Linking gene expression to clinical outcomes in pediatric Crohn's disease using machine learning.

Pediatric Crohn's disease (CD) is characterized by a severe disease course with frequent complications. We sought to apply machine learning-based models to predict risk of developing future complications in pediatric CD using ileal and colonic gene expression. Gene expression data was generated from 101 formalin-fixed, paraffin-embedded (FFPE) ileal and colonic biopsies obtained from treatment-naïve CD patients and controls. Clinical outcomes including development of strictures or fistulas and progression to surgery were analyzed using differential expression and modeled using machine learning. Differential expression analysis revealed downregulation of pathways related to inflammation and extra-cellular matrix production in patients with strictures. Machine learning-based models were able to incorporate colonic gene expression and clinical characteristics to predict outcomes with high accuracy. Models showed an area under the receiver operating characteristic curve (AUROC) of 0.84 for strictures, 0.83 for remission, and 0.75 for surgery. Genes with potential prognostic importance for strictures (REG1A, MMP3, and DUOX2) were not identified in single gene differential analysis but were found to have strong contributions to predictive models. Our findings in FFPE tissue support the importance of colonic gene expression and the potential for machine learning-based models in predicting outcomes for pediatric CD.

The value of national accreditation program for rectal cancer: A survey of accredited programs and programs seeking accreditation.

BACKGROUND: Significant variation in rectal cancer care has been demonstrated in the United States. The National Accreditation Program for Rectal Cancer was established in 2017 to improve the quality of rectal cancer care through standardization and emphasis on a multidisciplinary approach. The aim of this study was to understand the perceived value and barriers to achieving the National Accreditation Program for Rectal Cancer accreditation. METHODS: An electronic survey was developed, piloted, and distributed to rectal cancer programs that had already achieved or were interested in pursuing the National Accreditation Program for Rectal Cancer accreditation. The survey contained 40 questions with a combination of Likert scale, multiple choice, and open-ended questions to provide comments. This was a mixed methods study; descriptive statistics were used to analyze the quantitative data, and thematic analysis was used to analyze the qualitative data. RESULTS: A total of 85 rectal cancer programs were sent the survey (22 accredited, 63 interested). Responses were received from 14 accredited programs and 41 interested programs. Most respondents were program directors (31%) and program coordinators (40%). The highest-ranked responses regarding the value of the National Accreditation Program for Rectal Cancer accreditation included "improved quality and culture of rectal cancer care," "enhanced program organization and coordination," and "challenges our program to provide optimal, high-quality care." The most frequently cited barriers to the National Accreditation Program for Rectal Cancer accreditation were cost and lack of personnel. CONCLUSION: Our survey found significant perceived value in the National Accreditation Program for Rectal Cancer accreditation. Adhering to standards and a multidisciplinary approach to rectal cancer care are critical components of a high-quality care rectal cancer program.

Factors Associated With Performing IPAA After Total Colectomy for Ulcerative Colitis.

