Doctors of Osteopathic Medicine as Plastic Surgery Residents: Demographics, Credentials, and Pathways to Residency.

OBJECTIVE: Doctors of Osteopathic Medicine (DOs) are sparsely represented within plastic and reconstructive surgery (PRS) and recent changes including the elimination of step 1 scoring have further disadvantaged DO applicants. The demographics, degrees, and scholarly output of DO PRS trainees were compared to that of Doctors of Medicine (MDs) to identify areas of focus which could be used to increase competitiveness of DO applications. DESIGN: A cross-sectional study was created, including ACGME-accredited PRS program trainees during the 2020 to 2021 academic year. DO and MD trainee demographics and scholarly accomplishments were compared using t-test and chi-squared analysis. SETTING: Web-based publicly available information was collected for subjects. PARTICIPANTS: A total of 1092 PRS MD and DO trainees were identified. DOs made up only 2.7% (n = 30) and MDs made up 97.3% (n = 1062). RESULTS: More DOs trained in independent programs (63.3%) than integrated (36.7%) compared to MDs (88.2% v. 11.8%, p < 0.001) and more DOs trained at lower ranked PRS programs (60.0% of DOs and 18.1% of MDs trained at Q4 programs, p < 0.001). DOs had fewer publications (median, IQR: 1, [0-2]) compared to MDs (3, [1-8]), fewer citations (0, [0-6]) vs. (10, [1-56]) and lower H-index (1, [0-1]) vs. (1, [1-3]). CONCLUSION: DO candidates should consider research years in the field of PRS and optimize clinical experience opportunities to increase the competitiveness of their PRS applications. Special attention should be paid to providing networking and research opportunities to DOs who lack home institutions.

Subpectoral Implant Placement Is Not Protective against Postmastectomy Radiotherapy-Related Complications Compared to Prepectoral Placement.

BACKGROUND: Postmastectomy radiotherapy (PMRT) is associated with altered cosmetic outcomes and higher complication rates in implant-based breast reconstruction (IBR). Conventional wisdom suggests that muscle coverage is somewhat protective against PMRT-related complications. In this study, the authors compared surgical outcomes in patients who underwent two-stage prepectoral versus subpectoral IBR in the setting of PMRT. METHODS: The authors performed a retrospective cohort study of patients who underwent mastectomy and PMRT with two-stage IBR from 2016 to 2019. The primary outcome was breast-related complications, including device infection; the secondary outcome was device explantation. RESULTS: The authors identified 179 reconstructions (101 prepectoral and 78 subpectoral) in 172 patients with a mean follow-up time of 39.7 ± 14.4 months. There were no differences between the prepectoral and subpectoral reconstructions in rates of breast-related complications (26.7% and 21.8%, respectively; P = 0.274), device infection (18.8% and 15.4%, respectively; P = 0.307), skin flap necrosis (5.0% and 1.3%, respectively; P = 0.232), or device explantation (20.8% and 14.1%, respectively; P = 0.117). In adjusted models, compared with prepectoral device placement, subpectoral device placement was not associated with a lower risk of breast-related complications [hazard ratio (HR), 0.75; 95% confidence interval (CI), 0.41 to 1.36], device infection (HR, 0.73; 95% CI, 0.35 to 1.49), or device explantation (HR, 0.58; 95% CI, 0.28 to 1.19). CONCLUSIONS: Device placement plane was not predictive of complication rates in IBR in the setting of PMRT. Two-stage prepectoral IBR provides safe long-term outcomes with acceptable postoperative complication rates comparable to those with subpectoral IBR, even in the setting of PMRT. CLINICAL QUESTION/LEVEL OF EVIDENCE: Therapeutic, III.

Novel Method of Dual-innervated Free Gracilis Muscle Transfer for Facial Reanimation: A Case Series.

