Background Safety signals for potential drug-induced adverse events (AEs) typically emerge from multiple data sources,primarily spontaneous reporting systems, despite known limitations. Increasingly, real-world data from sources such aselectronic health records (EHRs) and administrative databases are leveraged for signal detection. Although network analysishas shown promise in mapping relationships between clinical attributes for signal detection in spontaneous reporting systemdatabases, its application in real-world data from EHRs and administrative databases remains limited.Objective This study aimed to evaluate the performance of network analysis in detecting safety signals within Italian administrative databases, using drug-induced acute myocardial infarction (AMI) as a proof of concept.Methods We employed a case–crossover design to explore the association between drug exposure and AMI using theHealthcare Administrative Database of Mantova, Italy, from 2014 to 2018. Patients with their frst AMI hospitalization wereidentifed after a 365-day washout period to exclude prior hospitalizations. We constructed a network to analyse the relationships between prescribed drugs and diagnoses, represented as nodes, with undirected edges illustrating their interactions.For each patient with AMI, we identifed all diagnoses and drugs recorded or redeemed within 365 days of the frst AMIepisode and generated various drug–diagnosis, drug–drug, and diagnosis–diagnosis pairs. We calculated the frequency ofthese pairs, and three types of edge weights quantifed the strength of connections. We identifed outlier drug–AMI pairs usinga predictive score (F) based on frequency (C) and full edge weights (WF), with validation for known AMI associations. Weprioritized signals using the F score, C of AMI, and WF, analysed through k-means clustering to identify patterns in the data.Results From 2014 to 2018, a total of 3918 patients had an AMI, with 4686 AMI diagnoses. Of those, 2866 had prescriptionsin the previous year, totalling 498,591 prescriptions. A network analysis identifed 2968 unique nodes, revealing 529,935diagnosis–diagnosis connections, 235,380 drug–diagnosis connections, and 102,831 drug–drug connections. The mediannumber of connections (C) was 404 (Q1–Q3: 194–671) for drug nodes and 380 (Q1–Q3: 216–664) for diagnosis nodes. Themedian WF was 11.8 (Q1–Q3: 9–14), and the median F score across pairs was 0.1 (Q1–Q3: 0.1–0.3). A total of 249 potentialsafety signals were detected, with 63.4% aligning with known AEs. Among the remaining signals, 80 were prioritized, andfve emerged as the highest priority: terazosin, tamsulosin, allopurinol, esomeprazole, and omeprazole.Conclusions Overall, our novel method demonstrates that network analysis is a valuable tool for signal detection and prioritization in drug-induced AEs based on EHRs and administrative databases.
Network Analysis and Machine Learning for Signal Detection and Prioritization Using Electronic Healthcare Records and Administrative Databases: A Proof of Concept in Drug-Induced Acute Myocardial Infarction
Maria Antonietta Barbieri;
2025-01-01
Abstract
Background Safety signals for potential drug-induced adverse events (AEs) typically emerge from multiple data sources,primarily spontaneous reporting systems, despite known limitations. Increasingly, real-world data from sources such aselectronic health records (EHRs) and administrative databases are leveraged for signal detection. Although network analysishas shown promise in mapping relationships between clinical attributes for signal detection in spontaneous reporting systemdatabases, its application in real-world data from EHRs and administrative databases remains limited.Objective This study aimed to evaluate the performance of network analysis in detecting safety signals within Italian administrative databases, using drug-induced acute myocardial infarction (AMI) as a proof of concept.Methods We employed a case–crossover design to explore the association between drug exposure and AMI using theHealthcare Administrative Database of Mantova, Italy, from 2014 to 2018. Patients with their frst AMI hospitalization wereidentifed after a 365-day washout period to exclude prior hospitalizations. We constructed a network to analyse the relationships between prescribed drugs and diagnoses, represented as nodes, with undirected edges illustrating their interactions.For each patient with AMI, we identifed all diagnoses and drugs recorded or redeemed within 365 days of the frst AMIepisode and generated various drug–diagnosis, drug–drug, and diagnosis–diagnosis pairs. We calculated the frequency ofthese pairs, and three types of edge weights quantifed the strength of connections. We identifed outlier drug–AMI pairs usinga predictive score (F) based on frequency (C) and full edge weights (WF), with validation for known AMI associations. Weprioritized signals using the F score, C of AMI, and WF, analysed through k-means clustering to identify patterns in the data.Results From 2014 to 2018, a total of 3918 patients had an AMI, with 4686 AMI diagnoses. Of those, 2866 had prescriptionsin the previous year, totalling 498,591 prescriptions. A network analysis identifed 2968 unique nodes, revealing 529,935diagnosis–diagnosis connections, 235,380 drug–diagnosis connections, and 102,831 drug–drug connections. The mediannumber of connections (C) was 404 (Q1–Q3: 194–671) for drug nodes and 380 (Q1–Q3: 216–664) for diagnosis nodes. Themedian WF was 11.8 (Q1–Q3: 9–14), and the median F score across pairs was 0.1 (Q1–Q3: 0.1–0.3). A total of 249 potentialsafety signals were detected, with 63.4% aligning with known AEs. Among the remaining signals, 80 were prioritized, andfve emerged as the highest priority: terazosin, tamsulosin, allopurinol, esomeprazole, and omeprazole.Conclusions Overall, our novel method demonstrates that network analysis is a valuable tool for signal detection and prioritization in drug-induced AEs based on EHRs and administrative databases.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
