Classification of patients with chronic disease by activation level using machine learning methods.

Autor: Demiray O; Department of Computing, Imperial College London, London, SW7 2AZ, UK., Gunes ED; College of Administrative Sciences and Economics, Koç University, Rumeli Feneri Yolu, Sariyer-Istanbul, Turkey. egunes@ku.edu.tr., Kulak E; Ministry of Health Caycuma District Health Directorate, Zonguldak, Turkey., Dogan E; Ministry of Health, Zonguldak Community Health Center, Zonguldak, Turkey., Karaketir SG; Department of Public Health, Istanbul University, Istanbul, Turkey., Cifcili S; Department of Family Medicine, Marmara University School of Medicine, Istanbul, Turkey., Akman M; Department of Family Medicine, Marmara University School of Medicine, Istanbul, Turkey., Sakarya S; MPH, MHPE, School of Medicine, Department of Public Health, Koç University, Rumeli Feneri Yolu, Sariyer-Istanbul, Turkey.
Jazyk: angličtina
Zdroj: Health care management science [Health Care Manag Sci] 2023 Dec; Vol. 26 (4), pp. 626-650. Date of Electronic Publication: 2023 Oct 12.
DOI: 10.1007/s10729-023-09653-4
Abstrakt: Patient Activation Measure (PAM) measures the activation level of patients with chronic conditions and correlates well with patient adherence behavior, health outcomes, and healthcare costs. PAM is increasingly used in practice to identify patients needing more support from the care team. We define PAM levels 1 and 2 as low PAM and investigate the performance of eight machine learning methods (Logistic Regression, Lasso Regression, Ridge Regression, Random Forest, Gradient Boosted Trees, Support Vector Machines, Decision Trees, Neural Networks) to classify patients. Primary data collected from adult patients (n=431) with Diabetes Mellitus (DM) or Hypertension (HT) attending Family Health Centers in Istanbul, Turkey, is used to test the methods. [Formula: see text] of patients in the dataset have a low PAM level. Classification performance with several feature sets was analyzed to understand the relative importance of different types of information and provide insights. The most important features are found as whether the patient performs self-monitoring, smoking and exercise habits, education, and socio-economic status. The best performance was achieved with the Logistic Regression algorithm, with Area Under the Curve (AUC)=0.72 with the best performing feature set. Alternative feature sets with similar prediction performance are also presented. The prediction performance was inferior with an automated feature selection method, supporting the importance of using domain knowledge in machine learning.
(© 2023. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje