/a-1866-2943. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 36.Chang C.W., Ho C.Y., Lai F., et al. Application of multiple deep learning models for automatic burn wound assessment. Burns. 2023;49(5):1039–1051. doi: 10.1016/j.burns.2022.07.006. [DOI] [PubMed] [Google Scholar]
  • 37.Song B., Kwon H., Kim S., Ha Y., Oh S.H., Song S.H. Introduction of deep learning-based infrared image analysis to marginal reflex distance1 measurement method to simultaneously capture images and compute results: clinical validation study. J Clin Med. 2023;12(23):7466. doi: 10.3390/jcm12237466. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 38.Chae M.P., Hunter-Smith D.J., Spychal R.T., Rozen W.M. 3D volumetric analysis for planning breast reconstructive surgery. Breast Cancer Res Treat. 2014;146(2):457–460. doi: 10.1007/s10549-014-3028-1. [DOI] [PubMed] [Google Scholar]
  • 39.Nishimoto S., Sotsuka Y., Kawai K., Fujita K., Kakibuchi M. Three-dimensional mock-up model for chondral framework in auricular reconstruction, built with a personal three-dimensional printer. Plast Reconstr Surg. 2014;134(1):180e–181e. doi: 10.1097/PRS.0000000000000263. [DOI] [PubMed] [Google Scholar]
  • 40.Xu Y., Fan F., Kang N., et al. Tissue engineering of human nasal alar cartilage precisely by using three-dimensional printing. Plast Reconstr Surg. 2015;135(2):451–458. doi: 10.1097/PRS.0000000000000856. [DOI] [PubMed] [Google Scholar]
  • 41.Lynn A.Q., Pflibsen L.R., Smith A.A., Rebecca A.M., Teven C.M. Three-dimensional printing in plastic surgery: current applications, future directions, and ethical Implications. Plast Reconstr Surg Glob Open. 2021;9(3):e3465. doi: 10.1097/GOX.0000000000003465. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 42.Aimar A., Palermo A., Innocenti B. The role of 3D printing in medical applications: a state of the art. J Healthc Eng. 2019;2019 doi: 10.1155/2019/5340616. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 43.Sutradhar A., Park J., Carrau D., Miller M.J. Experimental validation of 3D printed patient-specific implants using digital image correlation and finite element analysis. Comput Biol Med. 2014;52:8–17. doi: 10.1016/j.compbiomed.2014.06.002. [DOI] [PubMed] [Google Scholar]
  • 44.Ma L., Yu S., Xu X., Moses Amadi S., Zhang J., Wang Z. Application of artificial intelligence in 3D printing physical organ models. Mater Today Bio. 2023;23 doi: 10.1016/j.mtbio.2023.100792. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 45.Yu S., Dwight J., Siska R.C., et al. Feasibility of intra-operative image guidance in burn excision surgery with multispectral imaging and deep learning. Burns. 2024;50(1):115–122. doi: 10.1016/j.burns.2023.07.005. [DOI] [PubMed] [Google Scholar]
  • 46.Atkinson C.J., Seth I., Xie Y., et al. Artificial intelligence language model performance for rapid intraoperative queries in plastic surgery: chatGPT and the deep inferior epigastric perforator flap. J Clin Med. 2024;13(3):900. doi: 10.3390/jcm13030900. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 47.Borsting E., DeSimone R., Ascha M., Ascha M. Applied deep learning in plastic surgery: classifying rhinoplasty with a mobile app. J Craniofac Surg. 2020;31(1):102–106. doi: 10.1097/SCS.0000000000005905. [DOI] [PubMed] [Google Scholar]
  • 48.Fiedler L.S., Daaloul H. An overview of current assessment techniques for evaluating cutaneous perfusion in reconstructive surgery. J Biophotonics. 2024;17(5) doi: 10.1002/jbio.202400002. [DOI] [PubMed] [Google Scholar]
