Estimating disease prevalence from drug utilization data using the Random Forest algorithm.
Background Aggregated claims data on medication are often used as a proxy for the prevalence of diseases, especially chronic diseases. However, linkage between medication and diagnosis tend to be theory based and not very precise. Modelling disease probability at an individual level using individual...
| Publicado en: | European Journal of Public Health Vol. 29; no. 4; pp. 615 - 622 |
|---|---|
| Autores principales: | , , , , , , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
Oxford University Press / USA
Aug2019
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=137826605&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 137826605 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 11011262 BHW jtl: European Journal of Public Health issn: 11011262 maglogo: N pubinfo: dt: Aug2019 vid: 29 iid: 4 pid: 622 pub: Oxford University Press / USA artinfo: ui: 137826605 137826605 137826605 10.1093/eurpub/cky270 137826605 ppf: 615 ppct: 7 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Estimating disease prevalence from drug utilization data using the Random Forest algorithm. aug: au: Slobbe, Laurentius C J Füssenich, Koen Wong, Albert Boshuizen, Hendriek C Nielen, Markus M J Polder, Johan J Feenstra, Talitha L Oers, Hans A M van affil: National Institute for Public Health and the Environment (RIVM), Bilthoven, The Netherlands sug: subj: Chronic Disease Epidemiology Drug Utilization Algorithms Human Prevalence Physicians, Family Databases, Health Chronic Disease Diagnosis Chronic Disease Drug Therapy ROC Curve Parkinson Disease Diagnosis Confidence Intervals Osteoporosis Diagnosis Heart Failure Diagnosis Asthma Diagnosis Enteritis Diagnosis Pulmonary Disease, Chronic Obstructive Diagnosis Epilepsy Diagnosis HIV Infections Diagnosis ab: Background Aggregated claims data on medication are often used as a proxy for the prevalence of diseases, especially chronic diseases. However, linkage between medication and diagnosis tend to be theory based and not very precise. Modelling disease probability at an individual level using individual level data may yield more accurate results. Methods Individual probabilities of having a certain chronic disease were estimated using the Random Forest (RF) algorithm. A training set was created from a general practitioners database of 276 723 cases that included diagnosis and claims data on medication. Model performance for 29 chronic diseases was evaluated using Receiver-Operator Curves, by measuring the Area Under the Curve (AUC). Results The diseases for which model performance was best were Parkinson's disease (AUC =.89, 95% CI =.77–1.00), diabetes (AUC =.87, 95% CI =.85–.90), osteoporosis (AUC =.87, 95% CI =.81–.92) and heart failure (AUC =.81, 95% CI =.74–.88). Five other diseases had an AUC >.75: asthma, chronic enteritis, COPD, epilepsy and HIV/AIDS. For 16 of 17 diseases tested, the medication categories used in theory-based algorithms were also identified by our method, however the RF models included a broader range of medications as important predictors. Conclusion Data on medication use can be a useful predictor when estimating the prevalence of several chronic diseases. To improve the estimates, for a broader range of chronic diseases, research should use better training data, include more details concerning dosages and duration of prescriptions, and add related predictors like hospitalizations. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|