Exploratory pharmacovigilance with machine learning in big patient data: A focused scoping review

被引:5
作者
Kaas-Hansen, Benjamin Skov [1 ,2 ,6 ]
Gentile, Simona [3 ]
Caioli, Alessandro [4 ]
Andersen, Stig Ejdrup [5 ]
机构
[1] Copenhagen Univ Hosp, Dept Intens Care, Rigshosp, Copenhagen, Denmark
[2] Univ Copenhagen, Dept Publ Hlth, Sect Biostat, Copenhagen, Denmark
[3] Zealand Univ Hosp, Dept Radiol, Roskilde, Denmark
[4] Natl Inst Infect Dis Lazzaro Spallanzani, Dept Infect Dis Hepatol, Rome, Italy
[5] Zealand Univ Hosp Roskilde, Clin Pharmacol Unit, Roskilde, Denmark
[6] Blegdamsvej 9, DK-2100 Copenhagen, Denmark
关键词
administrative pharmacology; adverse drug reactions; machine learning; pharmacoepidemiology; postmarketing surveillance; HEALTH-CARE; INFORMATION; DESIGN; INFERENCE; REGISTRY; PRIVACY;
D O I
10.1111/bcpt.13828
中图分类号
R9 [药学];
学科分类号
1007 ;
摘要
BackgroundMachine learning can operationalize the rich and complex data in electronic patient records for exploratory pharmacovigilance endeavours. ObjectiveThe objective of this review is to identify applications of machine learning and big patient data in exploratory pharmacovigilance. MethodsWe searched PubMed and Embase and included original articles with an exploratory pharmacovigilance purpose, focusing on medicinal interventions and reporting the use of machine learning in electronic patient records with >= 1000 patients collected after market entry. FindingsOf 2557 studies screened, seven were included. Those covered six countries and were published between 2015 and 2021. The most prominent machine learning methods were random forests, logistic regressions, and support vector machines. Two studies used artificial neural networks or naive Bayes classifiers. One study used formal concept analysis for association mining, and another used temporal difference learning. Five studies compared several methods against each other. The numbers of patients in most data sets were in the order of thousands; two studies used what can more reasonably be considered big data with >1 000 000 patients records. ConclusionDespite years of great aspirations for combining machine learning and clinical data for exploratory pharmacovigilance, only few studies still seem to deliver somewhat on these expectations.
引用
收藏
页码:233 / 241
页数:9
相关论文
共 49 条
  • [21] Blueprint for harmonising unstandardised disease registries to allow federated data analysis: prepare for the future
    Kroes, Johannes A.
    Bansal, Aruna T.
    Berret, Emmanuelle
    Christian, Nils
    Kremer, Andreas
    Alloni, Anna
    Gabetta, Matteo
    Marshall, Chris
    Wagers, Scott
    Djukanovic, Ratko
    Porsbjerg, Celeste
    Hamerlijnck, Dominique
    Fulton, Olivia
    Ten Brinke, Anneke
    Bel, Elisabeth H.
    Sont, Jacob K.
    [J]. ERJ OPEN RESEARCH, 2022, 8 (04)
  • [22] Drug safety data mining with a tree-based scan statistic
    Kulldorff, Martin
    Dashevsky, Inna
    Avery, Taliser R.
    Chan, Arnold K.
    Davis, Robert L.
    Graham, David
    Platt, Richard
    Andrade, Susan E.
    Boudreau, Denise
    Gunter, Margaret J.
    Herrinton, Lisa J.
    Pawloski, Pamala A.
    Raebel, Marsha A.
    Roblin, Douglas
    Brown, Jeffrey S.
    [J]. PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2013, 22 (05) : 517 - 523
  • [23] Kum Hye-Chung, 2013, AMIA Jt Summits Transl Sci Proc, V2013, P126
  • [24] A MiniReview of the Use of Hospital-based Databases in Observational Inpatient Studies of Drugs
    Larsen, Michael D.
    Cars, Thomas
    Hallas, Jesper
    [J]. BASIC & CLINICAL PHARMACOLOGY & TOXICOLOGY, 2013, 112 (01) : 13 - 18
  • [25] Nordic Health Registry-Based Research: A Review of Health Care Systems and Key Registries
    Laugesen, Kristina
    Ludvigsson, Jonas F.
    Schmidt, Morten
    Gissler, Mika
    Valdimarsdottir, Unnur Anna
    Lunde, Astrid
    Sorensen, Henrik Toft
    [J]. CLINICAL EPIDEMIOLOGY, 2021, 13 : 533 - 554
  • [26] A New Era in Pharmacovigilance: Toward Real-World Data and Digital Monitoring
    Lavertu, Adam
    Vora, Bianca
    Giacomini, Kathleen M.
    Altman, Russ
    Rensi, Stefano
    [J]. CLINICAL PHARMACOLOGY & THERAPEUTICS, 2021, 109 (05) : 1197 - 1202
  • [27] Deep learning in radiology: An overview of the concepts and a survey of the state of the art with focus on MRI
    Mazurowski, Maciej A.
    Buda, Mateusz
    Saha, Ashirbani
    Bashir, Mustafa R.
    [J]. JOURNAL OF MAGNETIC RESONANCE IMAGING, 2019, 49 (04) : 939 - 954
  • [28] McMaster C, 2019, DRUG SAFETY, V42, P721, DOI 10.1007/s40264-018-00794-y
  • [29] Concurrence of big data analytics and healthcare: A systematic review
    Mehta, Nishita
    Pandit, Anil
    [J]. INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, 2018, 114 : 57 - 65
  • [30] The Seven Tools of Causal Inference, with Reflections on Machine Learning
    Pearl, Judea
    [J]. COMMUNICATIONS OF THE ACM, 2019, 62 (03) : 54 - 60