JMIR Publications

ABSTRACT

Background:

Telehealth expansion and artificial intelligence (AI) adoption are often described as parallel dimensions of health system digital transformation. However, whether telehealth scale is associated with hospital AI maturity, and whether this relationship varies across hospital settings, remains unclear.

Objective:

This study examined the association of telehealth scale with clinical and operational AI maturity in US hospitals and assessed whether these patterns differed by telehealth reporting behavior and geography.

Methods:

We conducted a cross-sectional study of 6,173 US acute care hospitals using linked 2024 American Hospital Association Annual Survey and Information Technology Supplement data and 2023 Healthcare Cost Report Information System data. Telehealth scale was parameterized using log-transformed telehealth volume, a telehealth nonreporting indicator, and a reported-zero telehealth indicator. Clinical and operational AI maturity were derived from hospital-reported AI capability items and classified into 3 tiers. We modeled both outcomes using multioutput gradient-boosted tree classifiers and interpreted model behavior using SHapley Additive exPlanations (SHAP), partial dependence plots, and stratified analyses by Core-Based Statistical Area category.

Results:

Telehealth volume was the strongest predictor of both clinical and operational AI maturity and had a larger contribution in the clinical AI model. Telehealth nonreporting was common, occurring in 57.0% (3,521/6,173) of hospitals, and was concentrated among hospitals in the lowest clinical AI maturity tier, accounting for 91.4% (3,145/3,441) of hospitals with no reported clinical AI adoption. Higher telehealth volume was associated with a steep increase in predicted clinical AI maturity at lower telehealth volumes, followed by a plateau at higher volumes. At similar telehealth volumes, rural hospitals showed weaker telehealth-attributed contributions to predicted clinical AI maturity than metropolitan hospitals. Supplementary analyses suggested that telehealth reporting status and telehealth intensity reflected related but distinct structural processes.

Conclusions:

Telehealth scale was strongly associated with hospital AI maturity, especially clinical AI maturity. These findings suggest that telehealth capacity may function as a marker of broader digital readiness for AI implementation rather than simply as a standalone service modality. Hospitals with telehealth nonreporting and rural hospitals may face additional structural barriers that limit translation of digital capacity into AI maturity. Policies to reduce inequities in hospital AI adoption may therefore need to pair telehealth expansion with implementation support, interoperability capacity, and organizational resources.