Utility and Comparative Performance of Current Artificial Intelligence Large Language Models as Postoperative Medical Support Chatbots in Aesthetic Surgery.

BACKGROUND: Large Language Models (LLMs) have revolutionized the way plastic surgeons and their patients may access and leverage artificial Intelligence (AI). OBJECTIVES: The present study aims to comparatively assess the performance of two current publically-available and patient-accessible LLMs in the potential application of AI as postoperative medical support chatbots in an aesthetic surgeon's practice. METHODS: Twenty-two simulated postoperative patient presentations following aesthetic breast plastic surgery were devised and expert-validated. Complications varied in their latency within the postoperative period, as well as urgency of required medical attention. In response to each patient-reported presentation, Open AI's ChatGPT and Google's Bard, in their unmodified and freely available versions, were objectively assessed for their comparative accuracy in generating an appropriate differential diagnosis, most likely diagnosis, suggested medical disposition, treatments or interventions to begin from home, and/or red flag signs/symptoms indicating deterioration. RESULTS: ChatGPT cumulatively and significantly outperformed Bard across all objective assessement metrics examined (66% vs. 55%, respectively; p < 0.05). Accuracy in generating an appropriate differential diagnosis were 61% for ChatGPT, and 57% for Bard (p = 0.45). ChatGPT asked an average of 9.2 questions on history, relative to 6.8 questions by Bard (p < 0.001), following which, accuracies of 91% vs. 68% at arriving at the most-likely diagnosis were noted, respectively (p < 0.01). Appropriate medical dispositions were suggested with an accuracy of 50% by ChatGPT, and 41% by Bard (p = 0.40); relevant home interventions/treatments with an accuracy of 59% and 55% (p = 0.94), and red flag signs/symptoms with accuracies of 79% and 54% (p < 0.01), respectively. Detailed and comparative performance breakdowns according to complication latency and urgency are presented herein. CONCLUSIONS: ChatGPT represents the superior LLM for the potential application of AI technology in postoperative medical support chatbots. Imperfect performance and limitations identified herein may guide the necessary refinement to facilitate adoption.

Artificial Intelligence-Generated Social Media Content Creation and Management Strategies for Plastic Surgeons.

BACKGROUND: Social media platforms have come to represent integral components of the professional marketing and advertising strategy for plastic surgeons. Effective and consistent content development, however, remains technically demanding and time consuming, prompting most to employ, at non-negligible costs, social media marketing specialists for content planning and development. OBJECTIVES: The present study aims to investigate the ability of presently available artificial intelligence (AI) models to assist plastic surgeons in their social media content development and sharing plans. METHODS: An AI Large Language Model was prompted on the study's objectives through a series of standardized user interactions; social media platforms of interest, on which the AI model was prompted, included Instagram, TikTok, and X (formerly Twitter). RESULTS: A one-year, entirely AI-generated social media plan, comprising a total of 1091 posts for the three aforementioned social media platforms, is presented herein. Themes of the AI-generated content proposed for each platform were classified into 6 categories, including patient-related, practice-related, educational, "uplifting", interactive, and promotional posts. Overall, 91 publicly recognized holidays, observant, and awareness days were incorporated into the content calendars. The AI model demonstrated an ability to differentiate between the distinct formats of each of the three social media platforms investigated, generating unique ideas for each, and providing detailed content development and posting instructions, scripts, and post captions, leveraging features specific to each platform. CONCLUSIONS: By providing detailed and actionable social media content creation and posting plans to plastic surgeons, presently available AI models can be readily leveraged to assist in and significantly alleviate the burden associated with social media account management, content generation, and potentially patient conversion.

Complications Following Body Contouring: Performance Validation of Bard, a Novel AI Large Language Model, in Triaging and Managing Postoperative Patient Concerns.

