Building interpretable models for polypharmacy prediction in older chronic patients based on drug prescription records.

PeerJ 2018 12;6:e5765. Epub 2018 Oct 12.

Faculty of Health Sciences, University of Maribor, Maribor, Slovenia.

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.

Download full-text PDF

Source
http://dx.doi.org/10.7717/peerj.5765DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6187991PMC
October 2018
23 Reads

Publication Analysis

Top Keywords

prescription records
20
drug prescription
16
auprc values
8
calibration plots
8
older population
8
auc auprc
8
model
8
complexity model
8
performance interpretability
8
interpretability model
8
chronic patients
8
polypharmacy drug
8
polypharmacy prediction
8
prediction older
8
prescription
6
polypharmacy
5
records
5
achieve acceptable
4
number dimensions
4
model evaluated
4

References

(Supplied by CrossRef)
Electronic phenotyping with APHRODITE and the Observational Health Sciences and Informatics (OHDSI) data network
Banda et al.
Archive of AMIA Summits on Translational Science Proceedings 2017
Polypharmacy: correlations with sex, age and drug regimen
Bjerrum et al.
European Journal of Clinical Pharmacology 1998
Regularization paths for generalized linear models via coordinate descent
Friedman et al.
Journal of Statistical Software 2010
Polypharmacy in elderly patients
Hajjar et al.
The American Journal of Geriatric Pharmacotherapy 2007
What do we need to build explainable AI systems for the medical domain?
Holzinger et al.
2017
Factors leading to excessive polypharmacy
Hovstadius et al.
Clinics in Geriatric Medicine 2012

Similar Publications