Background: Dynamic facial reanimation is the gold standard treatment for a paralyzed face. The use of the cross-face nerve graft (CFNG) in combination with the masseteric nerve to innervate the free gracilis muscle has been reported to provide both spontaneity and strong neural input. We report a case series of dual innervation, using a novel method where the branch to masseter is coapted to the side of the CFNG. Methods: Eight patients received free gracilis muscle transfer using the new dual innervation method between September 2014 and December 2017. The CFNG, which was performed nine months prior, was sutured in an end-to-end fashion to the obturator nerve. A nerve graft was coapted to the ipsilateral masseteric nerve and then sutured in an end-to-side fashion to the CFNG proximal to its coaptation to the obturator nerve. Results: All patients recovered smile function with and without teeth clenching around the same time period. Smiles without teeth clenching appeared later in two of eight patients and earlier in one of eight patients, being noted at an average of 8.25 months of follow-up versus 7.6 months. The estimate of true attainment is limited by the spacing of follow-up dates. Average follow-up time was 36.07 months (range: 10-71.5). FACE-Gram software smile analysis with and without biting demonstrated similar excursion on average (7.64 mm versus 8.6 mm respectively, P = 0.93), both of which are significantly improved from preoperation. Conclusion: This novel method of a dual-innervated free gracilis muscle transfer offers a viable technique that achieves a symmetric, strong, and emotional smile.

Surgical Outcomes of Vertical Rectus Abdominis Myocutaneous Flap Pelvic Reconstruction.

BACKGROUND: The vertical rectus abdominis myocutaneous (VRAM) flap has emerged as the workhorse flap for perineal and pelvic reconstruction. We aimed to evaluate outcomes of VRAM flap over a 20-year period and the role of mesh abdominal wall reinforcement following VRAM flap-based reconstruction. METHODS: We conducted a retrospective review of all consecutive patients who underwent pelvic reconstruction with a VRAM flap between January 2001 and March 2021. Our primary outcome measure included recipient and donor surgical site occurrences (SSOs). RESULTS: We identified a total of 546 patients (55% females) with a mean age was 58 years and mean BMI was 27 kg/m 2. Mesh was used at the time of VRAM reconstruction to reinforce the abdominal donor site in 36% of patients. Recipient-site SSOs occurred in 38% of patients while donor-site SSOs occurred in 17% of patients. Hernia was identified in 9.9% of patients while bulge developed in 6.4% of patients. Cox proportional hazards regression model for hernia occurrence identified age, BMI, tobacco use (HR 2.03, 95% CI [1.02 - 4.04]) and use as an extended VRAM (HR 2.13, 95% CI [1.04 - 4.36]). The use of mesh or component separation were not independent protective factors for hernia occurrence. CONCLUSION: The pedicled VRAM flap is versatile and is our preferred flap for reconstruction of pelvic and perineal defects. The use of mesh/component separation to allow for fascial closure was not shown to reduce donor site hernia occurrence.

Outcomes of Complex Abdominal Wall Reconstruction with Biologic Mesh in Patients with 8 Years of Follow-Up.

BACKGROUND: While many studies evaluated outcomes of abdominal wall reconstruction with biologic mesh, long-term data is lacking. In this study, we sought to analyze the outcomes of complex AWR with biologic mesh in a robust cohort of patients with a mean follow up of 8 years. METHODS: We conducted a longitudinal study of AWR patients from 2005 to 2019. Hernia recurrence was the primary outcome, and surgical site occurrence was the secondary outcome. Predictive/protective factors were identified using a Cox proportional hazards regression models. RESULTS: We identified 109 consecutive patients who met the inclusion criteria. Patient's mean (± SD) age was 57.5 ± 11.8 years, mean body mass index was 30.7 ± 7.2 kg/m2, and mean follow-up time was 96.2 ± 15.9 months. Fifty-six percent had clean defects, 34% had clean-contaminated defects, and 10% had contaminated/infected defects. Patients had a mean defect size of 261 ± 199.6 cm2 and mean mesh size of 391.3 ± 160.2 cm2. Nineteen patients (17.4%) developed HR at the final follow-up date. Obesity was independently associated with a four-fold higher risk of HR (hazard ratio, 3.98; 95%CI, 1.34 to 14.60, p = 0.02). SSOs were identified in 24.8% of patients. A prior hernia repair was associated with a three-fold higher risk of SSOs (Odds ratio, 3.13; 95%CI, 1.10 to 8.94, p = 0.03). No patient developed mesh infection. CONCLUSION: These longitudinal data demonstrate that complex AWR with biologic mesh provides long-term durable outcomes with acceptable HR and SSO rates despite high contamination levels, patients complexity, and large defect size.