INTRODUCTION: Large language models (LLM) have revolutionized the way humans interact with artificial intelligence (AI) technology, with marked potential for applications in esthetic surgery. The present study evaluates the performance of Bard, a novel LLM, in identifying and managing postoperative patient concerns for complications following body contouring surgery. METHODS: The American Society of Plastic Surgeons' website was queried to identify and simulate all potential postoperative complications following body contouring across different acuities and severity. Bard's accuracy was assessed in providing a differential diagnosis, soliciting a history, suggesting a most-likely diagnosis, appropriate disposition, treatments/interventions to begin from home, and red-flag signs/symptoms indicating deterioration, or requiring urgent emergency department (ED) presentation. RESULTS: Twenty-two simulated body contouring complications were examined. Overall, Bard demonstrated a 59% accuracy in listing relevant diagnoses on its differentials, with a 52% incidence of incorrect or misleading diagnoses. Following history-taking, Bard demonstrated an overall accuracy of 44% in identifying the most-likely diagnosis, and a 55% accuracy in suggesting the indicated medical dispositions. Helpful treatments/interventions to begin from home were suggested with a 40% accuracy, whereas red-flag signs/symptoms, indicating deterioration, were shared with a 48% accuracy. A detailed analysis of performance, stratified according to latency of postoperative presentation (<48hours, 48hours-1month, or >1month postoperatively), and according to acuity and indicated medical disposition, is presented herein. CONCLUSIONS: Despite promising potential of LLMs and AI in healthcare-related applications, Bard's performance in the present study significantly falls short of accepted clinical standards, thus indicating a need for further research and development prior to adoption. LEVEL OF EVIDENCE IV: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Large Language Models and Artificial Intelligence: A Primer for Plastic Surgeons on the Demonstrated and Potential Applications, Promises, and Limitations of ChatGPT.

BACKGROUND: The rapidly evolving field of artificial intelligence (AI) holds great potential for plastic surgeons. ChatGPT, a recently released AI large language model (LLM), promises applications across many disciplines, including healthcare. OBJECTIVES: The aim of this article was to provide a primer for plastic surgeons on AI, LLM, and ChatGPT, including an analysis of current demonstrated and proposed clinical applications. METHODS: A systematic review was performed identifying medical and surgical literature on ChatGPT's proposed clinical applications. Variables assessed included applications investigated, command tasks provided, user input information, AI-emulated human skills, output validation, and reported limitations. RESULTS: The analysis included 175 articles reporting on 13 plastic surgery applications and 116 additional clinical applications, categorized by field and purpose. Thirty-four applications within plastic surgery are thus proposed, with relevance to different target audiences, including attending plastic surgeons (n = 17, 50%), trainees/educators (n = 8, 24.0%), researchers/scholars (n = 7, 21%), and patients (n = 2, 6%). The 15 identified limitations of ChatGPT were categorized by training data, algorithm, and ethical considerations. CONCLUSIONS: Widespread use of ChatGPT in plastic surgery will depend on rigorous research of proposed applications to validate performance and address limitations. This systemic review aims to guide research, development, and regulation to safely adopt AI in plastic surgery.

Complications Following Facelift and Neck Lift: Implementation and Assessment of Large Language Model and Artificial Intelligence (ChatGPT) Performance Across 16 Simulated Patient Presentations.

INTRODUCTION: ChatGPT represents a potential resource for patient guidance and education, with the possibility for quality improvement in healthcare delivery. The present study evaluates the role of ChatGPT as an interactive patient resource, and assesses its performance in identifying, triaging, and guiding patients with concerns of postoperative complications following facelift and neck lift surgery. METHODS: Sixteen patient profiles were generated to simulate postoperative patient presentations, with complications of varying acuity and severity. ChatGPT was assessed for its accuracy in generating a differential diagnosis, soliciting a history, providing the most-likely diagnosis, the appropriate disposition, treatments/interventions to begin from home, and red-flag symptoms necessitating an urgent presentation to the emergency department. RESULTS: Overall accuracy in providing a complete differential diagnosis in response to simulated presentations was 85%, with an accuracy of 88% in identifying the most-likely diagnosis after history-taking. However, appropriate patient dispositions were suggested in only 56% of cases. Relevant home treatments/interventions were suggested with an 82% accuracy, and red-flag symptoms with a 73% accuracy. A detailed analysis, stratified according to latency of postoperative presentation (<48 h, 48 h-1 week, or >1 week), and according to acuity of complications, is presented herein. CONCLUSIONS: ChatGPT overestimated the urgency of indicated patient dispositions in 44% of cases, concerning for potential unnecessary increase in healthcare resource utilization. Imperfect performance, and the tool's tendency for overinclusion in its responses, risk increasing patient anxiety and straining physician-patient relationships. While artificial intelligence has great potential in triaging postoperative patient concerns, and improving efficiency and resource utilization, ChatGPT's performance, in its current form, demonstrates a need for further refinement before its safe and effective implementation in facial aesthetic surgical practice. LEVEL OF EVIDENCE IV: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Effective Strategies to Patent Plastic Surgery Ideas and Intellectual Property.

