JMIR Publications

ABSTRACT

Background:

The expansion of telehealth services, particularly during the COVID-19 pandemic, has transformed healthcare delivery in the U.S. 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 healthcare resource utilization across four specialties by examining two 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:

A deidentified dataset from Epic Cosmos covering healthcare visits across 48 U.S. states was analyzed. The study used a multi-step approach involving data preprocessing, machine learning (particularly deep neural networks), and clustering analysis. Factors like age, race, gender, insurance type, rurality, and the CDC’s Social Vulnerability Index were examined. Resource use was measured by appointment duration and patient-to-provider ratios. Clustering grouped healthcare facilities based on utilization patterns, and statistical tests assessed differences over time and across clusters.

Results:

Telehealth visits increased dramatically during the pandemic and remained above pre-pandemic levels. The highest telehealth usage was seen in Psychiatry and Behavioral Health, particularly in the West and Northeast. Telehealth generally led to higher patient-to-provider ratios and shorter appointment durations, though patterns varied by specialty and region. Machine learning models identified visit type, provider numbers, and public insurance as key predictors. Clustering revealed significant differences in resource use across facility types and specialties, influenced by rurality and socioeconomic vulnerability.

Conclusions:

Telehealth has become a sustainable component of healthcare, enhancing access and efficiency across both rural and urban areas. However, its impact varies across specialties and regions, necessitating tailored strategies for implementation. The study highlights the importance of supporting telehealth infrastructure in underserved areas and adapting care models and policies to ensure equitable and efficient healthcare delivery. Future research should focus on evolving usage patterns and translating findings into actionable policy and operational frameworks.