109 research outputs found
Super Learner Enhances Postoperative Complication Prediction in Colorectal Surgery
No full textObjective: To determine if a Super Learner (SL) machine learning approach could improve the predictive accuracy of the American College of Surgeons Risk Calculator (ACS-RC) for postoperative complications in patients undergoing colorectal surgery. Summary of Background Data: Machine learning (ML) has shown significant potential to advance medical fields, including surgical risk prediction. Current tools, like the ACS-RC which uses logistic regression and extreme gradient boosting, are standard but may be enhanced by more advanced ML ensembles. Methods: This retrospective study analyzed colorectal surgery cases from the 2018-2022 ACS National Surgical Quality Improvement Program (NSQIP) database. An SL model, which combines multiple ML algorithms, was developed to predict fourteen postoperative outcomes. Its performance was compared against traditional logistic regression (LOG) and extreme gradient boosting (XGB) models. Key performance metrics included discrimination (AUROC, AUPRC) and calibration (Brier score, Hosmer-Lemeshow test). Results: The SL model demonstrated superior performance across all predicted complications when compared to both LOG and XGB. It showed superior discrimination for severe outcomes, achieving an AUROC greater than 0.94 for predicting mortality. The SL model was also more accurate in predicting infectious complications and length of stay, and its calibration metrics indicated a better overall fit and accuracy. Conclusions: The Super Learner model enhances the accuracy of postoperative risk prediction in colorectal surgery. Its superior performance suggests it is a promising tool for improving personalized patient counseling, aiding clinical decision-making, and optimizing resource allocation
ASO Author Reflections: Presacral Neuroendocrine Neoplasms—Insights into a Rare Disease
No full textNo abstrac
Evaluating the Impact of Robotic IPAA
No full textObjective: To compare robotic-assisted proctectomy with ileal pouch-anal anastomosis (R-IPAA) outcomes and laparoscopic proctectomy with ileal pouch-anal anastomosis (L-IPAA) within a specialized robotic surgery center, using matching techniques to minimize potential confounding factors. Summary background data: Minimally invasive approaches, particularly laparoscopy, have improved outcomes for IBD and FAP patients undergoing IPAA. Robotic-assisted surgery offers potential technical advantages, but its definitive superiority over laparoscopy in this context remains under debate. Methods: This retrospective, STROBE-compliant study analyzed 234 consecutive IPAA patients (117 robotic, 117 laparoscopic). Data encompassed patient demographics, intraoperative details, and postoperative outcomes. We employed various matching techniques to address potential bias. Primary endpoints focused on 30-day complications, readmissions, and reoperations, with secondary endpoints including hospital stay, blood loss, and stoma closure rates. Results: R-IPAA demonstrated a lower conversion rate to open surgery (P=0.02), a shorter hospital stay (P=0.04), and reduced blood loss (P=0.0003) compared to L-IPAA. While overall 30-day morbidity rates were similar (P=0.4), matched analyses suggested a trend towards fewer reoperations and 3-month IPAA-associated complications after diverting loop ileostomy closure in the robotic group. However, these differences did not reach statistical significance. Conclusions: In a high-volume robotic surgery center, R-IPAA reduced the risk of conversion to open surgery while reducing intraoperative blood loss and providing shorter length of stay with equivalent perioperative outcomes. Promising trends to reduce 30-day reoperations and surgical complications following DLI closure were observed after a matching analysis
ACADEMIC PRODUCTIVITY AFTER COLON AND RECTAL SURGERY FELLOWSHIP
No full textPurpose/Background: Early career publication productivity among academic surgeons after Colon and Rectal Surgery (CRS) Fellowship has not been studied. Hypothesis/Aim: We aimed to describe predictive factors of academic surgeons’ publication productivity using pre-CRS fellowship characteristics. Methods/Interventions: Candidates included those applying for CRS fellowship at Mayo Clinic between 2015 and 2018 and appointed in an academic position post-fellowship. Academic position was defined as Instructor, Assistant Professor, Associate Professor, or Professor. It was assessed through a cross-checking of information on public online sources (American College of Surgeons, American Society of Colon and Rectal Surgeons, university website, and social media). Academic position and publications were blindly assessed by three authors (G.C, S.A., S.B.) in July 2021, any incongruity was further resolved. The number of publications post-fellowship and authorship positions was retrieved from PubMed, with a median follow-up of 2.5 years [range: 1-4 years]. Academics top quartile (Q1) was defined according to a composite productivity outcome of publications/year ratio as first, last and any-position author. Data were compared between Q1 and the less productive quartiles (Q2-4). Pre-fellowship data were retrieved from the Electronic Residency Application Service (ERAS®) application. Results/Outcome(s): Among 130 defined academic surgeons, first author, last author, and any position publications were less than one publication/year ratio in 80%, 86%, and 47%, respectively. First author publications were one, two, or ≥three publications/year ratio in 16%, 4%, and 2% of the academics, while last author publications in 9%, 3%, and 3%. Overall, the number of publications as any author position was one in 21%, two in 13%, three to five in 11%, and >five publications/year ratio in 10% of the academics. Academics in the top quartile (Q1) more frequently attended a top-20 medical school, top-20 Surgery Residency Program, and completed a Research Fellowship. Prior to fellowship, Q1 academics had more publications as 1st author and had more presentations. Understandably, these individuals frequently received research awards and had earned advanced degrees (Master/PhD) (Table 1). Limitations: Its retrospective nature and follow-up duration limited our study. Conclusions/Discussion: Among early-career academics, half coauthored less than one article/year after CRS fellowship, and more than 80% authored less than one article/year as first or last author. Conversely, academics with the highest publication productivity during their early career demonstrated high pre-fellowship research and publication performances
- …
