Work

Optimizing telehealth utilization during COVID-19: enhancing efficiency and equity through data envelopment analysis and machine learning

Year: 2025

Type: article

Abstract: This study investigates the efficiency of telehealth utilization across U.S. counties during the COVID-19 pandemic, with a focus on identifying the key drivers of efficiency, especially in rural and underserved areas. The primary research goal is to assess the efficiency of telehealth utilization and examine patterns of resource misallocation. A hybrid methodological framework integrates Data Envelopment Analysis to measure county-level efficiency scores and Machine Learning techniques to uncover the most influential predictors of those scores, revealing patterns in resource distribution and infrastructure that contribute to disparities in telehealth performance. Using secondary data from CMS’s 5% Medicare Fee-For-Service claims and various public health databases, the analysis spans all fifty states and the District of Columbia. Findings indicate significant inefficiencies in rural regions, largely tied to limited broadband access, workforce shortages, and adverse social determinants of health. These results highlight the need for targeted policy interventions to improve both the equity and efficiency of telehealth services.

Source: Operational Research

DOI: 10.1007/s12351-025-00978-2

Authors: Ying-Chih Sun, Ozlem Cosgun, Raj Sharman

Institutions: East Central University, Montclair State University, University at Buffalo, State University of New York

Language: English

Topic: Telemedicine and Telehealth Implementation

Subfield: Public Health, Environmental and Occupational Health

Field: Medicine

Domain: Health Sciences

SDGs: Reduced inequalities, Industry, innovation and infrastructure, Good health and well-being

Open Access status: hybrid

Estimated APC paid: $3,190