{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:23:04Z","timestamp":1787689384214,"version":"build-2784847793"},"reference-count":59,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>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&lt;.05).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Telehealth has become a sustainable component of health care, enhancing access and efficiency across both rural and urban areas. However, its impact varies across specialties and regions, highlighting the need for targeted strategies such as staffing support for vulnerable populations, infrastructure investments in rural facilities, and reimbursement models that reflect telehealth\u2019s resource use. This study provides robust evidence from ML and clustering analyses, demonstrating how telehealth shapes resource use and offering actionable insights for equitable and sustainable integration.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/78030","type":"journal-article","created":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T22:30:07Z","timestamp":1766010607000},"page":"e78030","source":"Crossref","is-referenced-by-count":1,"title":["Resource Use Patterns in US Telehealth Services: Machine Learning and Clustering Analysis Across 4 Specialties"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9468-6392","authenticated-orcid":false,"given":"Aysenur Betul","family":"Cengil","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-6783","authenticated-orcid":false,"given":"Burak","family":"Eksioglu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6674-2133","authenticated-orcid":false,"given":"Sandra Duni","family":"Eksioglu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7776-6157","authenticated-orcid":false,"given":"Corey","family":"Hayes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6002-5945","authenticated-orcid":false,"given":"Cari","family":"Bogulski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3199-5261","authenticated-orcid":false,"given":"Mir","family":"Ali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,5,7]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.2013.1054"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11886-021-01544-w"},{"key":"ref3","unstructured":"SarahGTelehealth expansion in Medicare: policy changes, recent trends in adoption, and future impactCareJourney20202024-01-07https:\/\/carejourney.com\/telehealth-expansion-in-medicare-policy-changes-recent-trends-in-adoption-and-future-impact\/"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.healthpol.2003.09.011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1601705"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/isre.2023.1220"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1007\/978-3-030-59687-3_11","author":"Bernacchio, CP","year":"2020","journal-title":"Sustainable Community Health: Systems and Practices in Diverse Settings"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2023.1184971"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa072"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1089\/tmj.2021.0077"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1089\/tmr.2021.0040"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2217\/cer-2021-0242"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/1357633X231160039"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1089\/tmj.2021.0041"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2196\/49190"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1089\/tmj.2022.0516"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2021.107134"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1089\/tmj.2020.0525"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1089\/tmj.2017.0095"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-022-07858-x"},{"key":"ref21","unstructured":"MadjidKEunyCLSaraJCAldrenGViolandaGScottRSNancyDLBenjaminDSNational survey trends in telehealth use in 2021: disparities in utilization and audio vs. video servicesOffice of Health Policy20222026-01-24https:\/\/aspe.hhs.gov\/sites\/default\/files\/documents\/4e1853c0b4885112b2994680a58af9ed\/telehealth-hps-ib.pdf"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2196\/38661"},{"key":"ref23","unstructured":"SamsonLWCoutureSJCreedonTBJacobusKantorLSheingoldSUpdated Medicare FFS telehealth trends by beneficiary characteristics, visit specialty, and state, 2019-2021Assistant Secretary for Planning and Evaluation20232026-01-24https:\/\/aspe.hhs.gov\/sites\/default\/files\/documents\/cb83f6f25c25c3a3529807f23cd2327d\/medicare-telehealth-updated-trends-report.pdf"},{"key":"ref24","unstructured":"SamsonLWTaraziWTurriniGSheingoldSMedicare beneficiaries\u2019 use of telehealth in 2020: trends by beneficiary characteristics and locationAssistant Secretary for Planning and Evaluation20212026-01-24https:\/\/aspe.hhs.gov\/reports\/medicare-beneficiaries-use-telehealth-2020"},{"key":"ref25","unstructured":"Organizations live with Epic CosmosEpic Systems Corporation20232023-06-19https:\/\/cosmos.epic.com\/"},{"key":"ref26","first-page":"27","author":"Max, KJ","year":"2013","journal-title":"Applied Predictive Modeling"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1089\/tmj.2021.0330"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1089\/tmj.2021.0412"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.2020.01786"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2196\/23905"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooaf056"},{"key":"ref32","unstructured":"Social Vulnerability IndexAgency for Toxic Substances and Disease Registry20232024-04-06https:\/\/www.atsdr.cdc.gov\/place-health\/php\/svi\/index.html"},{"key":"ref33","author":"Jason, B","year":"2020","journal-title":"Data Preparation for Machine Learning: Data Cleaning, Feature Selection, and Data Transforms in Python"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1149\/10701.6137ecst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00373-4"},{"issue":"3","key":"ref36","first-page":"18","volume":"2","author":"Andy, LW","year":"2002","journal-title":"R News"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2021.3060483"},{"key":"ref38","unstructured":"Efficient optimization algorithmsOptuna20242024-06-19https:\/\/optuna.readthedocs.io\/en\/stable\/tutorial\/10_key_features\/003_efficient_optimization_algorithms.html"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.623"},{"key":"ref40","unstructured":"LundbergSMLeeSIshapGitHub20172024-08-13https:\/\/github.com\/shap\/shap"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.2988796"},{"issue":"3","key":"ref42","first-page":"69","volume":"24","author":"Mukaka, MM","year":"2012","journal-title":"Malawi Med J"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-47578-3","author":"Aggarwal, CC","year":"2017","journal-title":"Outlier Analysis. 2nd Edition"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-7138-7","author":"James, G","year":"2013","journal-title":"An Introduction to Statistical Learning: With Applications in R"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.1979.4766909"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/03610927408827101"},{"key":"ref47","author":"Brian, SE","year":"2011","journal-title":"Wiley Series in Probability and Statistics"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.4103\/aca.ACA_94_19"},{"key":"ref49","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-6351-086-8","author":"Ross, A","year":"2017","journal-title":"Basic and Advanced Statistical Tests"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3102\/00028312003003187"},{"key":"ref51","doi-asserted-by":"crossref","DOI":"10.1201\/9781420036268","author":"Sheskin, DJ","year":"2003","journal-title":"Handbook of Parametric and Nonparametric Statistical Procedures"},{"key":"ref52","author":"Andy, F","year":"2024","journal-title":"Discovering Statistics Using IBM SPSS Statistics"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.10387"},{"key":"ref54","unstructured":"Rural-urban commuting area codes\u2014documentationUSDA, Economic Research Service20232024-06-14https:\/\/www.ers.usda.gov\/data-products\/rural-urban-commuting-area-codes\/documentation"},{"key":"ref55","author":"Afshin, G","year":"2018","journal-title":"Technical Report UTEP-CS-18-09"},{"key":"ref56","unstructured":"Telehealth visits unlikely to require in-person follow-up within 90 daysEpic Research20242026-01-24https:\/\/www.epicresearch.org\/articles\/telehealth-visits-unlikely-to-require-in-person-follow-up-within-90-days"},{"key":"ref57","unstructured":"Telehealth visits frequently billed at lower level of service than office visitsEpic Research2024-04-23https:\/\/www.epicresearch.org\/articles\/telehealth-visits-frequently-billed-at-lower-level-of-service-than-office-visits"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1089\/pop.2022.0189"},{"key":"ref59","unstructured":"American Community Survey 5-year data (2009-2024)US Census Bureau2026-03-14https:\/\/www.census.gov\/data\/developers\/data-sets\/acs-5year.html"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e78030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:10:29Z","timestamp":1782843029000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e78030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,7]]},"references-count":59,"URL":"https:\/\/doi.org\/10.2196\/78030","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.78030","asserted-by":"object"}]},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,7]]}}}