Graph representation and learning for drug administration prediction
TL;DR
This work proposes a graph representation learning model for predicting drug administration using the MIMIC-III database, which contains over 53K critical care admissions, and designs a heterogeneous, weighted, directed, and multi-feature graph from patient demographics, diagnoses, and drug administration records.
Abstract
The management of drug administration to patients promotes the customisation and accuracy of the treatments, reducing the risk of ineffective therapies and negative drug effects, and improving drug efficiency and management. We propose a graph representation learning model for predicting drug administration using the MIMIC-III database, which contains over 53K critical care admissions. We design a heterogeneous, weighted, directed, and multi-feature graph from patient demographics, diagnoses, and drug administration records. Our method uses a graph convolutional network to process node and edge features, predicting edge connections between patients and drugs. This choice enables us to analyse database properties, such as the relationship between drug administration and demographic classes, as well as the prediction accuracy with respect to drug occurrence. We analyse the results in terms of correct, false positive, and false negative edge predictions of drug-patient administration. Our method has an accuracy of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\boldsymbol{84.4\%}$$\end{document} on the MIMIC-III database, with an F1-score of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\boldsymbol{0.84}$$\end{document}. We discuss the training results regarding convergence and execution time, analyse the accuracy on low-occurrence drugs, and compare our method with previous work. Previous work has focused primarily on query and classification tasks for feature extraction and diagnosis prediction, achieving comparable accuracy but is often limited to specific pathologies (e.g., diabetes), patient groups (e.g., pregnant women), or drug types (e.g., antibiotics). Our approach processes heterogeneous data encompassing various patient characteristics, pathologies, and drug types, providing a more comprehensive and scalable solution.