The Global, Regional, and National Burden of Adult Lip, Oral, and Pharyngeal Cancer in 204 Countries and Territories: A Systematic Analysis for the Global Burden of Disease Study 2019.

Importance: Lip, oral, and pharyngeal cancers are important contributors to cancer burden worldwide, and a comprehensive evaluation of their burden globally, regionally, and nationally is crucial for effective policy planning. Objective: To analyze the total and risk-attributable burden of lip and oral cavity cancer (LOC) and other pharyngeal cancer (OPC) for 204 countries and territories and by Socio-demographic Index (SDI) using 2019 Global Burden of Diseases, Injuries, and Risk Factors (GBD) Study estimates. Evidence Review: The incidence, mortality, and disability-adjusted life years (DALYs) due to LOC and OPC from 1990 to 2019 were estimated using GBD 2019 methods. The GBD 2019 comparative risk assessment framework was used to estimate the proportion of deaths and DALYs for LOC and OPC attributable to smoking, tobacco, and alcohol consumption in 2019. Findings: In 2019, 370 000 (95% uncertainty interval [UI], 338 000-401 000) cases and 199 000 (95% UI, 181 000-217 000) deaths for LOC and 167 000 (95% UI, 153 000-180 000) cases and 114 000 (95% UI, 103 000-126 000) deaths for OPC were estimated to occur globally, contributing 5.5 million (95% UI, 5.0-6.0 million) and 3.2 million (95% UI, 2.9-3.6 million) DALYs, respectively. From 1990 to 2019, low-middle and low SDI regions consistently showed the highest age-standardized mortality rates due to LOC and OPC, while the high SDI strata exhibited age-standardized incidence rates decreasing for LOC and increasing for OPC. Globally in 2019, smoking had the greatest contribution to risk-attributable OPC deaths for both sexes (55.8% [95% UI, 49.2%-62.0%] of all OPC deaths in male individuals and 17.4% [95% UI, 13.8%-21.2%] of all OPC deaths in female individuals). Smoking and alcohol both contributed to substantial LOC deaths globally among male individuals (42.3% [95% UI, 35.2%-48.6%] and 40.2% [95% UI, 33.3%-46.8%] of all risk-attributable cancer deaths, respectively), while chewing tobacco contributed to the greatest attributable LOC deaths among female individuals (27.6% [95% UI, 21.5%-33.8%]), driven by high risk-attributable burden in South and Southeast Asia. Conclusions and Relevance: In this systematic analysis, disparities in LOC and OPC burden existed across the SDI spectrum, and a considerable percentage of burden was attributable to tobacco and alcohol use. These estimates can contribute to an understanding of the distribution and disparities in LOC and OPC burden globally and support cancer control planning efforts.

Impact of Obesity on Outcomes of Prepectoral vs Subpectoral Implant-Based Breast Reconstruction.

BACKGROUND: The impact of obesity on outcomes of prepectoral vs subpectoral implant-based reconstruction (IBR) is not well-established. OBJECTIVES: The goal of this study was to assess the surgical and patient-reported outcomes of prepectoral vs subpectoral IBR. The authors hypothesized that obese patients would have similar outcomes regardless of device plane. METHODS: We conducted a retrospective review of obese patients who underwent 2-stage IBR from January 2017 to December 2019. The primary endpoint was the occurrence of any breast-related complication; the secondary endpoint was device explantation. RESULTS: The authors identified a total of 284 reconstructions (184 prepectoral, 100 subpectoral) in 209 patients. Subpectoral reconstruction demonstrated higher rates of overall complications (50% vs 37%, P = .047) and device explantation (25% vs 12.5%, P = .008) than prepectoral reconstruction. In multivariable regression, subpectoral reconstruction was associated with higher risk of infection (hazard ratio [HR], 1.65; P = .022) and device explantation (HR, 1.97; P = .034). Subgroup analyses demonstrated significantly higher rates of complications and explantation in the subpectoral group in those with a body mass index (BMI) ≥ 35 and BMI ≥40. The authors found no significant differences in mean scores for satisfaction with the breast (41.57 ± 13.19 vs 45.50 ± 11.91, P = .469), psychosocial well-being (39.43 ± 11.23 vs 39.30 ± 12.49, P = .915), and sexual well-being (17.17 ± 7.83 vs 17.0 ± 9.03, P = .931) between subpectoral and prepectoral reconstruction. CONCLUSIONS: Prepectoral reconstruction was associated with significantly decreased overall complications, infections, and device explantation in obese patients compared with subpectoral reconstruction. Prepectoral reconstruction provides superior outcomes to subpectoral reconstruction with comparable patient-reported outcomes.

