Physicians have long used prediction models to stratify patients according to their risk of adverse outcomes. Such risk stratification can promote better treatment decisions, more efficient use of monitoring, and better implementation of approaches to mitigate risk.
1 One outcome for which risk stratification is routinely used is related to the decision to prescribe antithrombotic medications (vitamin K antagonists, direct oral anticoagulants [DOACs], and/or thienopyridine antiplatelet agents) to patients with cardiovascular diseases. One of the key goals of this risk stratification is to incorporate the risk of gastrointestinal bleeding (GIB) in the context of the treatment decision. Given the severity of GIB
2,3 and the widespread use of antithrombotic agents in this population, several risk models have been developed to predict bleeding, including HAS-BLED (hypertension, abnormal kidney and liver function, stroke, bleeding, labile international normalized ratio, older age, and drug or alcohol use), ATRIA (anticoagulation and risk factors in atrial fibrillation), ORBIT (Outcomes Registry for Better Informed Treatment of Atrial Fibrillation), and HEMORR(2)HAGES (hepatic or kidney disease, ethanol abuse, malignancy, older age, reduced platelet count or function, rebleeding, hypertension, anemia, genetic factors, excessive fall risk, and stroke).
4-7