SUMMARY: Patents are of great importance to plastic surgery, a field fueled by constant innovation. Familiarity with the patent process could promote further innovation by plastic surgeons. By granting proprietary rights to inventors in exchange for publication of their inventions, patents incentivize creativity and innovation while promoting diffusion and transfer of technology. The task of securing patent protection, however, is complex, and begins well before the patent application. Inventors must familiarize themselves with regulations to ensure that their inventions satisfy the criteria for patentability, which can differ among countries. Patents regarding surgical methods should undergo additional ethical deliberation given their potential interference with medical altruism. The patent application must be devised and written thoroughly, as it needs to withstand meticulous examination by patent offices and potential third-party opposition, and professional assistance in doing so should be sought. Filing of the application calls for intricate procedural and timing requirements that bear major benefits if well understood and respected by applicants. Given that patent rights only cover the issuing country's territorial scope, further endeavors must be pursued when seeking patent protection in additional countries. In this regard, two options exist, and the ultimate decision should be tailored to each inventor's personal needs. At every step of the patenting process, financial readiness is key because costs can be unpredictable and escalate quickly. In this article, the authors propose effective strategies directed at plastic surgeons to facilitate patenting of their ideas and protection of their intellectual property.

Nerve Blocks in Breast Plastic Surgery: Outcomes, Complications, and Comparative Efficacy.

BACKGROUND: As plastic surgeons continue to evaluate the utility of nonopioid analgesic alternatives, nerve block use in breast plastic surgery remains limited and unstandardized, with no syntheses of the available evidence to guide consensus on optimal approach. METHODS: A systematic review was performed to evaluate the role of pectoralis nerve blocks, paravertebral nerve blocks, transversus abdominus plane blocks, and intercostal nerve blocks in flap-based breast reconstruction, prosthetic-based reconstruction, and aesthetic breast plastic surgery, independently. RESULTS: Thirty-one articles reporting on a total of 2820 patients were included in the final analysis; 1500 patients (53 percent) received nerve blocks, and 1320 (47 percent) served as controls. Outcomes and complications were stratified according to procedures performed, blocks employed, techniques of administration, and anesthetic agents used. Overall, statistically significant reductions in opioid consumption were reported in 91 percent of studies evaluated, postoperative pain in 68 percent, postanesthesia care unit stay in 67 percent, postoperative nausea and vomiting in 53 percent, and duration of hospitalization in 50 percent. Nerve blocks did not significantly alter surgery and/or anesthesia time in 83 percent of studies assessed, whereas the overall, pooled complication rate was 1.6 percent. CONCLUSIONS: Transversus abdominus plane blocks provided excellent outcomes in autologous breast reconstruction, whereas both paravertebral nerve blocks and pectoralis nerve blocks demonstrated notable efficacy and versatility in an array of reconstructive and aesthetic procedures. Ultrasound guidance may minimize block-related complications, whereas the efficacy of adjunctive postoperative infusions was proven to be limited. As newer anesthetic agents and adjuvants continue to emerge, nerve blocks are set to represent essential components of the multimodal analgesic approach in breast plastic surgery.

Utility of Ultrasonography and Significance of Surgical Anatomy in the Management of de Quervain Disease: A Systematic Review and Meta-Analysis.

BACKGROUND: The role of ultrasound in plastic surgery practice has grown significantly over the past decade, with notable applications for conditions of the upper extremity. Its utility for the management of de Quervain disease, however, remains to be established, and the prevalence of first dorsal compartment anatomical variations needs to be adequately assessed. METHODS: A systematic review was performed to evaluate the role of ultrasound in the diagnosis, anatomical characterization, and clinical management of de Quervain disease. A meta-analysis was conducted to establish the prevalence of first dorsal compartment anatomical variations in the de Quervain disease and general population, along with the diagnostic accuracy of ultrasound for their detection. Outcomes were documented and compared to alternative treatment options. RESULTS: Extensor retinaculum thickening, tendon sheath swelling, peritendinous edema, and tendon enlargement were the most common sonographic features of de Quervain disease. The prevalence of an intercompartmental septum in the de Quervain disease surgical population was shown to be significantly greater than in the general cadaveric population (67 percent versus 35 percent, respectively). Although the efficacy of energy-based therapeutic ultrasound remains elusive, ultrasound-guided corticosteroid injections were shown to be more accurate than manual injections (90 to 100 percent versus 40 to 100 percent), and to confer significantly better treatment outcomes (73 to 100 percent versus 59 to 83 percent success rates, respectively). CONCLUSIONS: Ultrasound use is essential to achieve the best evidence-based outcomes in the management of de Quervain disease. The varied prevalence of first dorsal compartment anatomical variations and high accuracy of ultrasound for their detection carry significant prognostic implications.

