A Clustering Framework for Patient Phenotyping with Application to Adverse Drug Events
| Autor: | Panagiotis Papapetrou, Jaakko Hollmén, Maria Bampa |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
Structure (mathematical logic) Drug Safety surveillance Exploit Computer science business.industry media_common.quotation_subject Machine learning computer.software_genre Disease cluster 03 medical and health sciences 030104 developmental biology 0302 clinical medicine Unsupervised learning 030212 general & internal medicine Artificial intelligence Medical diagnosis Cluster analysis business computer media_common |
| Zdroj: | CBMS |
| DOI: | 10.1109/cbms49503.2020.00041 |
| Popis: | We present a clustering framework for identifying patient groups with Adverse Drug Reactions from Electronic Health Records (EHRs). The increased adoption of EHRs has brought changes in the way drug safety surveillance is carried out and plays an important role in effective drug regulation. Unsupervised machine learning methods using EHRs as their input can identify patients that share common meaningful information, without the need for expert input. In this work, we propose a generalized framework that exploits the strengths of different clustering algorithms and via clustering aggregation identifies consensus patient cluster profiles. Moreover, the inherent hierarchical structure of diagnoses and medication codes is exploited. We assess the statistical significance of the produced clusterings by applying a randomization technique that keeps the data distribution margins fixed, as we are interested in evaluating information that is not conveyed by the marginal distributions. The experimental findings suggest that the framework produces medically meaningful patient groups with regard to adverse drug events by investigating two use-cases, i.e., aplastic anaemia and drug-induced skin eruption. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|