Machine Learning Model for Outcome Prediction of Patients Suffering from Acute Diverticulitis Arriving at the Emergency Department—A Proof of Concept Study

Abstract

Background & Aims: We aimed at identifying specific emergency department (ED) risk factors for developing complicated acute diverticulitis (AD) and evaluate a machine learning model (ML) for predicting complicated AD. Methods: We analyzed data retrieved from unselected consecutive large bowel AD patients from five hospitals from the Mount Sinai health system, NY. The study time frame was from January 2011 through March 2021. Data were used to train and evaluate a gradient-boosting machine learning model to identify patients with complicated diverticulitis, defined as a need for invasive intervention or in-hospital mortality. The model was trained and evaluated on data from four hospitals and externally validated on held-out data from the fifth hospital. Results: The final cohort included 4997 AD visits. Of them, 129 (2.9%) visits had complicated diverticulitis. Patients with complicated diverticulitis were more likely to be men, black, and arrive by ambulance. Regarding laboratory values, patients with complicated diverticulitis had higher levels of absolute neutrophils (AUC 0.73), higher white blood cells (AUC 0.70), platelet count (AUC 0.68) and lactate (AUC 0.61), and lower levels of albumin (AUC 0.69), chloride (AUC 0.64), and sodium (AUC 0.61). In the external validation cohort, the ML model showed AUC 0.85 (95% CI 0.78–0.91) for predicting complicated diverticulitis. For Youden’s index, the model showed a sensitivity of 88% with a false positive rate of 1:3.6. Conclusions: A ML model trained on clinical measures provides a proof of concept performance in predicting complications in patients presenting to the ED with AD. Clinically, it implies that a ML model may classify low-risk patients to be discharged from the ED for further treatment under an ambulatory setting.

Development of an Ultrasound-Based Clinical Decision Rule to Rule-out Diverticulitis

“…In a similar wavelength to the ndings in this study, a large multi-center retrospective review of acute diverticulitis patients developed a machine learning algorithm that achieved 88% sensitivity and 72% speci city in identifying diverticulitis patients at risk of procedural or surgical intervention or hospital mortality [23]. Although the focus of this study was to identify patients safe for discharge from the ED, not those who are at high risk for serious complications, the suggestion that there exists a vital sign nding that can further risk stratify patients is echoed in the presented study.…”

Diagnosis of Inflammatory Bowel Disease and Colorectal Cancer through Multi-View Stacked Generalization Applied on Gut Microbiome Data

“…The importance of adding clinical data is also indirectly confirmed by higher feature importance of the base learner trained on a clinical data. Such a diversity can potentially stem from the fact that clinical data reflects traits with long term effects on disease e.g., adaptive immune responses [ 6 ], race-related [ 44 ] or sex-related [ 31 ] differences, while microbial features reflect more dynamic traits, e.g., microbial dysbiosis [ 4 , 29 ] or response to treatment [ 11 ]. The performance of stacking model trained on inflammatory bowel disease can be further improved by including more clinical features.…”

Application of Machine Learning Based on Structured Medical Data in Gastroenterology

“…Klang E et al employed 31 clinical and biological characteristics in a study involving 4497 individuals to identify specific risk factors in the emergency department associated with complex acute diverticulitis. They utilized the XGBoost model, which demonstrated an internal test sensitivity of 88% and a negative predictive value of 99% [26]. Yoshii S. et al developed an ML algorithm based on Lasso and elastic-net regularization techniques.…”