BACKGROUND: IPAA is considered the procedure of choice for restorative surgery after total colectomy for ulcerative colitis. Previous studies have examined the rate of IPAA within individual states but not at the national level in the United States. OBJECTIVE: This study aimed to assess the rate of IPAA after total colectomy for ulcerative colitis in a national population and identify factors associated with IPAA. DESIGN: This was a retrospective cohort study. SETTINGS: This study was performed in the United States. PATIENTS: Patients who were aged 18 years or older and who underwent total colectomy between 2009 and 2019 for a diagnosis of ulcerative colitis were identified within a commercial database. This database excluded patients with public insurance, including all patients older than 65 years with Medicare. MAIN OUTCOME MEASURES: The primary outcome was IPAA. Multivariable logistic regression was used to assess the association between covariates and the likelihood of undergoing IPAA. RESULTS: In total, 2816 patients were included, of whom 1414 (50.2%) underwent IPAA, 928 (33.0%) underwent no further surgery, and 474 (16.8%) underwent proctectomy with end ileostomy. Younger age, lower comorbidities, elective case, and laparoscopic approach in the initial colectomy were significantly associated with IPAA but socioeconomic status was not. LIMITATIONS: This retrospective study included only patients with commercial insurance. CONCLUSIONS: A total of 50.2% of patients who had total colectomy for ulcerative colitis underwent IPAA, and younger age, lower comorbidities, and elective cases are associated with a higher rate of IPAA placement. This study emphasizes the importance of ensuring follow-up with colorectal surgeons to provide the option of restorative surgery, especially for patients undergoing urgent or emergent colectomies. See Video Abstract . FACTORES ASOCIADOS CON LA REALIZACIN DE ANASTOMOSIS ANALBOLSA ILEAL DESPUS DE UNA COLECTOMA TOTAL POR COLITIS ULCEROSA: ANTECEDENTES:La anastomosis ileo-anal se considera el procedimiento de elección para la cirugía reparadora tras la colectomía total por colitis ulcerosa. Estudios previos han examinado la tasa de anastomosis ileo-anal dentro de los estados individuales, pero no a nivel nacional en los Estados Unidos.OBJETIVO:Evaluar la tasa de anastomosis bolsa ileal-anal después de la colectomía total para la colitis ulcerosa en una población nacional e identificar los factores asociados con la anastomosis bolsa ileal-anal.DISEÑO:Se trata de un estudio de cohortes retrospectivo.LUGAR:Este estudio se realizó en los Estados Unidos.PACIENTES:Los pacientes que tenían ≥18 años de edad que se sometieron a colectomía total entre 2009 y 2019 para un diagnóstico de colitis ulcerosa fueron identificados dentro de una base de datos comercial. Esta base de datos excluyó a los pacientes con seguro público, incluidos todos los pacientes >65 años con Medicare.MEDIDAS DE RESULTADO PRINCIPALES:El resultado primario fue la anastomosis ileal bolsa-anal. Se utilizó una regresión logística multivariable para evaluar la asociación entre las covariables y la probabilidad de someterse a una anastomosis ileal.RESULTADOS:En total, se incluyeron 2.816 pacientes, de los cuales 1.414 (50,2%) se sometieron a anastomosis ileo-anal, 928 (33,0%) no se sometieron a ninguna otra intervención quirúrgica y 474 (16,8%) se sometieron a proctectomía con ileostomía terminal. La edad más joven, las comorbilidades más bajas, el caso electivo, y el abordaje laparoscópico en la colectomía inicial se asociaron significativamente con la anastomosis ileal bolsa-anal, pero no el estatus socioeconómico.LIMITACIONES:Este estudio retrospectivo incluyó sólo pacientes con seguro comercial.CONCLUSIONES:Un 50,2% de los pacientes se someten a anastomosis ileo-anal y la edad más joven, las comorbilidades más bajas y los casos electivos se asocian con una mayor tasa de colocación de anastomosis ileo-anal. Esto subraya la importancia de asegurar el seguimiento con cirujanos colorrectales para ofrecer la opción de cirugía reparadora, especialmente en pacientes sometidos a colectomías urgentes o emergentes. (Traducción-Dr. Yolanda Colorado ).

Long-term Outcomes of the Kono-S Anastomosis: A Multicenter Study.