"Identification of Essential Assessment Criteria in Facial Botulinum Toxin Injections".

INTRODUCTION: Facial botulinum toxin injections represent the most commonly performed aesthetic non-surgical procedures by plastic surgeons; however, post-graduate programs remain devoid of objective tools to adequately assess competence in trainees. In this study, the authors employ the Delphi methodology to establish a list of essential assessment criteria in facial botulinum toxin injections. METHODS: A list of 10 suggested criteria was generated through a literature search and in consultation with an expert plastic surgeon. A panel of content experts was selected to which an online survey was administered; skills were ranked for their relevance using a 1-10 Likert scale. Recommendations for additional skills were solicited and survey rounds were repeated until consensus was achieved. The latter was a measure of panelist reliability and assessed using Cronbach α (≥0.8); skills with a rating of 7 or above were taken to be essential. RESULTS: The survey process was successful at achieving consensus following two rounds of survey administration. Twenty-one participants completed the first round representing a response rate of 38%. Percent agreement among the panel was 83% and Cronbach α was computed as 0.78, necessitating further rounds. The response rate in the second round was 90%; one additional skill was added; percent agreement and Cronbach α improved to 88% and 0.87, respectively. CONCLUSION: Nine assessment criteria were identified as essential in facial botulinum toxin injections; these findings provide the groundwork necessary for the development of an objective assessment tool for the more appropriate training of marginalized aesthetic procedures in plastic surgery.

Lower extremity postaxial polydactyly: Current literature status and future avenues.

BACKGROUND: Despite lower extremity polydactyly (LEP) representing the most common congenital foot anomaly with functional and psychosocial implications, the literature is devoid of comprehensive, synthesizing reviews. The purpose of the current review is to identify an evidence-based approach to guide clinical management and shed light on reported functional and esthetic outcomes for postaxial polydactyly. METHODS: A scoping systematic review of primary clinical studies was performed. Baseline patient characteristics, diagnostic, and surgical approaches were recorded. Main outcomes included immediate postoperative pain, infections, callouses, scar cosmesis, residual deformities, and difficulty with shoe-wear or mobility. A qualitative synthesis of outcomes was performed, and a therapeutic algorithm was developed. RESULTS: Nine primary studies were identified representing 375 cases of LEP; mean age was 28.8 months (range: 20-40.6 months), and mean follow-up: 42.7 months (range: 1 month-41 years). Ray dominance and the presence of syndactyly were identified as the most important factors for surgical planning; age at surgery was insignificant. A lateral incision approach was used in 78% of cases. Postoperative callouses occurred in 22.1% of cases, infections in 2.5%, and intermittent pain in 11.9%. Significant issues with shoe-wear or mobilization and esthetic residual deformities were reported for 0.78% and 41.2% of cases, respectively. The incidence of residual valgus was 10.6%. CONCLUSION: LEP is most commonly managed with excision of the non-dominant ray and carries excellent long-term functional outcomes, as presented herein. Numerous techniques are discussed to minimize the risk of esthetic sequalae, although the presence of residual valgus remains a concern. A therapeutic algorithm is proposed for the optimal management of LEP.

Metastatic Prostatic Adenocarcinoma in Patient With Muir-Torre Syndrome Misdiagnosed as Metastatic Sebaceous Carcinoma: Case Report and Systematic Literature Review.

Muir-Torre syndrome (MTS) is a rare autosomal dominant condition characterized by the presence of at least one cutaneous sebaceous tumor and one visceral malignancy, arising mostly from the gastrointestinal tract. We present the case of a 63-year-old man with several cutaneous and visceral neoplasias in the context of MTS, and a pelvic lymph node lesion diagnosed initially as metastatic sebaceous carcinoma, but later identified as metastasis from a newly diagnosed prostatic adenocarcinoma. Histological similarities between these 2 lesions are discussed. A systematic literature review was conducted evaluating all published cases of patients with MTS in which metastases were reported. Eighteen articles were included in the final synthesis, representing 20 patients with a total of 26 metastases. Seventeen patients (85%) exhibited metastases originating from MTS-related neoplasms, whereas only 2 patients (11%) exhibited metastases from concomitant malignancies. Of the 85% of patients with metastases from MTS-related malignancies, most originated from noncutaneous sources (78% from visceral neoplasms and 22% from sebaceous carcinomas). When stratifying according to metastases, 23 cases (88%) originated from MTS-related lesions, whereas only 3 (12%) originated from unrelated malignancies. Our findings thus demonstrate that most metastases found in MTS patients (88%) do indeed originate from MTS-related neoplasms. Nevertheless, it remains imperative that a broad differential diagnosis is maintained when assessing a novel lesion, to avoid misdiagnoses, as in the present case, with significant therapeutic and prognostic implications.

