CoChat

Quality Assurance during the Rapid Implementation of an AI-Assisted Clinical Documentation Support Tool

The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.

Abstract

AbstractWe describe a quality assurance evaluation process undertaken during the deployment of an artificial intelligence (AI)-assisted clinical documentation support tool throughout a large integrated delivery system. AI clinical documentation support tools have improved dramatically with the latest generation of large language models but have not been used in the variety of clinical specialties, geographic settings, and real-world situations available to large care delivery systems. In parallel with our deployment process, a small evaluation team assessed the level of risk for planned use cases, modified existing approaches, and leveraged the deployment teams and early adopters to provide a robust viewpoint on the technology through crowdsourced data and both quantitative and qualitative approaches. The results of the evaluation were used to modify training, provide feedback to the vendor, stage deployment, and transition to postdeployment monitoring.

Overview

Integrity signals

Registry

Crossref · 10.1056/aics2400977

Cites

20 of 20 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Research works printed but not linked: 4

  1. Lucian Leape Institute. Patient safety and artificial intelligence: opportunities and challenges for care delivery. Boston: Institute for Healthcare Improvement, 2024 (https://www.ihi.org/resources/publications/patient-safety-and-artificial-intelligence-opportunities-and-challenges-care#downloads).
  2. Kaiser Permanente. Kaiser Permanente improves member experience with AI-enabled clinical technology. August 14 2024 (https://about.kaiserpermanente.org/news/press-release-archive/kaiser-permanente-improves-member-experience-with-ai-enabled-clinical-technology).
  3. Oberst M, Liang D, Lipton ZC. Pioneering the science of AI evaluation. Pittsburgh: Abridge AI, 2024 (https://www.abridge.com/ai/science-ai-evaluation#monitoring).
  4. Rogers EM, Singhal A, Quinlan MM. Diffusion of innovations. In: Stacks DW, Salwen MB, eds. An integrated approach to communication theory and research. New York: Routledge, 2014:432-448.

Cited by

See all 19

Metadata

Authors
Cain, C. H., Davis, A. C., Broder, B., Chu, E., DeHaven, A. H., Domenigoni, A., Gin, N., Kapoor, A., Liu, V., MacLean, A., Mott, C., Nayak, R., Nevitt, K., Nguyen, K., Shin, J., Strull, W., Yang, D., Young, S. M., & Young, S.
Affiliations
  • Kaiser Permanente (US)
  • Kaiser Permanente Bernard J. Tyson School of Medicine (US)
  • Northwest Permanente, Portland, OR
  • KP Medical Foundation, Oakland, CA
  • The Southeast Permanente Medical Group, Atlanta, GA
  • Kaiser Foundation Health Plan and Hospitals Quality, Oakland, CA
Venue
NEJM AI
Published
2025-03-27
Volume
2
Issue
4
Pages
AIcs2400977-AIcs2400977
ISSN
2836-9386 (ISSN-L)
OpenAlex
W4408811414
Cited by
19
References
20
Citations by year
2026: 14 · 2025: 5
FWCI
14.94
Type
journal article
Language
en
Open access
closed
Locations
  • NEJM AI (publishedVersion)
  • PubMed (publishedVersion)
Topics
  • Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Nursing › Research and Theory › Nursing Diagnosis and Documentation
Keywords
quality assurance, artificial intelligence, clinical documentation, electronic health records, clinical documentation improvement, AI implementation, medical record accuracy

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.