ChatGPT Is Equivalent to First-Year Plastic Surgery Residents: Evaluation of ChatGPT on the Plastic Surgery In-Service Examination.

BACKGROUND: ChatGPT is an artificial intelligence language model developed and released by OpenAI (San Francisco, CA) in late 2022. OBJECTIVES: The aim of this study was to evaluate the performance of ChatGPT on the Plastic Surgery In-Service Examination and to compare it to residents' performance nationally. METHODS: The Plastic Surgery In-Service Examinations from 2018 to 2022 were used as a question source. For each question, the stem and all multiple-choice options were imported into ChatGPT. The 2022 examination was used to compare the performance of ChatGPT to plastic surgery residents nationally. RESULTS: In total, 1129 questions were included in the final analysis and ChatGPT answered 630 (55.8%) of these correctly. ChatGPT scored the highest on the 2021 exam (60.1%) and on the comprehensive section (58.7%). There were no significant differences regarding questions answered correctly among exam years or among the different exam sections. ChatGPT answered 57% of questions correctly on the 2022 exam. When compared to the performance of plastic surgery residents in 2022, ChatGPT would rank in the 49th percentile for first-year integrated plastic surgery residents, 13th percentile for second-year residents, 5th percentile for third- and fourth-year residents, and 0th percentile for fifth- and sixth-year residents. CONCLUSIONS: ChatGPT performs at the level of a first-year resident on the Plastic Surgery In-Service Examination. However, it performed poorly when compared with residents in more advanced years of training. Although ChatGPT has many undeniable benefits and potential uses in the field of healthcare and medical education, it will require additional research to assess its efficacy.

Surgical and Patient-Reported Outcomes of 694 Two-Stage Prepectoral versus Subpectoral Breast Reconstructions.

BACKGROUND: Opinion regarding the optimal plane for prosthetic device placement in breast reconstruction patients has evolved. The purpose of this study was to assess the differences in complication rates and patient satisfaction between patients who underwent prepectoral and subpectoral implant-based breast reconstruction (IBR). METHODS: The authors conducted a retrospective cohort study of patients who underwent two-stage IBR at their institution from 2018 to 2019. Surgical and patient-reported outcomes were compared between patients who received a prepectoral versus a subpectoral tissue expander. RESULTS: A total of 694 reconstructions in 481 patients were identified (83% prepectoral, 17% subpectoral). The mean body mass index was higher in the prepectoral group (27 versus 25 kg/m 2 , P = 0.001), whereas postoperative radiotherapy was more common in the subpectoral group (26% versus 14%, P = 0.001). The overall complication rate was very similar, with 29.3% in the prepectoral and 28.9% in the subpectoral group ( P = 0.887). Rates of individual complications were also similar between the two groups. A multiple-frailty model showed that device location was not associated with overall complications, infection, major complications, or device explantation. Mean scores for Satisfaction with the Breast, Psychosocial Well-Being, and Sexual Well-Being were similar between the two groups. Median time to permanent implant exchange was significantly longer in the subpectoral group (200 versus 150 days, P < 0.001). CONCLUSION: Prepectoral breast reconstruction results in similar surgical outcomes and patient satisfaction compared with subpectoral IBR. CLINICAL QUESTION/LEVEL OF EVIDENCE: Therapeutic, III.

Artificial Intelligence Modeling to Predict Periprosthetic Infection and Explantation following Implant-Based Reconstruction.

