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

Onur Demiray (), Evrim D. Gunes (), Ercan Kulak, Emrah Dogan, Seyma Gorcin Karaketir, Serap Cifcili (), Mehmet Akman () and Sibel Sakarya ()
Additional contact information
Onur Demiray: Imperial College London
Evrim D. Gunes: Koç University, Rumeli Feneri Yolu
Ercan Kulak: Ministry of Health Caycuma District Health Directorate
Emrah Dogan: Ministry of Health, Zonguldak Community Health Center
Seyma Gorcin Karaketir: Department of Public Health, Istanbul University
Serap Cifcili: Department of Family Medicine, Marmara University School of Medicine
Mehmet Akman: Department of Family Medicine, Marmara University School of Medicine
Sibel Sakarya: Koç University, Rumeli Feneri Yolu

Health Care Management Science, 2023, vol. 26, issue 4, No 3, 626-650

Abstract: Abstract 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. $$44.5\%$$ 44.5 % 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.

Keywords: Patient activation; Patient activation measure; Chronic care; Primary care; Machine learning; Binary classification; Logistic regression; Prediction (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10729-023-09653-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:hcarem:v:26:y:2023:i:4:d:10.1007_s10729-023-09653-4

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10729

DOI: 10.1007/s10729-023-09653-4

Access Statistics for this article

Health Care Management Science is currently edited by Yasar Ozcan

More articles in Health Care Management Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().