BACKGROUND: Postoperative recurrence remains a significant problem in Crohn's disease, and the mesentery is implicated in the pathophysiology. The Kono-S anastomosis was designed to exclude the mesentery from a wide anastomotic lumen, limit luminal distortion and fecal stasis, and preserve innervation and vascularization. OBJECTIVE: To review postoperative complications and long-term outcomes of the Kono-S anastomosis in a large series of consecutive unselected patients with Crohn's disease. DESIGN: Retrospective study of prospectively collected patients. SETTINGS: Four tertiary referral centers. PATIENTS: Consecutive patients with Crohn's disease who underwent resection with Kono-S anastomosis between May 2010 and June 2022. INTERVENTIONS: Extracorporeal handsewn Kono-S anastomosis. MAIN OUTCOME MEASURES: Postoperative outcomes and recurrence defined as endoscopic, clinical, laboratory, or surgical, including endoscopic, intervention. RESULTS: A total of 262 consecutive patients (53.4% male) were included. The mean duration of disease at surgery was 145.1 months. One hundred thirty-five patients (51.5%) had previous abdominal surgery for Crohn's disease. Forty-four patients (17%) were actively smoking and 150 (57.3%) were on biologic therapy. Anastomotic failure occurred in 4 (1.5%), with 2 patients requiring reoperation (0.7%). Sixteen patients had postoperative surgical site infection (6.1%). With a median follow-up of 49.4 months, 20 patients (7.6%) were found to have surgical recurrence. In the multivariate analysis, perianal disease (OR = 2.83, p = 0.001), urgent/emergent surgery (OR = 3.23, p = 0.007), and postoperative use of steroids (OR = 2.29, p = 0.025) were associated with increased risk of overall recurrence. LIMITATIONS: Retrospective study and variability of perioperative medical therapy. CONCLUSIONS: This study showed very low postoperative complication rates despite the complexity of the patient population. There was a low rate of surgical recurrence, likely due to the intrinsic advantages of the anastomotic configuration and the low rate of postoperative septic complications. In experienced hands, the Kono-S anastomosis is a safe technique with very promising short- and long-term results. Randomized controlled trials are underway to validate this study's findings. See Video Abstract . RESULTADO A LARGO PLAZO DE LA ANASTOMOSIS KONOS UN ESTUDIO MULTICNTRICO: ANTECEDENTES:La recurrencia posoperatoria sigue siendo un problema importante en la enfermedad de Crohn y el mesenterio está implicado en la fisiopatología. La anastomosis Kono-S fue diseñada para excluir el mesenterio de una anastomosis amplia, limitar la distorsión luminal y la estasis fecal y preservar la inervación y vascularización.OBJETIVO:Revisar las complicaciones posoperatorias y los resultados a largo plazo de la anastomosis Kono-S en una gran serie de pacientes consecutivos no seleccionados con enfermedad de Crohn.DISEÑO:Estudio retrospectivo de pacientes recolectados prospectivamente.ESCENARIO:Cuatro centros de referencia terciarios.PACIENTES:Pacientes consecutivos con enfermedad de Crohn sometidos a resección con anastomosis Kono-S entre mayo de 2010 y junio de 2022.INTERVENCIONES:Anastomosis Kono-S extracorpórea manual.PRINCIPALES MEDIDAS DE RESULTADO:Resultados posoperatorios y recurrencia definidos como endoscópicos, clínicos, de laboratorio o quirúrgicos, incluida la intervención endoscópica.RESULTADOS:Se incluyeron un total de 262 pacientes consecutivos (53,4% varones). La duración media de la enfermedad al momento de la cirugía fue de 145,1 meses. Ciento treinta y cinco pacientes (51,5%) habían tenido cirugía abdominal previa por enfermedad de Crohn. Cuarenta y cuatro pacientes (17%) eran fumadores activos y 150 (57,3%) estaban en tratamiento biológico. Se produjo filtración anastomótica en 4 (1,5%) y 2 pacientes requirieron reoperación (0,7%). Dieciséis pacientes tuvieron infección postoperatoria del sitio quirúrgico (6,1%). Con una mediana de seguimiento de 49,4 meses, se encontró que 20 pacientes (7,6%) tuvieron recurrencia quirúrgica. En el análisis multivariado, la enfermedad perianal (OR = 2,83, p = 0,001), la cirugía urgente/emergente (OR = 3,23, p = 0,007), el uso postoperatorio de esteroides (OR = 2,29, p = 0,025) se asociaron con un mayor riesgo de recurrencia general.LIMITACIÓN:Estudio retrospectivo. Variabilidad del tratamiento médico perioperatorio.CONCLUSIONES:Nuestro estudio mostró tasas de complicaciones postoperatorias muy bajas a pesar de la complejidad de la población de pacientes. Hubo una baja tasa de recurrencia quirúrgica, probablemente debido a las ventajas intrínsecas de la configuración anastomótica y la baja tasa de complicaciones sépticas posoperatorias. En manos experimentadas, la anastomosis Kono-S es una técnica segura con resultados muy prometedores a corto y largo plazo. Se están realizando estudios randomizados controlados para validar nuestros hallazgos. (Traducción-Dr. Felipe Bellolio ).

Prediction of Pathologic Complete Response for Rectal Cancer Based on Pretreatment Factors Using Machine Learning.

