Data Mining to Generate Adverse Drug Events Detection Rules

Abstract

Adverse drug events (ADEs) are a public health issue. Their detection usually relies on voluntary reporting or medical chart reviews. The objective of this paper is to automatically detect cases of ADEs by data mining. 115,447 complete past hospital stays are extracted from six French, Danish, and Bulgarian hospitals using a common data model including diagnoses, drug administrations, laboratory results, and free-text records. Different kinds of outcomes are traced, and supervised rule induction methods (decision trees and association rules) are used to discover ADE detection rules, with respect to time constraints. The rules are then filtered, validated, and reorganized by a committee of experts. The rules are described in a rule repository, and several statistics are automatically computed in every medical department, such as the confidence, relative risk, and median delay of outcome appearance. 236 validated ADE-detection rules are discovered; they enable to detect 27 different kinds of outcomes. The rules use a various number of conditions related to laboratory results, diseases, drug administration, and demographics. Some rules involve innovative conditions, such as drug discontinuations.

Detecting adverse drug events with multiple representations of clinical measurements

“…As pointed out earlier, the complex nature of EHR data needs to be handled in order to be able to use it for ADE detection. Both [17] and [15] have acknowledged such difficulties when including clinical measurements in their predictor set: the former tackled it by leaving the data intact and instead improving the learning algorithm, while the latter adopted a different approach by altering the representation of the data.…”

“…Faced with the problem of repeated measurements in EHRs, Chazard et al represented these in a simpler form by aggregating them into a single, new measurement [15]. For instance, several measurements of potassium 1 , a continuous variable, were aggregated into a binary measurement: hyperkalemia (1 = too high potassium value; 0 = otherwise).…”

Clinical Data Reuse or Secondary Use: Current Status and Potential Future Progress

“…In decision tree classification, a decision tree is used to predict the value of a target variable (or item) based on the observations of several input variables. Classification And Regression Tree (CART) analysis, a particular type of decision tree, has been applied to detect ADRs [171,172]. The k-Nearest Neighbors (k-NN) algorithm, another classification method, assigns an object to the most common class among its k nearest neighbors.…”

Evaluation of Classifiers Based on Decision Tree for Learning Medical Claim Process

“…Chazard et al 2011 [7] seguem as etapas do processo de DCBD para analisar dados de prontuários médicos. Na etapa de classificação são usadas técnicas de Regras de Indução e Árvore de Decisão para tentar descobrir automaticamente casos de efeitos colaterais de medicamentos.…”