Why the study?
Bleeding complications are a major contributor to adverse drug events in older inpatients receiving antithrombotic agents, making timely and accurate detection essential for drug safety surveillance and clinical risk management.
Does an integrated approach combining structured data algorithms and natural language processing improve the detection of hemorrhagic events in older hospitalized patients treated with antithrombotic agents?
Population
36,039 inpatient stays of patients 65 years or older receiving antithrombotic agents across 3 Swiss university hospitals
Comparison
Structured data algorithms, NLP, and their combination vs a manually reviewed gold standard
Design
Multicenter retrospective validation study
Loading...
May enhance bleeding surveillance in antithrombotic-treated inpatients; leaves open prospective validation before EMR integration.
Does an integrated approach combining structured data algorithms and natural language processing improve the detection of hemorrhagic events in older hospitalized patients treated with antithrombotic agents?
Combining structured data algorithms with natural language processing enhances the automated detection of antithrombotic-related bleeding events in older hospitalized patients, which can improve drug safety surveillance.
A 2025 study studied this question.