BACKGROUND: Pathologic complete response after neoadjuvant therapy is an important prognostic indicator for locally advanced rectal cancer and may give insights into which patients might be treated nonoperatively in the future. Existing models for predicting pathologic complete response in the pretreatment setting are limited by small data sets and low accuracy. OBJECTIVE: We sought to use machine learning to develop a more generalizable predictive model for pathologic complete response for locally advanced rectal cancer. DESIGN: Patients with locally advanced rectal cancer who underwent neoadjuvant therapy followed by surgical resection were identified in the National Cancer Database from years 2010 to 2019 and were split into training, validation, and test sets. Machine learning techniques included random forest, gradient boosting, and artificial neural network. A logistic regression model was also created. Model performance was assessed using an area under the receiver operating characteristic curve. SETTINGS: This study used a national, multicenter data set. PATIENTS: Patients with locally advanced rectal cancer who underwent neoadjuvant therapy and proctectomy. MAIN OUTCOME MEASURES: Pathologic complete response defined as T0/xN0/x. RESULTS: The data set included 53,684 patients. Pathologic complete response was experienced by 22.9% of patients. Gradient boosting showed the best performance with an area under the receiver operating characteristic curve of 0.777 (95% CI, 0.773-0.781), compared with 0.684 (95% CI, 0.68-0.688) for logistic regression. The strongest predictors of pathologic complete response were no lymphovascular invasion, no perineural invasion, lower CEA, smaller size of tumor, and microsatellite stability. A concise model including the top 5 variables showed preserved performance. LIMITATIONS: The models were not externally validated. CONCLUSIONS: Machine learning techniques can be used to accurately predict pathologic complete response for locally advanced rectal cancer in the pretreatment setting. After fine-tuning a data set including patients treated nonoperatively, these models could help clinicians identify the appropriate candidates for a watch-and-wait strategy. See Video Abstract . EL CNCER DE RECTO BASADA EN FACTORES PREVIOS AL TRATAMIENTO MEDIANTE EL APRENDIZAJE AUTOMTICO: ANTECEDENTES:La respuesta patológica completa después de la terapia neoadyuvante es un indicador pronóstico importante para el cáncer de recto localmente avanzado y puede dar información sobre qué pacientes podrían ser tratados de forma no quirúrgica en el futuro. Los modelos existentes para predecir la respuesta patológica completa en el entorno previo al tratamiento están limitados por conjuntos de datos pequeños y baja precisión.OBJETIVO:Intentamos utilizar el aprendizaje automático para desarrollar un modelo predictivo más generalizable para la respuesta patológica completa para el cáncer de recto localmente avanzado.DISEÑO:Los pacientes con cáncer de recto localmente avanzado que se sometieron a terapia neoadyuvante seguida de resección quirúrgica se identificaron en la Base de Datos Nacional del Cáncer de los años 2010 a 2019 y se dividieron en conjuntos de capacitación, validación y prueba. Las técnicas de aprendizaje automático incluyeron bosque aleatorio, aumento de gradiente y red neuronal artificial. También se creó un modelo de regresión logística. El rendimiento del modelo se evaluó utilizando el área bajo la curva característica operativa del receptor.ÁMBITO:Este estudio utilizó un conjunto de datos nacional multicéntrico.PACIENTES:Pacientes con cáncer de recto localmente avanzado sometidos a terapia neoadyuvante y proctectomía.PRINCIPALES MEDIDAS DE VALORACIÓN:Respuesta patológica completa definida como T0/xN0/x.RESULTADOS:El conjunto de datos incluyó 53.684 pacientes. El 22,9% de los pacientes experimentaron una respuesta patológica completa. El refuerzo de gradiente mostró el mejor rendimiento con un área bajo la curva característica operativa del receptor de 0,777 (IC del 95%: 0,773 - 0,781), en comparación con 0,684 (IC del 95%: 0,68 - 0,688) para la regresión logística. Los predictores más fuertes de respuesta patológica completa fueron la ausencia de invasión linfovascular, la ausencia de invasión perineural, un CEA más bajo, un tamaño más pequeño del tumor y la estabilidad de los microsatélites. Un modelo conciso que incluye las cinco variables principales mostró un rendimiento preservado.LIMITACIONES:Los modelos no fueron validados externamente.CONCLUSIONES:Las técnicas de aprendizaje automático se pueden utilizar para predecir con precisión la respuesta patológica completa para el cáncer de recto localmente avanzado en el entorno previo al tratamiento. Después de realizar ajustes en un conjunto de datos que incluye pacientes tratados de forma no quirúrgica, estos modelos podrían ayudar a los médicos a identificar a los candidatos adecuados para una estrategia de observar y esperar. (Traducción-Dr. Ingrid Melo ).

