Clinical decision support for population health management: development and validation of integrated acuity and intervention prediction models
Journal of the American Medical Informatics Association · 01.03.2026 · 33 (3) · 670-678
DOI: 10.1093/jamia/ocaf225 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 29.12.2025. Verfasst von Sanjay Basu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Clinical Product Development, Waymark, San Francisco, CA 94115, United States. Hauptthemen laut MEDLINE: Decision Support Systems, Clinical, Population Health Management, Patient Acuity. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Objective
Population health management programs coordinate care for over 80 million Medicaid beneficiaries but lack systematic clinical decision support for determining when to intervene and which interventions to select for patients with complex conditions. Our objective was to develop and validate a clinical decision support system integrating acuity prediction and intervention selection models for population health management programs. Materials and methods We conducted a retrospective cohort study of 155 631 Medicaid patients enrolled in population health programs across Washington, Virginia, and Ohio (January 2023-July 2025). We developed integrated informatics workflows combining time-to-event prediction models for acute care events with heterogeneous treatment effect estimators for intervention selection. Models used structured electronic health record data, claims, and care management records. Performance was evaluated through clinical validation with 3 blinded physicians reviewing 200 cases.
Results
The integrated decision support system achieved 81.3% sensitivity (95% CI, 79.8%-82.8%) and 82.1% specificity (95% CI, 80.6%-83.6%) for 30-day acute care prediction. The intervention selection component demonstrated 1.59 percentage points absolute risk reduction compared with standard care (95% CI, 0.21-3.04), translating to preventing one acute event for every 63 patients receiving model-guided rather than standard care. Clinical validation revealed systematic differences: physicians relied on recent utilization patterns (explaining 75.8% of decision variance) while models integrated broader clinical signals, identifying intervention opportunities earlier in disease trajectories. Both approaches recommended similar intervention types, suggesting complementary rather than replacement roles.
Discussion
An integrated clinical decision support system can enhance population health management by providing actionable guidance on intervention timing and selection.
Conclusion
An integrated decision support system’s ability to identify opportunities before high utilization manifests offers potential for shifting from reactive to preventive care delivery for vulnerable populations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Clinical Product Development, Waymark, San Francisco, CA 94115, United States.
- Department of Medicine, University of California San Francisco, San Francisco, CA 94110, United States.
- School of Social Policy & Practice, University of Pennsylvania, Philadelphia, PA 19104, United States.
ORCID-Profile: Sanjay Basu
Zitieren
APA
Basu, S., Patel, S. Y., Sheth, P., Muralidharan, B., Elamaran, N., Kinra, A., & Batniji, R. (2026). Clinical decision support for population health management: development and validation of integrated acuity and intervention prediction models. Journal of the American Medical Informatics Association, 33(3), 670-678. https://doi.org/10.1093/jamia/ocaf225
Vancouver
Basu S, Patel SY, Sheth P, Muralidharan B, Elamaran N, Kinra A, et al. Clinical decision support for population health management: development and validation of integrated acuity and intervention prediction models. Journal of the American Medical Informatics Association. 2026;33(3):670-678. doi:10.1093/jamia/ocaf225
BibTeX
@article{Basu2026,
author = {Basu, Sanjay and Patel, Sadiq Y and Sheth, Parth and Muralidharan, Bhairavi and Elamaran, Namrata and Kinra, Aakriti and Batniji, Rajaie},
title = {Clinical decision support for population health management: development and validation of integrated acuity and intervention prediction models},
journal = {Journal of the American Medical Informatics Association},
year = {2026},
volume = {33},
number = {3},
pages = {670--678},
doi = {10.1093/jamia/ocaf225}
}
EUVIMED