Predictive Analytics and Workflow Automation to Reduce Administrative Burden and Clinician Burnout in United States Clinical Settings: A Systematic Review
Advances in Health Information Science and Practice · 09.11.2026 · 2 (2)
DOI: 10.63116/ah.000000010 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Advances in Health Information Science and Practice, erschienen am 09.11.2026. Verfasst von Annette Akosah und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Health Informatics, Rutgers School of Health Professions, Rutgers, The State University of New Jersey. Hauptthemen laut MEDLINE: Workflow, Electronic Health Records, Burnout, Professional, Automation. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Burnout in der Pflege
Abstract (Originalsprache)
Background
Electronic health record (EHR)–related administrative burden remains a frequently cited contributor to clinician burnout in the United States. Although digital systems were implemented to improve quality, safety, and care coordination, expanded documentation requirements, inbox messaging, and regulatory reporting have increased clerical workload. Traditional interruptive clinical decision support tools may further increase cognitive demands through alert fatigue and workflow disruption. Health systems have increasingly adopted predictive analytics and workflow-integrated automation, including ambient artificial intelligence (AI) documentation, inbox prioritization, and audit log–based workflow monitoring. However, their effects on operational efficiency and clinician well-being remain uncertain. This review examined clinician-facing interventions in US clinical settings and their impact on documentation workload, operational efficiency, and burnout-related outcomes.
Methods
A systematic review guided by Preferred Reporting Items for Systematic Reviews and Meta-Analyses was conducted using PubMed, CINAHL, and Embase. The search included English-language studies published between January 1, 2019, and December 31, 2025, with an updated search capturing eligible early online publications through 2026. Eligible studies evaluated clinician-facing predictive analytics or workflow automation in US clinical settings and reported measurable outcomes, including documentation time, after-hours EHR use, alert burden, cognitive task load, productivity, or validated burnout measures. Findings were synthesized narratively because interventions and outcome measures varied.
Results
Of 520 records identified, 173 unique records were screened; 24 (13.9%) underwent full-text review, and 7 of 24 (29.2%) met inclusion criteria. Ambient AI documentation platforms were associated with approximately 10%–30% reductions in documentation time, although findings on after-hours EHR activity varied. Several multisite implementations reported improvements in validated burnout measures and cognitive task load. AI-driven inbox prioritization reduced message review time, while audit log–based clinical decision support monitoring identified changes in EHR activity patterns following intervention. Evidence quality varied, and follow-up periods were generally short.
Conclusions
Workflow-integrated predictive analytics and automation interventions were associated with measurable improvements in documentation workload and selected burnout indicators in US clinical settings. However, evidence remains mixed and largely observational. Rigorous, multisite, longitudinal evaluations using standardized workload and burnout metrics are needed to determine sustainability and generalizability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Health Informatics, Rutgers School of Health Professions, Rutgers, The State University of New Jersey.
ORCID-Profile: Annette Akosah
Zitieren
APA
Akosah, A., & Hunt, T. J. (2026). Predictive Analytics and Workflow Automation to Reduce Administrative Burden and Clinician Burnout in United States Clinical Settings: A Systematic Review. Advances in Health Information Science and Practice, 2(2). https://doi.org/10.63116/ah.000000010
Vancouver
Akosah A, Hunt TJ. Predictive Analytics and Workflow Automation to Reduce Administrative Burden and Clinician Burnout in United States Clinical Settings: A Systematic Review. Advances in Health Information Science and Practice. 2026;2(2). doi:10.63116/ah.000000010
BibTeX
@article{Akosah2026,
author = {Akosah, Annette and Hunt, Thomas J},
title = {Predictive Analytics and Workflow Automation to Reduce Administrative Burden and Clinician Burnout in United States Clinical Settings: A Systematic Review},
journal = {Advances in Health Information Science and Practice},
year = {2026},
volume = {2},
number = {2},
doi = {10.63116/ah.000000010}
}
EUVIMED