Hospitals Adopt Machine Learning Within EHRs
A study of 2,562 US general acute hospitals using 2022–2024 AHA survey data finds about 75% had ML functions integrated into EHRs in 2023–2024, with clinical and operational functions commonly adopted together and inpatient risk prediction most frequent. Multivariate models show higher adoption in large, not‑for‑profit, metropolitan, system‑affiliated hospitals using leading EHR vendors, while limited model-evaluation practices raise equity and oversight concerns.
Key Points
- 1Reports: about 75% of 2,562 US hospitals had ML integrated into EHRs in 2023–2024.
- 2Finds: adoption concentrated in large, not‑for‑profit, metropolitan, system‑affiliated hospitals and leading EHR vendors.
- 3Implies: limited ML evaluation practices risk digital inequities, requiring stronger oversight and targeted support.
Scoring Rationale
Provides nationally representative adoption estimates and predictors, but lacks causal analysis and detailed implementation guidance.
Sources
Public references used for this report.
Practice with real FinTech & Trading data
90 SQL & Python problems · 15 industry datasets
250 free problems · No credit card
See all FinTech & Trading problems
