Cargando…
Building interpretable models for polypharmacy prediction in older chronic patients based on drug prescription records
BACKGROUND: Multimorbidity presents an increasingly common problem in older population, and is tightly related to polypharmacy, i.e., concurrent use of multiple medications by one individual. Detecting polypharmacy from drug prescription records is not only related to multimorbidity, but can also po...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
PeerJ Inc.
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6187991/ https://www.ncbi.nlm.nih.gov/pubmed/30345175 http://dx.doi.org/10.7717/peerj.5765 |
_version_ | 1783363133233954816 |
---|---|
author | Kocbek, Simon Kocbek, Primoz Stozer, Andraz Zupanic, Tina Groza, Tudor Stiglic, Gregor |
author_facet | Kocbek, Simon Kocbek, Primoz Stozer, Andraz Zupanic, Tina Groza, Tudor Stiglic, Gregor |
author_sort | Kocbek, Simon |
collection | PubMed |
description | BACKGROUND: Multimorbidity presents an increasingly common problem in older population, and is tightly related to polypharmacy, i.e., concurrent use of multiple medications by one individual. Detecting polypharmacy from drug prescription records is not only related to multimorbidity, but can also point at incorrect use of medicines. In this work, we build models for predicting polypharmacy from drug prescription records for newly diagnosed chronic patients. We evaluate the models’ performance with a strong focus on interpretability of the results. METHODS: A centrally collected nationwide dataset of prescription records was used to perform electronic phenotyping of patients for the following two chronic conditions: type 2 diabetes mellitus (T2D) and cardiovascular disease (CVD). In addition, a hospital discharge dataset was linked to the prescription records. A regularized regression model was built for 11 different experimental scenarios on two datasets, and complexity of the model was controlled with a maximum number of dimensions (MND) parameter. Performance and interpretability of the model were evaluated with AUC, AUPRC, calibration plots, and interpretation by a medical doctor. RESULTS: For the CVD model, AUC and AUPRC values of 0.900 (95% [0.898–0.901]) and 0.640 (0.635–0.645) were reached, respectively, while for the T2D model the values were 0.808 (0.803–0.812) and 0.732 (0.725–0.739). Reducing complexity of the model by 65% and 48% for CVD and T2D, resulted in 3% and 4% lower AUC, and 4% and 5% lower AUPRC values, respectively. Calibration plots for our models showed that we can achieve moderate calibration with reducing the models’ complexity without significant loss of predictive performance. DISCUSSION: In this study, we found that it is possible to use drug prescription data to build a model for polypharmacy prediction in older population. In addition, the study showed that it is possible to find a balance between good performance and interpretability of the model, and achieve acceptable calibration at the same time. |
format | Online Article Text |
id | pubmed-6187991 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2018 |
publisher | PeerJ Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-61879912018-10-19 Building interpretable models for polypharmacy prediction in older chronic patients based on drug prescription records Kocbek, Simon Kocbek, Primoz Stozer, Andraz Zupanic, Tina Groza, Tudor Stiglic, Gregor PeerJ Drugs and Devices BACKGROUND: Multimorbidity presents an increasingly common problem in older population, and is tightly related to polypharmacy, i.e., concurrent use of multiple medications by one individual. Detecting polypharmacy from drug prescription records is not only related to multimorbidity, but can also point at incorrect use of medicines. In this work, we build models for predicting polypharmacy from drug prescription records for newly diagnosed chronic patients. We evaluate the models’ performance with a strong focus on interpretability of the results. METHODS: A centrally collected nationwide dataset of prescription records was used to perform electronic phenotyping of patients for the following two chronic conditions: type 2 diabetes mellitus (T2D) and cardiovascular disease (CVD). In addition, a hospital discharge dataset was linked to the prescription records. A regularized regression model was built for 11 different experimental scenarios on two datasets, and complexity of the model was controlled with a maximum number of dimensions (MND) parameter. Performance and interpretability of the model were evaluated with AUC, AUPRC, calibration plots, and interpretation by a medical doctor. RESULTS: For the CVD model, AUC and AUPRC values of 0.900 (95% [0.898–0.901]) and 0.640 (0.635–0.645) were reached, respectively, while for the T2D model the values were 0.808 (0.803–0.812) and 0.732 (0.725–0.739). Reducing complexity of the model by 65% and 48% for CVD and T2D, resulted in 3% and 4% lower AUC, and 4% and 5% lower AUPRC values, respectively. Calibration plots for our models showed that we can achieve moderate calibration with reducing the models’ complexity without significant loss of predictive performance. DISCUSSION: In this study, we found that it is possible to use drug prescription data to build a model for polypharmacy prediction in older population. In addition, the study showed that it is possible to find a balance between good performance and interpretability of the model, and achieve acceptable calibration at the same time. PeerJ Inc. 2018-10-12 /pmc/articles/PMC6187991/ /pubmed/30345175 http://dx.doi.org/10.7717/peerj.5765 Text en ©2018 Kocbek et al. http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited. |
spellingShingle | Drugs and Devices Kocbek, Simon Kocbek, Primoz Stozer, Andraz Zupanic, Tina Groza, Tudor Stiglic, Gregor Building interpretable models for polypharmacy prediction in older chronic patients based on drug prescription records |
title | Building interpretable models for polypharmacy prediction in older chronic patients based on drug prescription records |
title_full | Building interpretable models for polypharmacy prediction in older chronic patients based on drug prescription records |
title_fullStr | Building interpretable models for polypharmacy prediction in older chronic patients based on drug prescription records |
title_full_unstemmed | Building interpretable models for polypharmacy prediction in older chronic patients based on drug prescription records |
title_short | Building interpretable models for polypharmacy prediction in older chronic patients based on drug prescription records |
title_sort | building interpretable models for polypharmacy prediction in older chronic patients based on drug prescription records |
topic | Drugs and Devices |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6187991/ https://www.ncbi.nlm.nih.gov/pubmed/30345175 http://dx.doi.org/10.7717/peerj.5765 |
work_keys_str_mv | AT kocbeksimon buildinginterpretablemodelsforpolypharmacypredictioninolderchronicpatientsbasedondrugprescriptionrecords AT kocbekprimoz buildinginterpretablemodelsforpolypharmacypredictioninolderchronicpatientsbasedondrugprescriptionrecords AT stozerandraz buildinginterpretablemodelsforpolypharmacypredictioninolderchronicpatientsbasedondrugprescriptionrecords AT zupanictina buildinginterpretablemodelsforpolypharmacypredictioninolderchronicpatientsbasedondrugprescriptionrecords AT grozatudor buildinginterpretablemodelsforpolypharmacypredictioninolderchronicpatientsbasedondrugprescriptionrecords AT stiglicgregor buildinginterpretablemodelsforpolypharmacypredictioninolderchronicpatientsbasedondrugprescriptionrecords |