Financial Relationships in General Surgery Education: Recent Trends in Industry Payments to General Surgery Residency Leadership.

INTRODUCTION: Residency programs and their directors frequently receive funding from industry payers. Both general surgery residency program directors (PDs) and assistant program directors (APDs) receive industry funding for various reasons, including educational advancement. This study investigates recent trends in industry payments to both PDs and APDs to better understand the financial relationships among leaders in residency education. METHODS: We compared industry payments to general surgery residency PDs and APDs from 2019 to 2021 utilizing the U.S. Centers for Medicare & Medicaid Services (CMS) open payments database. In addition, secondary analyses were performed among PDs to assess differences based on gender, practicing surgical specialty, and geographical region. RESULTS: During the study period (2019-2021), PDs received payments amounting to 2,882,821 USD. PDs were found to receive more funding than APDs, with each receiving average funding of 10,045 vs. 323 USD (p < 0.01), respectively, over the study period. There was a significant decrease in total payments from 2019 to 2020 (1,512,190 vs. 868,811 USD; p < 0.01). Total payments made in 2021 were similar compared to 2020 (905,836 vs. 868,811 USD; p = 0.1). We found that male PDs received significantly more in-industry payments when compared to female PDs (11,702 USD per PD vs. 3971 USD per PD, p < 0.01). CONCLUSION: This study presents initial data that residency program leadership has robust biomedical industry relationships, and further research is warranted to investigate the impacts of these payments on program resources, educational opportunities for residents, and program outcomes. Male PDs received significantly more industry payments when compared to female PDs. Leaders in the surgical training community must cautiously ensure that these industry relationships are appropriately navigated.

Perspectives on Referring for Rectal Cancer Surgery: a Survey Study of Gastroenterologist and General Surgeons in Iowa.

PURPOSE: To understand referral practices for rectal cancer surgical care and to secondarily determine differences in referral practices by two main hypothesized drivers of referral: the rurality of the community endoscopists' practice and their affiliation with a colorectal surgeon. METHODS: Community gastroenterologists and general surgeons in Iowa completed a mailed questionnaire on practice demographics, volume, and referral practices for rectal cancer patients. Rurality was operationalized with RUCA codes. RESULTS: Twenty-two of 53 gastroenterologists (42%) and 120 of 188 general surgeons (64%) (total 144/241, 60%) in Iowa responded. Most performed colonoscopies, including 22 gastroenterologists (100%) and 96 general surgeons (80%). Regular referral of rectal cancer patients to colorectal surgeons was reported for 57% of urban physicians affiliated with a colorectal surgeon, 33% of urban physicians not affiliated with a colorectal surgeon, and 57% and 72% of physicians in large and small rural areas, respectively, who were not affiliated with a colorectal surgeon. High surgeon volume, high hospital volume, and colorectal surgeon specialty were important factors in the referral decisions for over half the physicians. 69% of diagnosing urban general surgeons reported performing rectal cancer surgery about half the time or more, while 85% of small rural and 60% of large rural diagnosing general surgeons reported never or rarely performing rectal cancer surgery. CONCLUSIONS: Diagnosing physicians have variable rectal cancer referral practices, including consistency in referred to surgeon and prioritization of volume and specialization. Prioritizing specialized or high-volume rectal cancer surgical care would require changing existing referring patterns.

How to say "I don't know": development and evaluation of workshops for medical students and surgical residents on communicating uncertainty using the ADAPT framework.