Conservative Management of de Quervain Stenosing Tenosynovitis: Review and Presentation of Treatment Algorithm.

BACKGROUND: Nonsurgical management of de Quervain disease relies mainly on the use of oral nonsteroidal antiinflammatory drug administration, splint therapy, and corticosteroid injections. Although the latter is most effective, with documented success rates of 61 to 83 percent, there exists no clear consensus pertaining to conservative treatment protocols conferring the best outcomes. This article reports on all present conservative treatment modalities in use for the management of de Quervain disease and highlights specific treatment- and patient-related factors associated with the best outcomes. METHODS: A systematic search was performed using the PubMed database using appropriate search terms; two independent reviewers evaluated retrieved articles using strict inclusion and exclusion criteria. RESULTS: A total of 66 articles met the inclusion criteria for review, consisting of 22 articles reporting on outcomes following a single conservative treatment modality, eight articles reporting on combined treatment approaches, 13 articles directly comparing different conservative treatment regimens, and 23 case reports. CONCLUSIONS: A multimodal approach using splint therapy and corticosteroid injections appears to be more beneficial than either used in isolation. Although there exists some evidence showing that multipoint injection techniques and multiple injections before surgical referral may provide benefit over a single point injection technique and a single injection before surgery, corticosteroid use is not benign and should thus be performed with caution. Ultrasound was proven valuable in the visualization of an intercompartmental septum, and ultrasound-guided injections were shown to both be more accurate and confer better outcomes. Several prior and concurrent medical conditions may affect conservative treatment outcome. A Level I to II evidence-based treatment protocol is recommended for the optimal nonsurgical management of de Quervain disease.

Exposing medical students to various difficulty levels of simulated endotracheal intubations improves success rate: a randomised non-blinded trial.

Objective: Simulation training of endotracheal intubation (ETI) has proven to be an effective training tool. We used an adjustable airway mannequin that allows the achievement of various difficulty levels of laryngoscopy to train inexperienced medical students. The purpose of this study was to evaluate the effect of training using this novel airway mannequin on ETI success rates of medical students. Methods: This was a randomised non-blinded trial conducted at the Steinberg Centre for Simulation and Interactive Learning. Twenty recruited medical students were randomly allocated to two different training groups. During training, the mixed training group was asked to perform successful intubations in three levels of difficulty; the standard training group was asked to perform the same number of successful intubations in one level of difficulty. After training, all participants were asked to perform intubations using both the adjustable airway mannequin and a standard mannequin. Success rates and airway surface area visualised were compared between the two groups. Results: Students in the mixed training group had a significantly higher success rate both in the adjustable airway mannequin (p=0.01) and in the standard mannequin (p=0.02). Students in the mixed group had 51%, 59% and 47% significantly more visual area surface than students in the standard group during standard and difficult setup of the adjustable airway mannequin and the standard airway mannequin, respectively. Conclusions: The use of an adjustable airway mannequin to train medical students leads to superior ETI success rates and better glottis visualisation.

The Development of a Benchtop Breast Reconstruction Surgical Simulator.

A modified Delphi technique was used to survey plastics surgeons with an expertise in breast reconstruction from 6 university centers with plastic surgery residency programs across Canada. A list of the most challenging steps in teaching alloplastic breast reconstruction was obtained. From the survey results, a benchtop post-mastectomy breast reconstruction simulator was created using various silicon materials. The simulator was designed to be completely reusable with no disposable components necessary for each use. Senior plastic surgeons (n= 6) with an expertise in breast reconstruction were recruited and asked to perform a sub-pectoral, implant-based breast reconstruction on the simulator. Following the procedure, participants were asked to complete a survey and grade the simulator on its physical attributes, realism of experience, realism of material and overall experience.Preliminary face and content validation results based on the evaluations performed by those expert plastic surgeons showed excellent results among parameters evaluated, with an overall mean score of 4.7 on 5 (94.0%). Evaluators considered the six relevant anatomical components that were successfully included in the simulator.