BACKGROUND: Despite improvements in prosthesis design and surgical techniques, periprosthetic infection and explantation rates following implant-based reconstruction (IBR) remain relatively high. Artificial intelligence is an extremely powerful predictive tool that involves machine learning (ML) algorithms. We sought to develop, validate, and evaluate the use of ML algorithms to predict complications of IBR. METHODS: A comprehensive review of patients who underwent IBR from January of 2018 to December of 2019 was conducted. Nine supervised ML algorithms were developed to predict periprosthetic infection and explantation. Patient data were randomly divided into training (80%) and testing (20%) sets. RESULTS: The authors identified 481 patients (694 reconstructions) with a mean ± SD age of 50.0 ± 11.5 years, mean ± SD body mass index of 26.7 ± 4.8 kg/m 2 , and median follow-up time of 16.1 months (range, 11.9 to 3.2 months). Periprosthetic infection developed in 113 of the reconstructions (16.3%), and explantation was required with 82 (11.8%) of them. ML demonstrated good discriminatory performance in predicting periprosthetic infection and explantation (area under the receiver operating characteristic curve, 0.73 and 0.78, respectively), and identified nine and 12 significant predictors of periprosthetic infection and explantation, respectively. CONCLUSIONS: ML algorithms trained using readily available perioperative clinical data accurately predict periprosthetic infection and explantation following IBR. The authors' findings support incorporating ML models into perioperative assessment of patients undergoing IBR to provide data-driven, patient-specific risk assessment to aid individualized patient counseling, shared decision-making, and presurgical optimization.

Free Fillet Flap of Lower Extremity: 38 Amputations with Seven Examples of Targeted Muscle Reinnervation and Regenerative Peripheral Nerve Interfaces.

BACKGROUND: Extremely high-level lower extremity amputations are rare procedures that require significant soft-tissue and bony reconstruction. This study describes the use of fillet flaps for oncologic reconstruction and the incorporation of targeted muscle reinnervation (TMR) and regenerative peripheral nerve interfaces (RPNIs) for chronic pain prevention. METHODS: The authors performed a retrospective review of patients who underwent lower extremity fillet flaps at MD Anderson Cancer Center from January of 2004 through April of 2021. Surgical outcomes were summarized and compared. Numeric rating scale and patient-reported outcomes measures were collected. RESULTS: Thirty-eight fillet flaps were performed for lower extremity reconstruction. Extirpative surgery included external hemipelvectomy (42%), external hemipelvectomy with sacrectomy (32%), and supratrochanteric above-knee amputation (26%). Median defect size was 600 cm 2 , and 50% included a bony component. Twenty-one patients (55%) experienced postoperative complications, with 16 requiring operative intervention. There was an increased trend toward complications in patients with preoperative radiotherapy, although this was not significant (44% versus 65%; P = 0.203). Seven patients underwent TMR or RPNI. In these patients, the mean numeric rating scale residual limb pain score was 2.8 ± 3.4 ( n = 5; range, 0 to 4/10) and phantom limb pain was 4 ± 3.2 ( n = 6; range, 0 to 7/10). The mean Patient-Reported Outcomes Measures Information Systems T scores were as follows: pain intensity, 50.8 ± 10.6 ( n = 6; range, 30.7 to 60.5); pain interference, 59.2 ± 12.1 ( n = 5; range, 40.7 to 70.1); and pain behavior, 62.3 ± 6.7 ( n = 3; range, 54.6 to 67.2). CONCLUSIONS: Lower limb fillet flaps are reliable sources of bone, soft tissue, and nerve for reconstruction of oncologic amputation. TMR or RPNI are important new treatment adjuncts that should be considered during every amputation. CLINICAL QUESTION/LEVEL OF EVIDENCE: Therapeutic, IV.

Outcomes of Abdominal Wall Reconstruction with a Bovine versus a Porcine Acellular Dermal Matrix: A Propensity Score-Matched Analysis.

