Design and validation of an automated method to detect known adverse drug reactions in MEDLINE: a contribution from the EU-ADR project

被引:49
作者
Avillach, Paul [1 ,2 ,3 ]
Dufour, Jean-Charles [3 ]
Diallo, Gayo [1 ]
Salvo, Francesco [4 ,5 ]
Joubert, Michel [3 ]
Thiessard, Frantz [1 ,2 ]
Mougin, Fleur [1 ]
Trifiro, Gianluca [6 ]
Fourrier-Reglat, Annie [2 ,4 ,5 ]
Pariente, Antoine [2 ,4 ,5 ]
Fieschi, Marius [3 ]
机构
[1] Univ Bordeaux, LESIM, ISPED, Bordeaux, France
[2] CHU Bordeaux, Pole Sante Publ, Bordeaux, France
[3] Univ Aix Marseille, LERTIM, EA 3283, Fac Med, Marseille, France
[4] Univ Bordeaux, Dept Pharmacol, Bordeaux, France
[5] Univ Bordeaux Segalen, INSERM, U657, Bordeaux, France
[6] Erasmus Univ, Dept Med Informat, Med Ctr, NL-3000 DR Rotterdam, Netherlands
关键词
KNOWLEDGE EXTRACTION; DOCUMENTATION; EVENTS;
D O I
10.1136/amiajnl-2012-001083
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Objectives The aim of this research was to automate the search of publications concerning adverse drug reactions (ADR) by defining the queries used to search MEDLINE and by determining the required threshold for the number of extracted publications to confirm the drug/event association in the literature. Methods We defined an approach based on the medical subject headings (MeSH) 'descriptor records' and 'supplementary concept records' thesaurus, using the subheadings 'chemically induced' and 'adverse effects' with the 'pharmacological action' knowledge. An expert-built validation set of true positive and true negative drug/adverse event associations (n=61) was used to validate our method. Results Using a threshold of three of more extracted publications, the automated search method presented a sensitivity of 90% and a specificity of 100%. For nine different drug/event pairs selected, the recall of the automated search ranged from 24% to 64% and the precision from 93% to 48%. Conclusions This work presents a method to find previously established relationships between drugs and adverse events in the literature. Using MEDLINE, following a MeSH approach to filter the signals, is a valid option. Our contribution is available as a web service that will be integrated in the final European EU-ADR project (Exploring and Understanding Adverse Drug Reactions by integrative mining of clinical records and biomedical knowledge) automated system.
引用
收藏
页码:446 / 452
页数:7
相关论文
共 22 条
[1]   A Knowledge Management Platform for Documentation of Case Reports in Pharmacovigilance [J].
Amardeilh, Florence ;
Bousquet, Cedric ;
Guillemin-Lanne, Sylvie ;
Wiss-Thebault, Mathilde ;
Guillot, Laetitia ;
Delamarre, Denis ;
Lillo-Le Louet, Agnes ;
Burgun, Anita .
MEDICAL INFORMATICS IN A UNITED AND HEALTHY EUROPE, 2009, 150 :517-521
[2]   Harmonization process for the identification of medical events in eight European healthcare databases: the experience from the EU-ADR project [J].
Avillach, Paul ;
Coloma, Preciosa M. ;
Gini, Rosa ;
Schuemie, Martijn ;
Mougin, Fleur ;
Dufour, Jean-Charles ;
Mazzaglia, Giampiero ;
Giaquinto, Carlo ;
Fornari, Carla ;
Herings, Ron ;
Molokhia, Mariam ;
Pedersen, Lars ;
Fourrier-Reglat, Annie ;
Fieschi, Marius ;
Sturkenboom, Miriam ;
van der Lei, Johan ;
Pariente, Antoine ;
Trifiro, Gianluca .
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2013, 20 (01) :184-192
[3]   Design and evaluation of a semantic approach for the homogeneous identification of events in eight patient databases: a contribution to the European EU-ADR project [J].
Avillach, Paul ;
Joubert, Michel ;
Thiessard, Frantz ;
Trifiro, Gianluca ;
Dufour, Jean-Charles ;
Pariente, Antoine ;
Mougin, Fleur ;
Polimeni, Giovanni ;
Catania, Maria Antonietta ;
Giaquinto, Carlo ;
Mazzaglia, Giampiero ;
Fornari, Carla ;
Herings, Ron ;
Gini, Rosa ;
Hippisley-Cox, Julia ;
Molokhia, Mariam ;
Pedersen, Lars ;
Fourrier-Reglat, Annie ;
Sturkenboom, Miriam ;
Fieschi, Marius .
MEDINFO 2010, PTS I AND II, 2010, 160 :1085-1089
[4]   Detecting adverse events using information technology [J].
Bates, DW ;
Evans, RS ;
Murff, H ;
Stetson, PD ;
Pizziferri, L ;
Hripcsak, G .
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2003, 10 (02) :115-128
[5]   From SNPs to pathways: integration of functional effect of sequence variations on models of cell signalling pathways [J].
Bauer-Mehren, Anna ;
Furlong, Laura I. ;
Rautschka, Michael ;
Sanz, Ferran .
BMC BIOINFORMATICS, 2009, 10
[6]   Rates of spontaneous reporting of adverse drug reactions in France [J].
Bégaud, B ;
Martin, K ;
Haramburu, F ;
Moore, N .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2002, 288 (13) :1588-1588
[7]   The Unified Medical Language System (UMLS): integrating biomedical terminology [J].
Bodenreider, O .
NUCLEIC ACIDS RESEARCH, 2004, 32 :D267-D270
[8]   Combining electronic healthcare databases in Europe to allow for large-scale drug safety monitoring: the EU-ADR Project [J].
Coloma, Preciosa M. ;
Schuemie, Martijn J. ;
Trifiro, Gianluca ;
Gini, Rosa ;
Herings, Ron ;
Hippisley-Cox, Julia ;
Mazzaglia, Giampiero ;
Giaquinto, Carlo ;
Corrao, Giovanni ;
Pedersen, Lars ;
van der Lei, Johan ;
Sturkenboom, Miriam .
PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2011, 20 (01) :1-11
[9]   Documentation in Pharmacovigilance: Using an ontology to extend and normalize Pubmed queries [J].
Delamarre, Denis ;
Lillo-Le Louet, Agnes ;
Guillot, Laetitia ;
Jamet, Anne ;
Sadou, Eric ;
Ouazine, Theo ;
Burgun, Anita ;
Jaulent, Marie-Christine .
MEDINFO 2010, PTS I AND II, 2010, 160 :518-522
[10]  
Duda Stephany, 2005, AMIA Annu Symp Proc, P216