Purpose: Uncertainty, or the conscious awareness of having doubts, is pervasive in medicine, from differential diagnoses and the sensitivity of diagnostic tests, to the absence of a single known recovery path. While openness about uncertainty is necessary for shared decision-making and is a pillar of patient-centered care, it is a challenge to do so while preserving patient confidence. The authors' aim was to develop, pilot, and evaluate an uncertainty communication curriculum to prepare medical students and residents to confidently navigate such conversations. Methods: The authors developed ADAPT, a mnemonic framework to improve student comprehension and recall of the important steps in uncertainty disclosure: assess the patient's knowledge, disclose uncertainty directly, acknowledge patient emotions, plan next steps, and temper expectations. Using this framework, the authors developed, piloted, and evaluated an uncertainty communications course as part of an ongoing communication curriculum for second year medical students in 2020 and with surgical residents in 2021. Results: Learner confidence in uncertainty communication skills significantly increased post-class. Resident confidence in disclosing uncertainty was significantly correlated with observer ratings of their related communication skills during simulation. Students expressed positive experiences of the class, noting particular appreciation for the outline of steps included in the ADAPT framework, and the ability to observe a demonstration prior to practice. Conclusions: The ADAPT communication curriculum was effective at increasing learner confidence and performance in communicating uncertainty. More rigorous evaluation of the ADAPT protocol will be important in confirming its generalizability. Supplementary Information: The online version contains supplementary material available at 10.1007/s44186-022-00075-4.

Analysis of Specimen Mammography with Artificial Intelligence to Predict Margin Status.

BACKGROUND: Intraoperative specimen mammography is a valuable tool in breast cancer surgery, providing immediate assessment of margins for a resected tumor. However, the accuracy of specimen mammography in detecting microscopic margin positivity is low. We sought to develop an artificial intelligence model to predict the pathologic margin status of resected breast tumors using specimen mammography. METHODS: A dataset of specimen mammography images matched with pathologic margin status was collected from our institution from 2017 to 2020. The dataset was randomly split into training, validation, and test sets. Specimen mammography models pretrained on radiologic images were developed and compared with models pretrained on nonmedical images. Model performance was assessed using sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). RESULTS: The dataset included 821 images, and 53% had positive margins. For three out of four model architectures tested, models pretrained on radiologic images outperformed nonmedical models. The highest performing model, InceptionV3, showed sensitivity of 84%, specificity of 42%, and AUROC of 0.71. Model performance was better among patients with invasive cancers, less dense breasts, and non-white race. CONCLUSIONS: This study developed and internally validated artificial intelligence models that predict pathologic margins status for partial mastectomy from specimen mammograms. The models' accuracy compares favorably with published literature on surgeon and radiologist interpretation of specimen mammography. With further development, these models could more precisely guide the extent of resection, potentially improving cosmesis and reducing reoperations.

Estimating Risk of Locoregional Failure and Overall Survival in Anal Cancer Following Chemoradiation: A Machine Learning Approach.

BACKGROUND: Optimal treatment of anal squamous cell carcinoma (ASCC) is definitive chemoradiation. Patients with persistent or recurrent disease require abdominoperineal resection (APR). Current models for predicting need for APR and overall survival are limited by low accuracy or small datasets. This study sought to use machine learning (ML) to develop more accurate models for locoregional failure and overall survival for ASCC. METHODS: This study used the National Cancer Database from 2004-2018, divided into training, validation, and test sets. We included patients with stage I-III ASCC who underwent chemoradiation. Our primary outcomes were need for APR and 3-year overall survival. Random forest (RF), gradient boosting (XGB), and neural network (NN) ML-based models were developed and compared with logistic regression (LR). Accuracy was assessed using area under the receiver operating characteristic curve (AUROC). RESULTS: APR was required in 5.3% (1,015/18,978) of patients. XGB performed best with AUROC of 0.813, compared with 0.691 for LR. Tumor size, lymphovascular invasion, and tumor grade showed the strongest influence on model predictions. Mortality was 23.6% (7,988/33,834). AUROC for XGB and LR were similar at 0.766 and 0.748, respectively. For this model, age, radiation dose, sex, and insurance status were the most influential variables. CONCLUSIONS: We developed and internally validated machine learning-based models for predicting outcomes in ASCC and showed higher accuracy versus LR for locoregional failure, but not overall survival. After external validation, these models may assist clinicians with identifying patients with ASCC at high risk of treatment failure.

Program Website Evaluation Regarding Dedicated Research Years Offered in General Surgery Residency Programs in the United States.

