Data mining to generate adverse drug events detection rules. Chazard, E., Ficheur, G., Bernonville, S., Luyckx, M., & Beuscart, R. IEEE transactions on information technology in biomedicine: a publication of the IEEE Engineering in Medicine and Biology Society, 15(6):823–830, November, 2011. Paper doi abstract bibtex 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.
@article{chazard_data_2011,
title = {Data mining to generate adverse drug events detection rules},
volume = {15},
copyright = {All rights reserved},
issn = {1558-0032},
url = {http://www.chazard.org/emmanuel/pdf_articles/paper_2011_ieeetitb_dataminingadedetectionrules.pdf},
doi = {10.1109/TITB.2011.2165727},
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.},
language = {eng},
number = {6},
journal = {IEEE transactions on information technology in biomedicine: a publication of the IEEE Engineering in Medicine and Biology Society},
author = {Chazard, Emmanuel and Ficheur, Grégoire and Bernonville, Stéphanie and Luyckx, Michel and Beuscart, Régis},
month = nov,
year = {2011},
pmid = {21859604},
keywords = {Adverse Drug Reaction Reporting Systems, Adverse drug events (ADEs), Data Mining, Decision Support Systems, Clinical, Decision Trees, Drug Toxicity, Electronic Health Records, Humans, Medical diagnostic imaging, Medical information systems, Medical services, Patient Safety, Patient monitoring, Pharmaceutical Preparations, Software, adverse drug events detection rules, automatically detect cases, data model, data models, demographics, drug administrations, drug discontinuations, drugs, free-text recording, median delay, medical computing, patient diagnosis, public health, relative risk, rule repository, statistical analysis, supervised rule methods},
pages = {823--830},
}
Downloads: 0
{"_id":"PmKpkTLwqBbEtcySt","bibbaseid":"chazard-ficheur-bernonville-luyckx-beuscart-dataminingtogenerateadversedrugeventsdetectionrules-2011","author_short":["Chazard, E.","Ficheur, G.","Bernonville, S.","Luyckx, M.","Beuscart, R."],"bibdata":{"bibtype":"article","type":"article","title":"Data mining to generate adverse drug events detection rules","volume":"15","copyright":"All rights reserved","issn":"1558-0032","url":"http://www.chazard.org/emmanuel/pdf_articles/paper_2011_ieeetitb_dataminingadedetectionrules.pdf","doi":"10.1109/TITB.2011.2165727","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.","language":"eng","number":"6","journal":"IEEE transactions on information technology in biomedicine: a publication of the IEEE Engineering in Medicine and Biology Society","author":[{"propositions":[],"lastnames":["Chazard"],"firstnames":["Emmanuel"],"suffixes":[]},{"propositions":[],"lastnames":["Ficheur"],"firstnames":["Grégoire"],"suffixes":[]},{"propositions":[],"lastnames":["Bernonville"],"firstnames":["Stéphanie"],"suffixes":[]},{"propositions":[],"lastnames":["Luyckx"],"firstnames":["Michel"],"suffixes":[]},{"propositions":[],"lastnames":["Beuscart"],"firstnames":["Régis"],"suffixes":[]}],"month":"November","year":"2011","pmid":"21859604","keywords":"Adverse Drug Reaction Reporting Systems, Adverse drug events (ADEs), Data Mining, Decision Support Systems, Clinical, Decision Trees, Drug Toxicity, Electronic Health Records, Humans, Medical diagnostic imaging, Medical information systems, Medical services, Patient Safety, Patient monitoring, Pharmaceutical Preparations, Software, adverse drug events detection rules, automatically detect cases, data model, data models, demographics, drug administrations, drug discontinuations, drugs, free-text recording, median delay, medical computing, patient diagnosis, public health, relative risk, rule repository, statistical analysis, supervised rule methods","pages":"823–830","bibtex":"@article{chazard_data_2011,\n\ttitle = {Data mining to generate adverse drug events detection rules},\n\tvolume = {15},\n\tcopyright = {All rights reserved},\n\tissn = {1558-0032},\n\turl = {http://www.chazard.org/emmanuel/pdf_articles/paper_2011_ieeetitb_dataminingadedetectionrules.pdf},\n\tdoi = {10.1109/TITB.2011.2165727},\n\tabstract = {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.},\n\tlanguage = {eng},\n\tnumber = {6},\n\tjournal = {IEEE transactions on information technology in biomedicine: a publication of the IEEE Engineering in Medicine and Biology Society},\n\tauthor = {Chazard, Emmanuel and Ficheur, Grégoire and Bernonville, Stéphanie and Luyckx, Michel and Beuscart, Régis},\n\tmonth = nov,\n\tyear = {2011},\n\tpmid = {21859604},\n\tkeywords = {Adverse Drug Reaction Reporting Systems, Adverse drug events (ADEs), Data Mining, Decision Support Systems, Clinical, Decision Trees, Drug Toxicity, Electronic Health Records, Humans, Medical diagnostic imaging, Medical information systems, Medical services, Patient Safety, Patient monitoring, Pharmaceutical Preparations, Software, adverse drug events detection rules, automatically detect cases, data model, data models, demographics, drug administrations, drug discontinuations, drugs, free-text recording, median delay, medical computing, patient diagnosis, public health, relative risk, rule repository, statistical analysis, supervised rule methods},\n\tpages = {823--830},\n}\n\n","author_short":["Chazard, E.","Ficheur, G.","Bernonville, S.","Luyckx, M.","Beuscart, R."],"key":"chazard_data_2011","id":"chazard_data_2011","bibbaseid":"chazard-ficheur-bernonville-luyckx-beuscart-dataminingtogenerateadversedrugeventsdetectionrules-2011","role":"author","urls":{"Paper":"http://www.chazard.org/emmanuel/pdf_articles/paper_2011_ieeetitb_dataminingadedetectionrules.pdf"},"keyword":["Adverse Drug Reaction Reporting Systems","Adverse drug events (ADEs)","Data Mining","Decision Support Systems","Clinical","Decision Trees","Drug Toxicity","Electronic Health Records","Humans","Medical diagnostic imaging","Medical information systems","Medical services","Patient Safety","Patient monitoring","Pharmaceutical Preparations","Software","adverse drug events detection rules","automatically detect cases","data model","data models","demographics","drug administrations","drug discontinuations","drugs","free-text recording","median delay","medical computing","patient diagnosis","public health","relative risk","rule repository","statistical analysis","supervised rule methods"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://api.zotero.org/users/1597782/collections/MSB7W4UM/items?key=gxIPM4PJtMVcB8OpssCWodtP&format=bibtex&limit=100&start=100&sort=date","dataSources":["Ad3P6FkzWSCKrZQXc","PSBFFbnPhFKwYx7yq"],"keywords":["adverse drug reaction reporting systems","adverse drug events (ades)","data mining","decision support systems","clinical","decision trees","drug toxicity","electronic health records","humans","medical diagnostic imaging","medical information systems","medical services","patient safety","patient monitoring","pharmaceutical preparations","software","adverse drug events detection rules","automatically detect cases","data model","data models","demographics","drug administrations","drug discontinuations","drugs","free-text recording","median delay","medical computing","patient diagnosis","public health","relative risk","rule repository","statistical analysis","supervised rule methods"],"search_terms":["data","mining","generate","adverse","drug","events","detection","rules","chazard","ficheur","bernonville","luyckx","beuscart"],"title":"Data mining to generate adverse drug events detection rules","year":2011}