Currently submitted to: JMIR Medical Informatics
Date Submitted: Mar 24, 2026
Open Peer Review Period: Apr 17, 2026 - Jun 12, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
An End-to-End DataOps Framework for Automated Predictive Analytics in Regulated Healthcare Environments: Architecture, Implementation, and Evaluation
ABSTRACT
Background:
Skilled nursing facilities (SNFs) operate under data-intensive regulatory environments requiring HIPAA-compliant, continuously deployable predictive analytics pipelines. Existing DataOps approaches address individual pipeline components in isolation but lack an integrated clinical informatics architecture tailored to the long-term care setting.
Objective:
To design, implement, and evaluate an end-to-end DataOps framework for automated predictive analytics in regulated SNF environments, integrating infrastructure-as-code, CI/CD automation, and automated MLOps into a unified architecture.
Methods:
We developed a five-layer, cloud-native DataOps framework unifying Azure Synapse Analytics, Terraform infrastructure-as-code, and GitHub Actions CI/CD. The framework was deployed across five SNF sites serving over 3,500 patients monthly and evaluated over a three-month pilot with a matched three-month pre-implementation baseline.
Results:
The framework reduced manual data engineering effort by 30%, improved 30-day readmission prediction ROC-AUC from 0.82 to 0.89, and was associated with a 12.2% reduction in 30-day unplanned readmissions (148 to 130 events). Dashboard latency was maintained below 15 minutes (mean: 11.4 min) and infrastructure provisioning was repeatable within 30 minutes.
Conclusions:
The proposed DataOps framework provides a reproducible, audit-ready clinical informatics architecture for SNF environments. The integration of CI/CD, infrastructure-as-code, and automated MLOps addresses a gap in the health informatics literature and offers a practical blueprint for operationalizing predictive analytics under regulatory constraints.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.