INTRODUCTION: Research is a vital component in the advancements of surgical sciences due to the reliance of treatment options on innovations and outcomes of patient care. This study aimed to identify research pathways, opportunities, and academic productivities of different general surgery residency programs in the United States. MATERIALS AND METHODS: A web-based review was conducted concerning accredited US general surgery residency programs. Each program's official website was assessed for the availability of research year, compulsory status, duration, type, structure, and location. The study also identified faculty supervision, research day, funding, output, and opportunities to obtain an advanced degree. RESULTS: Data were collected from all 313 general surgery programs in the United States, out of which 127 (41%) offered a dedicated research year to their residents. The research year was deemed mandatory in 27 programs (8%) and optional in 100 programs (32%). Seventy-two programs (23%) offered to start the dedicated research year after postgraduate year 2 or postgraduate year 3. Twenty-two programs (7.02%) provided examples of resident publications and presentations. Resident research day was cited by 42 programs (13.41%). On campus research opportunity was mentioned by nine programs (2.8%), while the off campus chance was provided by 10 programs (3.19%). Furthermore, 36 programs (11.5%) demonstrated potential funding sources. Finally, 38 (12.14%) programs mentioned receiving advanced degrees after the research year. CONCLUSIONS: Although dedicated research time is provided to trainees for some research programs, there is a lack of structure and the need to expand the available content and information regarding research opportunities for the various general surgery residency programs.

Predicting readmission after bariatric surgery using machine learning.

BACKGROUND: While bariatric surgery is an effective method for achieving long-term weight loss, postoperative readmissions are associated with negative clinical outcomes and significant costs. OBJECTIVES: We aimed to use machine learning (ML) algorithms to predict readmissions and compare results to logistic regression. SETTING: Hospitals participating in the Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program, United States. METHODS: Patients who underwent sleeve gastrectomy (SG), Roux-en-Y gastric bypass (RYGB), and biliopancreatic diversion with duodenal switch between 2016 and 2020 were selected from the Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program (MBSAQIP) database. Patient variables reported by the MBSAQIP database were analyzed by ML algorithms random forest (RF), gradient boosting (XGB), and deep neural networks (NN), and the results of the predictive models were compared to logistic regression using area under the receiver operating characteristic curve (AUROC). RESULTS: Our study included 863,348 patients, of which 39,068 (4.52%) were readmitted. AUROC scores were XGB .785 (95% CI .784-.786), RF .785 (95% CI .784-.785), and NN .754 (95% CI .753-.754), compared with .62 (95% CI .62-.621) for logistic regression (LR) (P < .001). The sensitivity and specificity for XGB, the best performing model, were 73.81% and 70%, compared with 52.94% and 70% for logistic regression. The most important variables were intervention or reoperation prior to discharge, unplanned ICU admission, initial procedure, and the intraoperative transfusion. CONCLUSIONS: ML demonstrates significant advantages over logistic regression when predicting 30-day readmission following bariatric surgery. With external validation, models could identify the best candidates for early discharge or targeted postdischarge resources.

Application of machine learning to predict postoperative gastrointestinal bleed in bariatric surgery.

BACKGROUND: Postoperative gastrointestinal bleeding (GIB) is a rare but serious complication of bariatric surgery. The recent rise in extended venous thromboembolism regimens as well as outpatient bariatric surgery may increase the risk of postoperative GIB or lead to delay in diagnosis. This study seeks to use machine learning (ML) to create a model that predicts postoperative GIB to aid surgeon decision-making and improve patient counseling for postoperative bleeds. METHODS: The Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program (MBSAQIP) database was used to train and validate three types of ML methods: random forest (RF), gradient boosting (XGB), and deep neural networks (NN), and compare them with logistic regression (LR) regarding postoperative GIB. The dataset was split using fivefold cross-validation into training and validation sets, in an 80/20 ratio. The performance of the models was assessed using area under the receiver operating characteristic curve (AUROC) and compared with the DeLong test. Variables with the strongest effect were identified using Shapley additive explanations (SHAP). RESULTS: The study included 159,959 patients. Postoperative GIB was identified in 632 (0.4%) patients. The three ML methods, RF (AUROC 0.764), XGB (AUROC 0.746), and NN (AUROC 0.741) all outperformed LR (AUROC 0.709). The best ML method, RF, was able to predict postoperative GIB with a specificity and sensitivity of 70.0% and 75.4%, respectively. Using DeLong testing, the difference between RF and LR was determined to be significant with p < 0.01. Type of bariatric surgery, pre-op hematocrit, age, duration of procedure, and pre-op creatinine were the 5 most important features identified by ML retrospectively. CONCLUSIONS: We have developed a ML model that outperformed LR in predicting postoperative GIB. Using ML models for risk prediction can be a helpful tool for both surgeons and patients undergoing bariatric procedures but more interpretable models are needed.

