EUVIMEDDescoperă EUVIMED
Open access

Resource Use Patterns in US Telehealth Services: Machine Learning and Clustering Analysis Across 4 Specialties

Aysenur Betul Cengil iD, Burak Eksioglu iD, Sandra Duni Eksioglu iD, Corey Hayes iD, Cari Bogulski iD, Mir Ali iD

JMIR Medical Informatics · 2026

DOI: 10.2196/78030 ↗

At a glance

Journal article in JMIR Medical Informatics, 2026. Written by Aysenur Betul Cengil and 5 co-authors. Institution: Department of Industrial Engineering, University of Arkansas, Fayetteville, AR, United States. Major MEDLINE topics: Telemedicine, Machine Learning, Medicine. Cited 1 times so far (Crossref); 59 references. The full text is freely available in PubMed Central. Funded by: HRSA HHS.

RezumatSubjectsDate bibliograficeCiteRelated studies

Abstract (original language)

Background

The expansion of telehealth services, particularly during the COVID-19 pandemic, has transformed health care delivery in the United States. Telehealth promises greater access and resource efficiency by reducing wait times and appointment lengths, especially in specialties like psychiatry, behavioral health, bariatrics, and sleep medicine. However, disparities exist in adoption based on demographics, geography, and socioeconomic status, raising concerns about equitable access and optimal resource use.

Objective

This study aims to evaluate how telehealth impacts health care resource use across 4 specialties by examining 2 key metrics: patient-to-provider ratios and appointment durations. It seeks to understand how factors such as patient demographics, facility characteristics, and social determinants influence telehealth adoption and efficiency using a national dataset spanning from 2018 to 2023.

Methods

We analyzed a deidentified dataset from Epic Cosmos, covering outpatient visits across 48 US states (2018-2023). After data preprocessing and feature engineering, we applied 3 machine learning (ML) models (random forest, extreme gradient boosting, and deep neural networks) to predict resource use. Using the model performing the best, feature importance was assessed using Shapley Additive Explanations values. We then used k-means clustering to group facilities into clusters per specialty. Comparative analyses were conducted to evaluate differences in use among clusters, during and after the pandemic.

Results

Telehealth use peaked in 2020 and has remained above prepandemic levels since then. In 2018-2023, telehealth adoption reached 36.9% (4,543,021/12,311,710) in psychiatry, 23.9% (5,321,099/22,264,013) in behavioral health, 21.2% (924,333/4,360,061) in bariatrics, and 16.8% (851,803/5,070,256) in sleep medicine. Telehealth visits were consistently shorter than office visits (mean reduction 12.24 minutes; SD 3.33 minutes; P=.18), while patient-to-provider ratios varied significantly across specialties. Among ML models, extreme gradient boosting regression achieved the best performance (patient-to-provider ratios: R2=0.96-0.99; appointment durations: R2=0.61-0.69). Shapley Additive Explanations analysis identified visit type, telehealth use, facility size, rurality, and Social Vulnerability Index household vulnerability as the strongest predictors. Comparative analyses showed significant differences across clusters (all P

Subjects

MeSH terms (MEDLINE)

TelemedicineMachine LearningMedicineHumansCOVID-19United StatesCluster AnalysisClustering AlgorithmsSARS-CoV-2PandemicsDigital Health

Author keywords

COVID-19 pandemicclusteringdeep neural networksmachine learningresource usetelehealth

Authors and institutions

  • Department of Industrial Engineering, University of Arkansas, Fayetteville, AR, United States.
  • Department of Industrial, Manufacturing and Systems Engineering, Texas Tech University, Lubbock, TX, United States.
  • Institute for Digital Health and Innovation, University of Arkansas for Medical Sciences, Little Rock, AR, United States.
  • Department of Biomedical Informatics, University of Arkansas for Medical Sciences, Little Rock, AR, United States.
  • Center for Mental Healthcare and Outcomes Research, Central Arkansas Veterans Healthcare System, Little Rock, AR, United States.

ORCID profiles: Aysenur Betul Cengil, Burak Eksioglu, Sandra Duni Eksioglu, Corey Hayes, Cari Bogulski, Mir Ali

Funding

  • HRSA HHS

Cite

APA

Cengil, A. B., Eksioglu, B., Eksioglu, S. D., Hayes, C., Bogulski, C., & Ali, M. (2026). Resource Use Patterns in US Telehealth Services: Machine Learning and Clustering Analysis Across 4 Specialties. JMIR Medical Informatics. https://doi.org/10.2196/78030

Vancouver

Cengil AB, Eksioglu B, Eksioglu SD, Hayes C, Bogulski C, Ali M. Resource Use Patterns in US Telehealth Services: Machine Learning and Clustering Analysis Across 4 Specialties. JMIR Medical Informatics. 2026. doi:10.2196/78030

BibTeX
@article{Cengil2026,
  author = {Cengil, Aysenur Betul and Eksioglu, Burak and Eksioglu, Sandra Duni and Hayes, Corey and Bogulski, Cari and Ali, Mir},
  title = {Resource Use Patterns in US Telehealth Services: Machine Learning and Clustering Analysis Across 4 Specialties},
  journal = {JMIR Medical Informatics},
  year = {2026},
  doi = {10.2196/78030}
}
Start for free →