AI-Driven EHR and Clinical Decision Support Integration for Reliable, Efficient, and Patient-Centered Care: A Scoping Review

Background Artificial Intelligence (AI) and Electronic Health Records (EHRs) are increasingly working together to enhance predictive ability, decision-making, workflow efficiency, and deliver care. But good algorithmic performance is no guarantee of successful clinical integration or patient benefit. Objective The objective of the scoping review was to identify the current evidence regarding the use of AI to enhance EHRs and clinical decision support, exploring clinical applications, EHR integration, reliability and safety, workflow efficiency, patient-centered care and implementation maturity. Methods English language peer-reviewed articles between 2015 and 2026 were searched in 8 multidisciplinary information sources. The search was a combination of concepts involving AI, EHRs/EMRs and clinical decision support/workflow integration. There were 2,028 records identified with 184 being duplicates and 1,844 being screened. Sixty-two full-text reports were assessed for eligibility, of which 16 publications met the inclusion criteria and were included in the review. Evidence was compiled descriptively and thematically by care delivery domains and a continuum of evidence maturities. Results The types of AI-powered EHR/CDSS applications included risk prediction, early warning, diagnosis and prognosis, triage, treatment and medication support, documentation, and workflow optimization. Technical performance and selected reliability outcomes were best supported by evidence, while prospective evaluation, external validation, sustained deployment in the real-world, and directly measured outcomes from a patient perspective were less well developed. Reported benefits of workflow were noted, but interoperability concerns, alert and cognitive burden, usability, clinician trust, explainability and governance were still key implementation concerns. Conclusion AI has developed from prediction to clinically integrated decision support, but has not reached a level of translational maturity. Systems that are interoperable and prospectively evaluated and systemically human-supervised should be emphasized in future progress, and should be shown to have measurable advantages in safety, efficiency, clinician workflow, patient-centered outcomes, and real-world systems of care delivery.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-18
DOI
https://doi.org/10.21203/rs.3.rs-11275950/v1
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

AI-Driven EHR and Clinical Decision Support Integration for Reliable, Efficient, and Patient-Centered Care: A Scoping Review

David Tetteh Akuaku Blemano, Frederick Damptey, Gideon Owusu, Benjamin Asomaning Odoom
4 links
Research Square
Artificial Intelligence in Healthcare and Education
preprint

AI-Driven EHR and Clinical Decision Support Integration for Reliable, Efficient, and Patient-Centered Care: A Scoping Review

David Tetteh Akuaku Blemano, Frederick Damptey, Gideon Owusu, Benjamin Asomaning Odoom
preprint en

Abstract

Background Artificial Intelligence (AI) and Electronic Health Records (EHRs) are increasingly working together to enhance predictive ability, decision-making, workflow efficiency, and deliver care. But good algorithmic performance is no guarantee of successful clinical integration or patient benefit. Objective The objective of the scoping review was to identify the current evidence regarding the use of AI to enhance EHRs and clinical decision support, exploring clinical applications, EHR integration, reliability and safety, workflow efficiency, patient-centered care and implementation maturity. Methods English language peer-reviewed articles between 2015 and 2026 were searched in 8 multidisciplinary information sources. The search was a combination of concepts involving AI, EHRs/EMRs and clinical decision support/workflow integration. There were 2,028 records identified with 184 being duplicates and 1,844 being screened. Sixty-two full-text reports were assessed for eligibility, of which 16 publications met the inclusion criteria and were included in the review. Evidence was compiled descriptively and thematically by care delivery domains and a continuum of evidence maturities. Results The types of AI-powered EHR/CDSS applications included risk prediction, early warning, diagnosis and prognosis, triage, treatment and medication support, documentation, and workflow optimization. Technical performance and selected reliability outcomes were best supported by evidence, while prospective evaluation, external validation, sustained deployment in the real-world, and directly measured outcomes from a patient perspective were less well developed. Reported benefits of workflow were noted, but interoperability concerns, alert and cognitive burden, usability, clinician trust, explainability and governance were still key implementation concerns. Conclusion AI has developed from prediction to clinically integrated decision support, but has not reached a level of translational maturity. Systems that are interoperable and prospectively evaluated and systemically human-supervised should be emphasized in future progress, and should be shown to have measurable advantages in safety, efficiency, clinician workflow, patient-centered outcomes, and real-world systems of care delivery.

Research Square
Michigan Technological University (US)
Good health and well-being
Artificial Intelligence in Healthcare and Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon