Adherence can be defined as "the extent to which patients take their medications as prescribed by their healthcare providers"[Osterberg and Blaschke, 2005]. World Health Organization's reports point out that, in developed countries, only about 50% of patients with chronic diseases correctly follow their treatments. This severely compromises the efficiency of long-term therapy and increases the cost of health services. We propose in this paper different models of patient drug consumption in breast cancer treatments. The aim of these different approaches is to predict medication non-adherence while giving insights to doctors of the underlying reasons of these illegitimate drop-outs. Working with oncologists, we show the interest of Machine- Learning algorithms fined tune by the feedback of experts to estimate a risk score of a patient's non-adherence and thus improve support throughout their care path.
@article{arxiv.1811.12234,
title = {Machine Learning on Electronic Health Records: Models and Features Usages to predict Medication Non-Adherence},
author = {Thomas Janssoone and Clémence Bic and Dorra Kanoun and Pierre Hornus and Pierre Rinder},
journal= {arXiv preprint arXiv:1811.12234},
year = {2018}
}
Comments
Machine Learning for Health (ML4H) Workshop at NeurIPS 2018