  • 49.Kyriacou P.A., Zaman T., Pal S.K. Photoplethysmography in postoperative monitoring of deep inferior epigastric perforator (DIEP) free flaps. Physiol Meas. 2021;41(12) doi: 10.1088/1361-6579/abc4c8. [DOI] [PubMed] [Google Scholar]
  • 50.Bassani S., Eccher A., Molteni G. Harnessing the power of artificial intelligence: revolutionizing free flaps monitoring in head and neck tumor treatment. Crit Rev Oncog. 2023;28(3):25–30. doi: 10.1615/CritRevOncog.2023049158. [DOI] [PubMed] [Google Scholar]
  • 51.Hassan A.M., Biaggi-Ondina A., Asaad M., et al. Artificial intelligence modeling to predict periprosthetic infection and explantation following implant-based reconstruction. Plast Reconstr Surg. 2023;152(5):929–938. doi: 10.1097/PRS.0000000000010345. [DOI] [PubMed] [Google Scholar]
  • 52.Brennan M., Puri S., Ozrazgat-Baslanti T., et al. Comparing clinical judgment with the mysurgeryrisk algorithm for preoperative risk assessment: a pilot usability study. Surgery. 2019;165(5):1035–1045. doi: 10.1016/j.surg.2019.01.002. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 53.Montemurro P., Lehnhardt M., Behr B., Wallner C. A machine learning approach to identify previously unconsidered causes for complications in aesthetic breast augmentation. Aesthetic Plast Surg. 2022;46(6):2669–2676. doi: 10.1007/s00266-022-02997-2. [DOI] [PubMed] [Google Scholar]
  • 54.Abi-Rafeh J., Henry N., Xu H.H., et al. Utility and comparative performance of current artificial intelligence large language models as postoperative medical support chatbots in aesthetic surgery. Aesthet Surg J. 2024;44(8):sjae025. doi: 10.1093/asj/sjae025. [DOI] [PubMed] [Google Scholar]
  • 55.Zhang H., Zhao J., Farzan R., Alizadeh Otaghvar H. Risk predictions of surgical wound complications based on a machine learning algorithm: a systematic review. Int Wound J. 2024;21(1):e14665. doi: 10.1111/iwj.14665. [DOI] [PMC free article] [PubMed] [Google Scholar] [Retracted]
  • 56.Altmann P., Ponleitner M., Monschein T., et al. Feasibility of a smartphone app to monitor patient reported outcomes in multiple sclerosis: the hamster interventional trial. Digit Health. 2022;8 doi: 10.1177/20552076221135387. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 57.Shah S.S., Gvozdanovic A., Knight M., Gagnon J. Mobile app-based remote patient monitoring in acute medical conditions: prospective feasibility study exploring digital health solutions on clinical workload during the COVID crisis. JMIR Form Res. 2021;5(1):e23190. doi: 10.2196/23190. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 58.Hijazi Y., Elbaz A., Mutsago T., Bystrzonowski N., Berner J.E., Pafitanis G. Fasciocutaneous perforator flap direct monitoring with a smartphone instant heart rate App. Microsurgery. 2022;42(5):522–523. doi: 10.1002/micr.30922. [DOI] [PubMed] [Google Scholar]
  • 59.Hsu S.Y., Chen L.W., Huang R.W., et al. Quantization of extraoral free flap monitoring for venous congestion with deep learning integrated iOS applications on smartphones: a diagnostic study. Int J Surg. 2023;109(6):1584–1593. doi: 10.1097/JS9.0000000000000391. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 60.Alaniz L., Vu C., Pfaff M.J. The utility of artificial intelligence for systematic reviews and boolean query formulation and translation. Plast Reconstr Surg Glob Open. 2023;11(10):e5339. doi: 10.1097/GOX.0000000000005339. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 61.Roberts R.H., Ali S.R., Hutchings H.A., Dobbs T.D., Whitaker I.S. Comparative study of ChatGPT and human evaluators on the assessment of medical literature according to recognised reporting standards. BMJ Health Care Inform. 