AI can predict which inflammatory bowel disease patients are at risk of dying prematurely

Publicly released:
International
CC-0. https://pixabay.com/illustrations/ai-generated-robot-hand-machine-8331364/
CC-0. https://pixabay.com/illustrations/ai-generated-robot-hand-machine-8331364/

Canadian scientists say they've used artificial intelligence (AI) to predict which inflammatory bowel disease (IBD) patients are at risk of dying prematurely, defined as dying before age 75, with a high degree of accuracy. They trained the AI using data on people with IBD who died between 2010 and 2020 in Ontario, Canada, and found that 17 different chronic conditions and the age at which IBD develops are important factors in determining whether a patient is at risk of dying prematurely. When they fed in data about the age at which patients developed chronic conditions, the accuracy of the AI was even higher, they found. They say the most important factors when predicting premature deaths among IBD patients were being diagnosed with a mental illness, arthritis, or high blood pressure at a younger age. Men were also more likely to die prematurely than women, they say.

Media release

From: Canadian Medical Association

AI can predict premature deaths in people with inflammatory bowel disease

Almost half of people who died with inflammatory bowel disease (IBD) died prematurely, according to a study published in CMAJ (Canadian Medical Association Journal) that used machine learning models to predict death.

Canada has some of the highest rates of IBD worldwide, which includes Crohn disease and ulcerative colitis. People with IBD have shorter life expectancy than people without such diseases, and they can develop other chronic health conditions related to their IBD. The study found that people with IBD are at risk for premature death (defined as death before age 75) when they develop other chronic health conditions earlier in life.

As machine learning models can predict premature death in the general population, researchers applied the technology to determine whether it could predict premature deaths among people in Ontario with IBD and other chronic conditions using health care data held at ICES.  
“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,” writes Dr. Eric Benchimol, a pediatric gastroenterologist and senior scientist at The Hospital for Sick Children (SickKids), professor of pediatrics and epidemiology at the Temerty Faculty of Medicine, University of Toronto, and a senior core scientist at ICES. “Although our insights are not causal insights, 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,” he says.

Of the total 9278 deaths in people with IBD between 2010 and 2020, almost half (47%) were premature, with higher rates in males than in females (50% v. 44%). The most common chronic conditions at death were various types of arthritis (77%), hypertension (73%), mood disorders (69%), kidney failure (50%) and cancer (46%). The researchers found that including chronic conditions diagnosed before age 60 and the age of diagnosis improved the models’ predictions.

“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,” write the authors.

The study was co-led by medical student Gemma Postill of the Temerty Faculty of Medicine, and Dr. Laura Rosella, professor and Canada Research Chair in Population Health Analytics at the Dalla Lana School of Public Health.

The authors hope that their research will help pinpoint areas for more targeted follow up from a range of health care professionals, from dietitians to mental health professionals and specialists when required.

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

Attachments

Note: Not all attachments are visible to the general public. Research URLs will go live after the embargo ends.

Research Canadian Medical Association, Web page The URL will go live after the embargo ends
Journal/
conference:
CMAJ
Research:Paper
Organisation/s: SickKids Research Institute, Canada, Institute of Clinical Evaluative Sciences (ICES), Canada
Funder: This study received funding from the Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM) 2022 summer studentship and the 2023 American College of Gastroenterology Medical Student Research Award (both received by Gemma Postill). Laura Rosella is funded by a Canada Research Chair in Population Health Analytics (72051628) and Stephen Family Chair in Community Health from Trillium Health Partners. Eric Benchimol holds the Northbridge Financial Corporation Chair in Inflammatory Bowel Disease, a joint Hospital– University Chair between the University of Toronto, The Hospital for Sick Children, and the SickKids Foundation.
Media Contact/s
Contact details are only visible to registered journalists.