Predicting inpatient mortality in patients with inflammatory bowel disease: A machine learning approach |
| |
| Authors: | Paris Charilaou Sonmoon Mohapatra Sotirios Doukas Maanit Kohli Dhruvil Radadiya Kalpit Devani Arkady Broder Olivier Elemento Dana J Lukin Robert Battat |
| |
| Affiliation: | 1. New York Presbyterian Hospital/Weill-Cornell Medical College - Jill Roberts Center for Inflammatory Bowel Disease, Weill Cornell Medicine, New York, New York, USA;2. Division of Gastroenterology and Hepatology, Mayo Clinic, Scottsdale, Arizona, USA;3. Department of Medicine, Saint Peter's University Hospital/Rutgers-RWJ Medical School, New Brunswick, New Jersey, USA;4. Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, USA;5. Division of Gastroenterology and Hepatology, University of Kansas Medical Center, Kansas City, Kansas, USA;6. Division of Gastroenterology and Hepatology, Prisma Health Greenville Memorial Hospital, Greenville, South Carolina, USA;7. Division of Gastroenterology and Hepatology, Saint Peter's University Hospital/Rutgers-RWJ Medical School, New Brunswick, New Jersey, USA;8. Weill Cornell Medical College - Caryl and Israel Englander Institute for Precision Medicine, Institute for Computational Biomedicine, Weill Cornell Medicine, New York, New York, USA;9. Department of Gastroenterology and Hepatology, Centre Hospitalier de l' Universite de Montreal, Montreal, Quebec, Canada |
| |
| Abstract: | Background and Aim Data are lacking on predicting inpatient mortality (IM) in patients admitted for inflammatory bowel disease (IBD). IM is a critical outcome; however, difficulty in its prediction exists due to infrequent occurrence. We assessed IM predictors and developed a predictive model for IM using machine-learning (ML). Methods Using the National Inpatient Sample (NIS) database (2005–2017), we extracted adults admitted for IBD. After ML-guided predictor selection, we trained and internally validated multiple algorithms, targeting minimum sensitivity and positive likelihood ratio (+LR) ≥ 80% and ≥ 3, respectively. Diagnostic odds ratio (DOR) compared algorithm performance. The best performing algorithm was additionally trained and validated for an IBD-related surgery sub-cohort. External validation was done using NIS 2018. Results In 398 426 adult IBD admissions, IM was 0.32% overall, and 0.87% among the surgical cohort (n = 40 784). Increasing age, ulcerative colitis, IBD-related surgery, pneumonia, chronic lung disease, acute kidney injury, malnutrition, frailty, heart failure, blood transfusion, sepsis/septic shock and thromboembolism were associated with increased IM. The QLattice algorithm, provided the highest performance model (+LR: 3.2, 95% CI 3.0–3.3; area-under-curve [AUC]:0.87, 85% sensitivity, 73% specificity), distinguishing IM patients by 15.6-fold when comparing high to low-risk patients. The surgical cohort model (+LR: 8.5, AUC: 0.94, 85% sensitivity, 90% specificity), distinguished IM patients by 49-fold. Both models performed excellently in external validation. An online calculator ( https://clinicalc.ai/im-ibd/ ) was developed allowing bedside model predictions. Conclusions An online prediction-model calculator captured > 80% IM cases during IBD-related admissions, with high discriminatory effectiveness. This allows for risk stratification and provides a basis for assessing interventions to reduce mortality in high-risk patients. |
| |
| Keywords: | artificial intelligence calculator hospitalized patients IBD machine learning prediction model |
|
|