2023;30(1) doi: 10.1136/bmjhci-2023-100830. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 62.Macdonald C., Adeloye D., Sheikh A., Rudan I. Can ChatGPT draft a research article? an example of population-level vaccine effectiveness analysis. J Glob Health. 2023;13:01003. doi: 10.7189/jogh.13.01003. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 63.Seth I., Xie Y., Rodwell A., et al. Exploring the role of a large language model on carpal tunnel syndrome management: an observation study of ChatGPT. J Hand Surg Am. 2023;48(10):1025–1033. doi: 10.1016/j.jhsa.2023.07.003. [DOI] [PubMed] [Google Scholar]
  • 64.Tan R.E.S., Teo W.Z.W., Puhaindran M.E. Artificial intelligence in hand surgery – how generative AI is transforming the hand surgery landscape. J Hand Surg Asian-Pac. 2024;29(2):81–87. doi: 10.1142/S2424835524300019. [DOI] [PubMed] [Google Scholar]
  • 65.Kenig N., Monton Echeverria J., Rubi C. Ethics for AI in plastic surgery: guidelines and review. Aesthetic Plast Surg. 2024;48(11):2204–2209. doi: 10.1007/s00266-024-03932-3. [DOI] [PubMed] [Google Scholar]
  • 66.d'Elia A., Gabbay M., Rodgers S., et al. Artificial intelligence and health inequities in primary care: a systematic scoping review and framework. Fam Med Community Health. 2022;10(Suppl 1) doi: 10.1136/fmch-2022-001670. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 67.Oca M.C., Meller L., Wilson K., et al. Bias and Inaccuracy in AI chatbot ophthalmologist recommendations. Cureus. 2023;15(9):e45911. doi: 10.7759/cureus.45911. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 68.Kiyasseh D., Laca J., Haque T.F., et al. Human visual explanations mitigate bias in AI-based assessment of surgeon skills. NPJ Digit Med. 2023;6(1):54. doi: 10.1038/s41746-023-00766-2. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 69.Kooi K., Martinez E.T., Freundt L., et al. From data to decisions: how AI is revolutionizing clinical prediction models in plastic surgery. Plast Reconstr Surg. 2024 doi: 10.1097/PRS.0000000000011266. Published online January 8. [DOI] [PubMed] [Google Scholar]
  • 70.Farid Y., Fernando Botero Gutierrez L., Ortiz S., et al. Artificial intelligence in plastic surgery: insights from plastic surgeons, education integration, ChatGPT's survey predictions, and the path forward. Plast Reconstr Surg Glob Open. 2024;12(1):e5515. doi: 10.1097/GOX.0000000000005515. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 71.Researcher View | Virtual Assistant for Plastic Surgery Patients | ClinicalTrials.gov. Accessed 6.05.24. https://clinicaltrials.gov/study/NCT04017351?cond=Plastic%20Surgery&term=Artificial%20Intelligence&rank=1&tab=table
  • 72.Study Details | Artificial Intelligence - to Predict and Prevent Hypotension During Surgery | ClinicalTrials.gov. Accessed 6.05.24. https://clinicaltrials.gov/study/NCT06240234?cond=Surgery&term=Artificial%20Intelligence&limit=50&page=1&rank=12
  • 73.Study Details | Surgical Ward Innovation: telemonitoring Controlled by Healthdot | ClinicalTrials.gov. Accessed 6.05.24. https://clinicaltrials.gov/study/NCT05956210?cond=Surgery&term=Artificial%20Intelligence&limit=50&page=2&rank=64
  • 74.Study Details | Evaluation of the Impact of the SMART ANGEL ™ Device on follow-up at home following major or intermediate outpatient surgery | ClinicalTrials.gov. Accessed 6.05.24. https://clinicaltrials.gov/study/NCT04068584?cond=Surgery&term=Artificial%20Intelligence&limit=50&page=1&rank=17

Articles from JPRAS Open are provided here courtesy of Elsevier

RESOURCES