Antithrombotic drugs are often prescribed for patients receiving cardiac care, but one of the associated risks is gastrointestinal bleeding (GIB).

According to a study recently published in JAMA Network Open, researchers have developed machine learning (ML) models to predict the risk of GIB within six to twelve months of a patient being prescribed.

For the study, the team tested three ML models, then compared their effectiveness to the effectiveness of the current standard risk model, HAS-BLED, which assesses risk for, among other things, hypertension, stroke, older age and drug or alcohol use.

Researchers studied more than 300,000 patients over the age of 18 who were prescribed thienopyridine antiplatelet and/or oral anticoagulant agents and had a history of ischemic heart disease, venous thromboembolism, or atrial fibrillation.

According to the study, the models were assessed using “the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value, and prediction density plots. Relative importance scores were used to identify the variables that were more influential in the top-performing machine learning model.”

Among other findings, the study noted that all of the models are more effective at pinpointing the patients who will not have any GIB, but not as effective for determining which patients will experience GIB. Given those results, the researchers concluded that all the models mentioned are best applied to patients with a low risk of GIB.

Specifically, the team reported, “the RegCox model performed the best in the validation set, with an AUC of 0.67 at 6 months and 0.66 at 12 months. XGBoost was similar, with AUCs of 0.67 at 6 months and 0.66 at 12 months, whereas for RSF, AUCs were 0.62 at 6 months and 0.60 at 12 months.”

In a separate article discussing the findings, Fei Wang, PhD, of Weil Cornell Medical College, noted that the study “demonstrated on a large real-world patient claims data set that ML models can perform better than clinically used risk predictor tools on GIB, which implies the great potential of ML on predicting rare clinical outcomes.

“This is a good start. Many other factors, including more comprehensive performance evaluation metrics, model interpretability, and data quantity need to be considered for assessing the potential clinical impact of these models. More importantly, efforts on prospective evaluations on clinical ML models with implementation science are critical and urgently needed.”

Photo by VM/Getty Images