Network Analysis and Machine Learning for Signal Detection and Prioritization Using Electronic Healthcare Records and
Maria Antonietta Barbieri1,2, Andrea Abate1,2, Olivér M Balogh3,4
1Department of Clinical and Experimental Medicine, University of Messina, 98125, Messina, Italy.
Drug Safety
|February 7, 2025
Summary
Network analysis effectively detects drug-induced adverse events (AEs) in administrative health data. This method identified known and novel safety signals, prioritizing five key drugs for further investigation.
Area of Science:
- Pharmacovigilance
- Network Science
- Real-World Data Analysis
Background:
- Traditional safety signal detection relies on spontaneous reporting systems with known limitations.
- Real-world data from electronic health records (EHRs) and administrative databases are increasingly used for pharmacovigilance.
- Network analysis shows promise for mapping clinical attribute relationships but is underutilized in real-world data.
Purpose of the Study:
- To evaluate network analysis for detecting drug-induced adverse events (AEs) in Italian administrative healthcare databases.
- To use drug-induced acute myocardial infarction (AMI) as a proof of concept for this novel signal detection method.
Main Methods:
- A case-crossover design was used with the Healthcare Administrative Database of Mantova (2014-2018).
- A network was constructed to analyze relationships between drugs and diagnoses, with edge weights quantifying connection strength.
- A predictive score (F) identified outlier drug-AMI pairs, with prioritization using k-means clustering.
Main Results:
- Analysis of 3918 AMI patients revealed extensive drug-diagnosis and drug-drug connections within the network.
- Network analysis detected 249 potential safety signals, with 63.4% confirming known adverse events.
- Five high-priority safety signals were identified: terazosin, tamsulosin, allopurinol, esomeprazole, and omeprazole.
Conclusions:
- Network analysis is a valuable tool for detecting and prioritizing drug-induced adverse events (AEs) using real-world data from electronic health records and administrative databases.
- This novel method enhances pharmacovigilance by uncovering potential safety signals more effectively.
Related Concept Videos
01:30Pulse rhythm
754
Pulse rhythm refers to the pattern of pulsations within specific intervals, offering valuable insights into the regularity or irregularity of the heart's beats as observed through the pattern of pulsation within specific intervals. A regular pulse exhibits a consistent heart rate with uniform waveforms and pulsation force, variations of which can be classified as normal, weak, or bounding.
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
754
01:29Electrocardiogram
2.1K
An electrocardiogram (ECG or EKG) is a critical diagnostic tool that records the electrical signals produced by the heart during each heartbeat. This recording is achieved through electrodes placed strategically on the arms, legs, and chest. The electrocardiograph amplifies these signals and produces 12 distinct tracings, offering a comprehensive understanding of the heart's electrical activity.
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
2.1K