Review of machine learning for optical imaging of burn wound severity assessment.

Significance: Over the past decade, machine learning (ML) algorithms have rapidly become much more widespread for numerous biomedical applications, including the diagnosis and categorization of disease and injury. Aim: Here, we seek to characterize the recent growth of ML techniques that use imaging data to classify burn wound severity and report on the accuracies of different approaches. Approach: To this end, we present a comprehensive literature review of preclinical and clinical studies using ML techniques to classify the severity of burn wounds. Results: The majority of these reports used digital color photographs as input data to the classification algorithms, but recently there has been an increasing prevalence of the use of ML approaches using input data from more advanced optical imaging modalities (e.g., multispectral and hyperspectral imaging, optical coherence tomography), in addition to multimodal techniques. The classification accuracy of the different methods is reported; it typically ranges from ∼70% to 90% relative to the current gold standard of clinical judgment. Conclusions: The field would benefit from systematic analysis of the effects of different input data modalities, training/testing sets, and ML classifiers on the reported accuracy. Despite this current limitation, ML-based algorithms show significant promise for assisting in objectively classifying burn wound severity.

Assessing Trends in Supply and Demand for Pediatric Surgery Training.

OBJECTIVE: This study assessed the supply and demand for Pediatric Surgery training in the U.S. from 2008 to 2022. We hypothesized that in the Pediatric Surgery Match: match rates would increase over time; U.S. MD Graduates would have higher match rates than non-U.S. MD Graduates; and fewer applicants would match at one of their top fellowship choices. DESIGN: This was a retrospective cohort study of Pediatric Surgery Match applicants (2008-2022). Cochran-Armitage tests elucidated temporal trends and chi square tests compared outcomes by applicant archetype. SETTING: Accreditation Council for Graduate Medical Education (ACGME)-accredited Pediatric Surgery training programs in the United States and non-ACGME-accredited programs in Canada. PARTICIPANTS: A total of 1,133 applicants for Pediatric Surgery training. RESULTS: From 2008 to 2012, growth in the annual number of fellowship positions (34-43, 27% increase) exceeded growth in number of applicants (62-69, 11% increase) (p < 0.001). Over the study period, the applicant-to-training ratio peaked at 2.1 to 2.2 in 2017 to 2018 and decreased to 1.4 to 1.6 in 2021 to 2022. The annual match rate for U.S. MD Graduates increased from 60% to 68% (p < 0.05), but decreased from 40% to 22% (p < 0.05) for non-U.S. MD Graduates. In 2022, there was a 3.1-fold difference in match rates between U.S. MD and non-U.S. MD Graduates (68% vs 22%, p < 0.001). The percentage of applicants that matched at their first choice (25%-20%, p < 0.001), second choice (11%-4%, p < 0.001), and third choice (7%-4%, p < 0.001) fellowships decreased over the study period. The percentage of applicants that matched at their fourth choice to least desirable fellowship increased from 23% to 33% (p < 0.001). CONCLUSIONS: The demand for Pediatric Surgery training peaked in 2017 to 2018 and has decreased since. However, the Pediatric Surgery Match remains competitive especially for non-U.S. MD Graduates. More research is needed to understand barriers to matching into Pediatric Surgery for non-U.S. MD Graduates.

Correlation of Scholarly Activity and Departmental Clinical Productivity in a Surgical Subspecialty.

INTRODUCTION: Promotion within academic surgery involves demonstrated excellence in administrative, clinical, and scholarly activities. The present study analyzes the relationship between scholarly and clinical productivity in the field of reconstructive microsurgery. METHODS: This is a retrospective cohort study of microsurgery fellowship directors (MFDs). Data on clinical productivity were obtained from the American Society for Reconstructive Microsurgery and scholarly productivity from Scopus. Outcomes were department annual free flap volume, number of publications, and h-index. Descriptive statistics were calculated, and nonparametric tests were used to compare continuous variables. RESULTS: Thirty-nine MFDs were included in this study. All were plastic surgery residency trained and 38% trained under the independent training pathway. Most underwent formal fellowship training in reconstructive microsurgery (89%). The top three microsurgery fellowships trained 37% of all MFDs. Twenty-five percent of MFDs trained at the institution where they ultimately became program director. Twenty percent of MFDs had an additional degree (4 MS, 2 PhD, and 1 MBA). The median number of annual free flaps performed per institution was 175 (interquartile range [IQR] 122). The median h-index was 17 (IQR 13) resulting from 48 (IQR 99) publications. There was a correlation between department annual free flap volume and h-index (r = 0.333, P = 0.038). CONCLUSIONS: There is a correlation between academic productivity of MFDs and the clinical productivity of their department. This study provides a benchmark for aspiring reconstructive microsurgeons.

