A prebill control plane for record integrity in inpatient artificial intelligence-enabled clinical documentation workflows.
- 1Accuity Delivery Systems, LLC d/b/a Accuity, Mount Laurel, NJ, United States.
- 2Icahn School of Medicine at Mount Sinai, New York, NY, United States.
Abstract
Ambient artificial intelligence (AI) scribes and other electronic health record (EHR)-integrated generative AI tools are entering clinical documentation workflows because they offer measurable, if still modest, gains in documentation efficiency and clinician experience. At the same time, the medical record remains a high-consequence informatics object that supports clinical communication, continuity, documentation clarification, coding, payment, and downstream organizational reporting. As AI-generated content moves through drafting, summarization, clarification, and coding-adjacent workflows, the central challenge is no longer simply whether a model can generate fluent text, but whether health systems can preserve record integrity as documentation moves downstream. We examine this problem in United States inpatient claim-linked workflows. This Perspective proposes a prebill control plane as a candidate governance model for that problem. We describe three recurring modes of record-integrity failure that motivate it: unsupported addition, clinically meaningful loss, and propagation across encounters and systems. We then outline five operational components of a minimum viable control plane: physician-led governance and oversight, evidence visibility, change control, monitoring, and auditability. The framework is intended to support safer adoption by protecting patient safety, clinician safety, and record integrity under real-world inpatient and mid-revenue-cycle workflow pressure.
Related
- A Framework to Monitor Editing of Artificial Intelligence-Generated Medical Documentation
- Diagnostic Concordance Across Text and Image Workflows in Nine Consumer Multimodal Artificial Intelligence Systems for Cutaneous Vascular Anomalies: A Cross-Sectional Audit.
- A focused PubMed artificial intelligence search program creates better literature reviews than general purpose artificial intelligence and is comparable to trainees in shoulder and elbow surgery
- Generative Artificial Intelligence Models in Breast Cancer Diagnosis: A Systematic Review
- Low-Dose CT in the Age of Artificial Intelligence: Techniques, Evidence, and Clinical Impact
BibTeX
@article{smith2026prebill,
title = {{A prebill control plane for record integrity in inpatient artificial intelligence-enabled clinical documentation workflows.}},
author = {Stephanie Smith and Hani Judeh},
journal = {Frontiers in digital health},
year = {2026},
month = oct,
doi = {10.3389/fdgth.2026.1910263},
url = {https://europepmc.org/article/MED/42923338},
note = {CC BY},
}
RIS
TY - JOUR
TI - A prebill control plane for record integrity in inpatient artificial intelligence-enabled clinical documentation workflows.
AU - Stephanie Smith
AU - Hani Judeh
PY - 2026
DA - 2026/10/08
JO - Frontiers in digital health
DO - 10.3389/fdgth.2026.1910263
UR - https://europepmc.org/article/MED/42923338
AB - Ambient artificial intelligence (AI) scribes and other electronic health record (EHR)-integrated generative AI tools are entering clinical documentation workflows because they offer measurable, if still modest, gains in documentation efficiency and clinician experience. At the same time, the medical record remains a high-consequence informatics object that supports clinical communication, continuity, documentation clarification, coding, payment, and downstream organizational reporting. As AI-generated content moves through drafting, summarization, clarification, and coding-adjacent workflows, the central challenge is no longer simply whether a model can generate fluent text, but whether health systems can preserve record integrity as documentation moves downstream. We examine this problem in United States inpatient claim-linked workflows. This Perspective proposes a prebill control plane as a candidate governance model for that problem. We describe three recurring modes of record-integrity failure that motivate it: unsupported addition, clinically meaningful loss, and propagation across encounters and systems. We then outline five operational components of a minimum viable control plane: physician-led governance and oversight, evidence visibility, change control, monitoring, and auditability. The framework is intended to support safer adoption by protecting patient safety, clinician safety, and record integrity under real-world inpatient and mid-revenue-cycle workflow pressure.
SN - 2673-253X
ER -