EventsThe 2nd International Conference on Bioengineering
Published
This submission belongs to the session S3. Biosignal Processing of the event The 2nd International Conference on Bioengineering
Published date
16 Nov, 2026
Citation
Yiela Saperstein, Uday Sankar Akash Vankayala, Ali Sohail, Bivin George, Liliane Deeb, Machine Learning vs Traditional Risk Scores for Predicting 30-Day In-Hospital Mortality in Upper Gastrointestinal Bleeding, in Proceedings of The 2nd International Conference on Bioengineering, Barcelona, 10 November–13 November 2026, MDPI: Basel, Switzerland
Share
Email
Facebook
Twitter
LinkedIn

Machine Learning vs Traditional Risk Scores for Predicting 30-Day In-Hospital Mortality in Upper Gastrointestinal Bleeding

image
Bivin George 1
image
1. Staten Island University Hospital, Northwell Health, NY
Abstract

Introduction:Upper gastrointestinal bleeding(UGIB) causes substantial morbidity/mortality. Early risk stratification guides triage, resource-allocation, and timely intervention. Clinical tools(AIMS65, modified-ABC, pre-endoscopic-Rockall) have modest predictive performance that don’t incorporate nonlinear relationships. We developed machine-learning(ML)-models using triage/early data to predict in-hospital-mortality-within-30-days-of-UGIB-presentation(IHM30) and compared with established risk scores.

Methods:Retrospective cohort study of adults ≥18 with acute UGIB(1/2019-12/2024) at SIUH. Predictors were demographics, vitals, comorbidities, medications, labs within 2-4hrs of presentation. Primary outcome was IHM30. Missing data was handled using multiple imputation(m=10) with missingness indicators for variables with substantial missingness. Data was split into train(80%)/test(20%) sets. Supervised models were developed(penalized-logistic-regression(LR), decision-tree(DT), random-forest(RF), XGBoost) with nested cross-validation hyperparameter tuning. Performance was evaluated on the test set(AUROC, AUPRC, Brier-score, decision-curve-analysis). ML-models were compared with established risk scores using DeLong testing.

Results/Discussion:Mortality occurred in 454/8,501 patients(5.3%). ML-models demonstrated strong discrimination: LR(AUROC 0.824), DT(0.768), RF(0.823), XGBoost(0.817). ML-models significantly outperformed AIMS65(AUROC 0.674), modified-ABC(0.732), Rockall(0.734)(p < 0.001). AUPRC ranged from 0.26-0.32, exceeding baseline prevalence(~0.05). RF/XGBoost achieved lowest Brier scores(~0.045). At high-sensitivity thresholds(≥0.90), RF/XGBoost identified 93-98% of deaths. Decision-curve-analysis demonstrated ML-models, particularly XGBoost/RF, provided greater net benefit than traditional scores across clinically relevant risk thresholds(2-10%). Lactate had 55% missingness. Lactate availability was the strongest mortality predictor. Other predictors included age, lactate, albumin, creatinine, INR.

Conclusion:ML-models improved prediction of IHM30 compared with traditional risk scores. XGBoost/RF showed greatest clinical utility with superior net benefit across clinically relevant thresholds. Lactate availability’s strong predictive contribution suggests that model performance reflects clinician behavior/latent concern in addition to objective data, supporting future incorporation of clinician-gestalt into predictive models. Local recalibration and external validation are needed before implementation. Overall, ML-based early risk stratification in UGIB may serve as a triage-adjunct to support care prioritization, escalation decisions, and resource allocation.

Keywords
Upper GI bleed
machine learning
Clinical predictions
Protease-Activated Lipid Nanoparticles Enable Tumor-Selective Transfection through Reversible Surface Masking
A Leader–Follower Flexor System Using EMG-Based Motion Prediction for Remote Rehabilitation