BACKGROUND: Abdominal wall reconstruction (AWR) is one of the most commonly performed procedures, yet large comparative studies comparing outcomes of AWR using bovine acellular dermal matrix (BADM) and porcine acellular dermal matrix (PADM) are lacking. METHODS: In this retrospective cohort study of patients who underwent AWR from March of 2005 to June of 2019, the primary comparative outcome measure was hernia recurrence with BADM versus PADM. The secondary outcome was the incidence of surgical-site occurrence (SSO) and surgical-site infection. A propensity score matching approach was applied to compare the clinical outcomes between the two study groups. RESULTS: The authors identified 725 patients who underwent AWR using BADM (50.5%) or PADM (49.5%). Their mean ± SD age was 59.8 ± 11.5 years, mean body mass index was 31.4 ± 6.7 kg/m 2 , and mean follow-up time was 42 ± 29 months. With propensity score matching, 219 matched pairs were identified. Hernia recurrence rates in BADM (11.4%) and PADM (13.7%) groups did not differ significantly ( P = 0.793). SSO (26.5% versus 29.2%; P = 0.518) and SSI (13.2% versus 11%; P = 0.456) rates did not differ significantly in the PADM and BADM groups, respectively. Conditional logistic regression model and marginal Cox proportional hazards regression model determined that type of acellular dermal matrix was not significantly associated with SSOs (adjusted OR, 1.11; 95% CI, 0.74 to 1.70; P = 0.589) or hernia recurrence (adjusted hazard ratio, 0.85; 95% CI, 0.50 to 1.42; P = 0.52). CONCLUSIONS: Both BADMs and PADMs provide durable, long-term outcomes. The hernia recurrence and postoperative surgical complication rates were not significantly different between BADM and PADM. CLINICAL QUESTION/LEVEL OF EVIDENCE: Therapeutic, III.

Free Fibula Flap for Extremity Oncologic Defects: Factors Influencing Union and Functional Outcomes.

BACKGROUND: The goal of this study was to evaluate outcomes after vascularized bone flap (VBF) reconstruction of oncologic bony extremity defects. A secondary goal was to compare union rates based on various insetting methods, including onlay, intermedullary, and intercalary. METHODS: The authors conducted a retrospective review of consecutive patients who received an extremity reconstruction with a fibula flap after oncologic resection between 2001 and 2019. RESULTS: The authors identified a total of 60 fibular VBFs in 55 patients (67% lower extremity, 33% upper extremity). The overall union rate was 91.7% (55 of 60). For lower extremity reconstructions, the mean time to full weightbearing was 16 months (range, 4 to 44 months). Fibula VBFs were onlay in 65% of cases, intercalary in 23%, and intramedullary in 12%. Forty-three percent of patients required a reoperation as a result of a surgical complication. Immediate femur reconstruction subgroup analysis demonstrated that onlay fibula flap orientation was associated with a significantly increased risk for any complication (odds ratio, 6.3; 95% CI, 1.4 to 28.7; P = 0.03) as well as an increased risk for requiring conversion to endoprostheses because of nonunion (OR, 12.1; 90% CI, 1.03 to 143.5; P = 0.03) compared with intramedullary placement. CONCLUSIONS: The free vascularized fibula flap is a reliable option for functional reconstruction of any long bone extremity defect, but complications in these complex procedures are not uncommon. In patients with immediate femur reconstructions, intramedullary fibula placement was associated with significantly lower complication and lower metallic implant conversion rates and a trend toward a more rapid early union compared with onlay VBF. CLINICAL QUESTION/LEVEL OF EVIDENCE: Therapeutic, III.

Outcomes of Third-Attempt Breast Reconstruction following Infection-Associated Failure of Secondary Implant-Based Reconstruction.

BACKGROUND: Implant-based reconstruction (IBR) is the most common method of breast reconstruction in the United States. Despite ongoing advancements, periprosthetic infection is a serious problem that often results in device explantation. The objective of this study was to evaluate the outcomes of third-attempt reconstruction in patients in whom secondary implant-based reconstruction failed because of infection. METHODS: The authors performed a retrospective review of patients who underwent mastectomy followed by IBR from 2000 to 2019. The outcomes of patients in whom secondary IBR failed because of infection and who ultimately underwent third-attempt breast reconstruction were analyzed. RESULTS: Of 6093 patients who underwent primary IBR, 13 patients had third-attempt breast reconstruction following infection-related explantation [median age, 52 years (interquartile range, 51 to 56 years); median body mass index, 23 kg/m 2 (interquartile range, 22 to 31 kg/m 2 ); median follow-up, 46 months (interquartile range, 16 to 62 months)]. Nine patients (70%) underwent IBR, two (15%) underwent IBR combined with pedicled latissimus dorsi flap, and two (15%) underwent abdominally based free tissue transfer. Third-attempt breast reconstruction was immediate in 46% of patients and delayed in 54%. The success rate was 78% in the IBR group, with a 23% complication rate. The success rate for autologous breast reconstruction was 100%, with one patient developing venous congestion necessitating return to the operating room. CONCLUSIONS: Third-attempt breast reconstruction following infection-associated failed secondary IBR is a safe and feasible option. Although the risk of failure is higher than that for primary implant-based reconstruction, a third attempt after secondary IBR infection had a surprisingly high 78% success rate. CLINICAL QUESTION/LEVEL OF EVIDENCE: Risk, III.

