A Novel Strategy to Classify Chronic Patients at Risk: A Hybrid Machine Learning Approach

Abstract

Various care processes have been affected by COVID-19. One of the most dramatic has been the care of chronic patients under medical supervision. According to the World Health Organization (WHO), a chronic patient has one or more long-term illnesses, and must be permanently monitored by the health team.. In fact, and according to the Chilean Ministry of Health (MINSAL), 7 out of 10 chronic patients have suspended their medical check-ups, generating critical situations, such as a more significant number of visits to emergency units, expired prescriptions, and a higher incidence in hospitalization rates. For this problem, health services in Chile have had to reschedule their scarce medical resources to provide care in all health processes. One element that has been considered is caring through telemedicine and patient prioritization. In the latter case, the aim was to provide timely care to those critical patients with high severity and who require immediate clinical attention. For this reason, in this work, we present the following methodological contributions: first, an unsupervised algorithm that analyzes information from anonymous patients to classify them according to priority levels; and second, rules that allow health teams to understand which variable(s) determine the classification of patients. The results of the proposed methodology allow classifying new patients with 99.96% certainty using a three-level decision tree and five classification rules.

Ensemble Approach Using k-Partitioned Isolation Forests for the Detection of Stock Market Manipulation

“…We evaluated the performance in terms of recall, precision, F1 Score (F1), and F2 Score (F2), which are commonly used metrics in this type of problem [28][29][30][31].…”

A Hybrid Algorithm of ML and XAI to Prevent Breast Cancer: A Strategy to Support Decision Making

“…The structure of the patient classification strategy is based on the Intersectoral Standard Process for the development of Machine Learning applications with the quality assurance methodology (CRISP-ML(Q)), a method widely used in the health sector and which has been mentioned in different works, such as Silva-Aravena et al [17], Kolyshkina and Simoff [81], Silva-Aravena and Morales [82], Silva-Aravena et al [83]. Additionally, we have incorporated an explainability algorithm, XAI, into this strategy to provide betterquality information that favors clinical decision making.…”

“…ML has been applied in different areas, and its applications are very wide. They include, e.g., the prediction of the length of stay of cardiac patients in hospitals (Hachesu et al [15]), classification of disease, cited by Saranya and Pravin [16] where the authors propose a sensitivity analysis for ML-based heart disease classification or instance, classifying chronic patients in risk for medical care using a lot of ML tools (Silva-Aravena et al [17]), among many others in the health field.…”