Surgical Benchmarks for ACGME-accredited Adult Reconstructive Orthopaedic Fellowship Training.

INTRODUCTION: Higher case volumes correlate with improved outcomes in total joint arthroplasty surgery. The purpose of this study was to understand the effect of adult reconstruction fellowship training on reported case volume in a contemporary cohort of orthopaedic surgeons. METHODS: The Accreditation Council for Graduate Medical Education provided case logs for orthopaedic surgery residents and adult reconstructive orthopaedic fellows from 2017 to 2018 to 2020 to 2021. Reported case volumes for total joint arthroplasty surgeries were compared using Student t tests. RESULTS: One hundred eighty-three adult reconstructive orthopaedic fellows and 3,000 orthopaedic surgery residents were included. Residents reported more total hip arthroplasty cases (98.9 ± 30 to 106.1 ± 33, 7.3% increase, P < 0.05) and total knee arthroplasty cases (126.0 ± 41 to 136.5 ± 44, 8.3% increase, P < 0.05) over the study period. On average, fellows reported 439.6 total cases: primary total knee arthroplasty, 164.9 cases (37.5%); primary total hip arthroplasty, 146.8 cases (33.4%); revision total knee arthroplasty, 35.2 cases (8.0%); revision total hip arthroplasty, 33.0 cases (7.5%); unicompartmental knee arthroplasty, 4.4 cases (1.0%); and other, 55.0 cases (12.5%). Overall, adult reconstructive orthopaedic fellowship reported between 1.7- and 2.0-fold more joint arthroplasty cases during 1 year of fellowship training than 5 years of residency ( P < 0.001). DISCUSSION: Adult reconstructive orthopaedic fellowship training provides notable exposure to additional cases after residency training. The results from this study may inform prospective applicants on the effect of fellowship training in total joint arthroplasty and help establish benchmarks in case volume for independent practice.

Analysis of Strengths in Exposure to Cases During Plastic and Orthopaedic Hand Surgery Fellowships.

INTRODUCTION: Prospective residents interested in hand surgery must decide to apply for hand surgery fellowships sponsored by different specialties. This study compares case volumes reported during plastic surgery and orthopaedic hand surgery fellowships. METHODS: The American Council for Graduate Medical Education case logs of accredited hand surgery fellowships were analyzed for hand surgery cases (2012 to 2013 to 2020 to 2021). The reported case volume was compared by specialty. Temporal trends were described, intrapathway variabilities calculated, and interpathway differences calculated with Student t -tests. RESULTS: Two hundred plastic surgery (13%) and 1,323 orthopaedic (87%) hand surgery fellows were included. The number of orthopaedic hand surgery fellowships increased from 58 in 2012 to 2013 to 70 in 2020 to 2021 (21% increase), whereas the number of plastic surgery fellowships was stable at 16. Orthopaedic hand surgery fellows reported more hand surgery cases (764 ± 22 versus 628 ± 226), arthroscopy cases (53 ± 54 versus 23 ± 38), and miscellaneous hand surgery cases (42 ± 23 versus 31 ± 18) than plastic surgery hand fellows. Plastic surgery hand fellows reported more cases in wound closure with graft, wound reconstruction with flap, nerve injury, and vascular repair. Overall, orthopaedic surgery offered more experience in 15 case categories (58%), while plastic surgery offered more experience in five case categories (19%). Six case categories (23%) had no difference between specialties. DISCUSSION: Although orthopaedic hand surgery fellowship affords more cases overall, plastic surgery hand fellowships have unique strengths in wound reconstruction with grafts and flaps, nerve injury, and vascular repair. Ultimately, results from this study create a benchmark to improve future training opportunities for hand surgery fellows and orthopaedic surgery residents.

A Prospective Multicenter Study Evaluating Learning Curves and Competence in Endoscopic Ultrasound and Endoscopic Retrograde Cholangiopancreatography Among Advanced Endoscopy Trainees: The Rapid Assessment of Trainee Endoscopy Skills Study.