The Use of Machine Learning for Predicting Complications of Free-Flap Head and Neck Reconstruction.

BACKGROUND: Machine learning has been increasingly used for surgical outcome prediction, yet applications in head and neck reconstruction are not well-described. In this study, we developed and evaluated the performance of ML algorithms in predicting postoperative complications in head and neck free-flap reconstruction. METHODS: We conducted a comprehensive review of patients who underwent microvascular head and neck reconstruction between January 2005 and December 2018. Data were used to develop and evaluate nine supervised ML algorithms in predicting overall complications, major recipient-site complication, and total flap loss. RESULTS: We identified 4000 patients who met inclusion criteria. Overall, 33.7% of patients experienced a complication, 26.5% experienced a major recipient-site complication, and 1.7% suffered total flap loss. The k-nearest neighbors algorithm demonstrated the best overall performance for predicting any complication (AUROC = 0.61, sensitivity = 0.60). Regularized regression had the best performance for predicting major recipient-site complications (AUROC = 0.68, sensitivity = 0.66), and decision trees were the best predictors of total flap loss (AUROC = 0.66, sensitivity = 0.50). CONCLUSIONS: ML accurately identified patients at risk of experiencing postsurgical complications, including total flap loss. Predictions from ML models may provide insight in the perioperative setting and facilitate shared decision making.

The Use of Artificial Intelligence and Machine Learning in Surgery: A Comprehensive Literature Review.

Interest in the use of artificial intelligence (AI) and machine learning (ML) in medicine has grown exponentially over the last few years. With its ability to enhance speed, precision, and efficiency, AI has immense potential, especially in the field of surgery. This article aims to provide a comprehensive literature review of artificial intelligence as it applies to surgery and discuss practical examples, current applications, and challenges to the adoption of this technology. Furthermore, we elaborate on the utility of natural language processing and computer vision in improving surgical outcomes, research, and patient care.

The Virtual Interview Experience for MATCH 2021: A Pilot Survey of General Surgery Residency Program Directors.

BACKGROUND: Virtual interviews (VIs) for the 2020 residency application season were mandated as a result of the COVID-19 pandemic. We aimed to determine the perspectives of general surgery (GS) program directors (PDs) on the benefits and drawbacks of VIs. METHODS: A 14-item survey was emailed to all GS PDs from programs identified on the American Council for Graduate Medical Education website. Program directors were asked about the cost-time benefit of VIs, its ability to assess candidates, and their thoughts on the future of VIs for evaluating residency applicants. RESULTS: 60 PDs responded corresponding to a response rate of 21%. While 93% agreed/strongly agreed that VIs were less expensive, only 35% found VIs to be less time-consuming. 75% and 67%, respectively, disagreed/strongly disagreed that VIs allowed for an easier assessment of an applicant's fit, and personality and communication skills. Almost one-half of our survey respondents suggested that VIs made the selection committee rely more heavily on objective applicant data. Almost two-thirds of GS PDs suggested that they would adopt both VI and in-person interview formats for future application cycles. The median [interquartile range] cost saved through the implementation of VIs was US$ 4500 [1625 - 10 000]. CONCLUSION: Remarkably, VIs have been swiftly imbibed by all residency programs and many aspects of the VI experience were positive. While MATCH 2021 has definitely proved to be one of its kind, the implementation of VIs has been met with overall broad success and a promising future awaits this novel modality of resident selection to GME programs in the United States.