Posted in | News | Medical Robotics

Machine Learning Predicts Premature Death in IBD

A study published in the Canadian Medical Association Journal (CMAJ) found that nearly half of individuals who died from inflammatory bowel disease (IBD) did so prematurely. The study used machine learning models to predict mortality.

Image depicting man with stomach ache.Image Credit: JARIRIYAWAT/Shutterstock.com

IBD, which includes ulcerative colitis and Crohn's disease, is prevalent in Canada, with rates among the highest in the world. People with IBD generally have a lower life expectancy compared to those without the disease and may develop additional chronic conditions linked to IBD. The study found that individuals with IBD who develop other chronic health conditions at an earlier stage in life are at higher risk of premature death (before age 75).

Researchers used healthcare data from ICES to test if machine learning technology could predict premature deaths among individuals with IBD and other chronic diseases in Ontario. They employed machine learning models that have been used to predict premature death in the broader population.

The clinical implication is that chronic conditions developed early in life may be more important in determining a patient’s health trajectory, although further causal research is needed to elucidate this relationship. Although our insights are not causal, they identify patients potentially at higher risk of premature death and, therefore, who might benefit from more coordinated care of their IBD and other chronic conditions.

Dr. Eric Benchimol, Pediatric Gastroenterologist and Senior Scientist, The Hospital for Sick Children (SickKids)

Benchimol is a Professor of Pediatrics and Epidemiology at the Temerty Faculty of Medicine, University of Toronto, and a Senior Core Scientist at ICES.

Between 2010 and 2020, nearly half (47%) of the 9,278 deaths among IBD patients were preventable, with males experiencing higher rates than females (50 % vs. 44 %). The most common chronic illnesses at the time of death included arthritis (77 %), hypertension (73 %), mental disorders (69 %), kidney failure (50 %), and cancer (46 %). The researchers found that the machine learning models' predictive accuracy improved when incorporating the age of diagnosis and chronic illnesses detected before age 60.

The use of premature death as the outcome more directly identifies opportunities for health system improvements, as premature deaths are considered avoidable through appropriate prevention or early and effective treatment,” wrote the authors.

Dr. Laura Rosella, a Professor and Canada Research Chair in Population Health Analytics at the Dalla Lana School of Public Health, and Gemma Postill, a Medical Student at the Temerty Faculty of Medicine, co-led the study.

The authors stated that the goal of the study is to identify regions that require more targeted follow-up from various medical specialists, including nutritionists, mental health professionals, and other specialists, as needed.

These findings provide scientific support for providing multidisciplinary and integrated health care across the lifespan (particularly during young and middle adulthood),” concluded the authors.

Journal Reference:

Postill, G., et al. (2025) Machine learning prediction of premature death from multimorbidity among people with inflammatory bowel disease: a population-based retrospective cohort study. Canadian Medical Association Journal. doi.org/10.1503/cmaj.241117

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.