BACKGROUND & AIMS: On the basis of the Next Accreditation System, trainee assessment should occur on a continuous basis with individualized feedback. We aimed to validate endoscopic ultrasound (EUS) and endoscopic retrograde cholangiopancreatography (ERCP) learning curves among advanced endoscopy trainees (AETs) by using a large national sample of training programs and to develop a centralized database that allows assessment of performance in relation to peers. METHODS: ASGE recognized training programs were invited to participate, and AETs were graded on ERCP and EUS exams by using a validated competency assessment tool that assesses technical and cognitive competence in a continuous fashion. Grading for each skill was done by using a 4-point scoring system, and a comprehensive data collection and reporting system was built to create learning curves by using cumulative sum analysis. Individual results and benchmarking to peers were shared with AETs and trainers quarterly. RESULTS: Of the 62 programs invited, 20 programs and 22 AETs participated in this study. At the end of training, median number of EUS and ERCP performed/AET was 300 (range, 155-650) and 350 (125-500), respectively. Overall, 3786 exams were graded (EUS, 1137; ERCP-biliary, 2280; ERCP-pancreatic, 369). Learning curves for individual end points and overall technical/cognitive aspects in EUS and ERCP demonstrated substantial variability and were successfully shared with all programs. The majority of trainees achieved overall technical (EUS, 82%; ERCP, 60%) and cognitive (EUS, 76%; ERCP, 100%) competence at conclusion of training. CONCLUSIONS: These results demonstrate the feasibility of establishing a centralized database to report individualized learning curves and confirm the substantial variability in time to achieve competence among AETs in EUS and ERCP. ClinicalTrials.gov: NCT02509416.

Assessment of racial and sex disparities in open femoral fractures.

BACKGROUND: Open femoral fractures are common; however, many factors may affect treatment protocol. We aim to assess any racial/ethnic or sex disparities associated with the definitive fixation of open femoral fractures. METHODS: ICD-9 codes from the National Trauma Data Bank (2007 to 2010) for patients greater than or equal to 18 years with open femoral fractures who underwent operative management at level I or II trauma centers were identified and analyzed. RESULTS: Of the 9,406 cases, the majority were White (61%), men (73%), and aged between 25 and 44 years (41%). The odds of definitive fixation after hospital day 2 (odds ratio [OR] .96, 95% confidence interval [CI] .82 to 1.09, P = .53) or any complication (OR .96, 95% CI .79 to 1.15, P = .69) were not associated with race/ethnicity. Men were 17% less likely to have surgery after hospital day 2 (OR .83, 95% CI .78 to .96, P < .001), and 18% more likely to have a complication (OR 1.18, 95% CI 1.03 to 1.35, P = .02). CONCLUSIONS: There are no racial/ethnic disparities associated with the timing of definitive fixation. Men are more likely to undergo fixation earlier than women; however, they are more likely to have a complication. Fixation within the first 2 hospital days may decrease complications.

Development of a spatially offset Raman spectroscopy probe for breast tumor surgical margin evaluation.

The risk of local recurrence for breast cancers is strongly correlated with the presence of a tumor within 1 to 2 mm of the surgical margin on the excised specimen. Previous experimental and theoretical results suggest that spatially offset Raman spectroscopy (SORS) holds much promise for intraoperative margin analysis. Based on simulation predictions for signal-to-noise ratio differences among varying spatial offsets, a SORS probe with multiple source-detector offsets was designed and tested. It was then employed to acquire spectra from 35 frozen-thawed breast tissue samples in vitro. Spectra from each detector ring were averaged to create a composite spectrum with biochemical information covering the entire range from the tissue surface to ∼2 mm below the surface, and a probabilistic classification scheme was used to classify these composite spectra as "negative" or "positive" margins. This discrimination was performed with 95% sensitivity and 100% specificity, or with 100% positive predictive value and 94% negative predictive value.

Monte Carlo model of spatially offset Raman spectroscopy for breast tumor margin analysis.

We have previously demonstrated the discrimination of two layers of soft tissue, specifically normal breast tissue overlying breast tumor, using spatially offset Raman spectroscopy (SORS). In this report, a Monte Carlo code for evaluating SORS in soft tissues has been developed and compared to experimental results. The model was employed to investigate the effects of tissue and probe geometry on SORS measurements and therefore to develop the design strategies of applying SORS for breast tumor surgical margin evaluation. The model was used to predict SORS signals for different tissue geometries difficult to precisely control experimentally, such as varying normal and tumor layer sizes and the addition of a third layer. The results from the model suggest that, using source-detector separations of up to 3.75 mm, SORS can detect sub-millimeter-thick tumors under a 1 mm normal layer, and tumors at least 1 mm thick can be detected under a 2 mm normal layer.