Prediction of Ureteral Injury During Colorectal Surgery Using Machine Learning.

BACKGROUND: Ureteral injury (UI) is a rare but devastating complication during colorectal surgery. Ureteral stents may reduce UI but carry risks themselves. Risk predictors for UI could help target the use of stents, but previous efforts have relied on logistic regression (LR), shown moderate accuracy, and used intraoperative variables. We sought to use an emerging approach in predictive analytics, machine learning, to create a model for UI. METHODS: Patients who underwent colorectal surgery were identified in the National Surgical Quality Improvement Program (NSQIP) database. Patients were split into training, validation, and test sets. The primary outcome was UI. Three machine learning approaches were tested including random forest (RF), gradient boosting (XGB), and neural networks (NN), and compared with traditional LR. Model performance was assessed using area under the curve (AUROC). RESULTS: The data set included 262,923 patients, of whom 1519 (.578%) experienced UI. Of the modeling techniques, XGB performed the best, with an AUROC score of .774 (95% CI .742-.807) compared with .698 (95% CI .664-.733) for LR. Random forest and NN performed similarly with scores of .738 and .763, respectively. Type of procedure, work RVUs, indication for surgery, and mechanical bowel prep showed the strongest influence on model predictions. CONCLUSIONS: Machine learning-based models significantly outperformed LR and previous models and showed high accuracy in predicting UI during colorectal surgery. With proper validation, they could be used to support decision making regarding the placement of ureteral stents preoperatively.

Characteristics and symptomatology of colorectal cancer in the young.

BACKGROUND: The incidence of colorectal cancer in patients <50 years has rapidly risen recently. Understanding the presenting symptoms may facilitate earlier diagnosis. We aimed to delineate patient characteristics, symptomatology, and tumor characteristics of colorectal cancer in a young population. METHODS: A retrospective cohort study was conducted evaluating patients <50 years diagnosed between 2005 and 2019 with primary colorectal cancer at a university teaching hospital. The number and character of colorectal cancer-related symptoms at presentation was the primary outcome measured. Patient and tumor characteristics were also collected. RESULTS: Included were 286 patients with a median age of 44 years, with 56% <45 years. Nearly all patients (95%) were symptomatic at presentation, with 85% having 2 or more symptoms. The most common symptoms were pain (63%), followed by change in stool habits (54%), rectal bleeding (53%), and weight loss (32%). Diarrhea was more common than constipation. More than 50% had symptoms for at least 3 months before diagnosis. The number and duration of symptoms were similar in patients older than 45 compared to those younger. Most cancers were left-sided (77%) and advanced stage at presentation (36% stage III, 39% stage IV). CONCLUSION: In this cohort of young patients with colorectal cancer, the majority presented with multiple symptoms having a median duration of 3 months. It is essential that providers be mindful of the ever-increasing incidence of colorectal malignancy in young patients, and that those with multiple, durable symptoms should be offered screening for colorectal neoplasms based on symptoms alone.

Computer Vision Analysis of Specimen Mammography to Predict Margin Status.

Intra-operative specimen mammography is a valuable tool in breast cancer surgery, providing immediate assessment of margins for a resected tumor. However, the accuracy of specimen mammography in detecting microscopic margin positivity is low. We sought to develop a deep learning-based model to predict the pathologic margin status of resected breast tumors using specimen mammography. A dataset of specimen mammography images matched with pathology reports describing margin status was collected. Models pre-trained on radiologic images were developed and compared with models pre-trained on non-medical images. Model performance was assessed using sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). The dataset included 821 images and 53% had positive margins. For three out of four model architectures tested, models pre-trained on radiologic images outperformed domain-agnostic models. The highest performing model, InceptionV3, showed a sensitivity of 84%, a specificity of 42%, and AUROC of 0.71. These results compare favorably with the published literature on surgeon and radiologist interpretation of specimen mammography. With further development, these models could assist clinicians with identifying positive margins intra-operatively and decrease the rate of positive margins and re-operation in breast-conserving surgery.