A Large Language Model Screening Tool to Target Patients for Best Practice Alerts: Development and Validation
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Background: Best Practice Alerts (BPAs) are alert messages to physicians in the electronic health record that are used to encourage appropriate use of health care resources. While these alerts are helpful in both improving care and reducing costs, BPAs are often broadly applied nonselectively across entire patient populations. The development of large language models (LLMs) provides an opportunity to selectively identify patients for BPAs. Objective: In this paper, we present an example case where an LLM screening tool is used to select patients appropriate for a BPA encouraging the prescription of deep vein thrombosis (DVT) anticoagulation prophylaxis. The artificial intelligence (AI) screening tool was developed to identify patients experiencing acute bleeding and exclude them from receiving a DVT prophylaxis BPA. Methods: Our AI screening tool used a BioMed-RoBERTa (Robustly Optimized Bidirectional Encoder Representations from Transformers Pretraining Approach; AllenAI) model to perform classification of physician notes, identifying patients without active bleeding and thus appropriate for a thromboembolism prophylaxis BPA. The BioMed-RoBERTa model was fine-tuned using 500 history and physical notes of patients from the MIMIC-III (Medical Information Mart for Intensive Care) database who were not prescribed anticoagulation. A development set of 300 MIMIC patient notes was used to determine the model’s hyperparameters, and a separate test set of 300 patient notes was used to evaluate the screening tool. Results: Our MIMIC-III test set population of 300 patients included 72 patients with bleeding (ie, were not appropriate for a DVT prophylaxis BPA) and 228 without bleeding who were appropriate for a DVT prophylaxis BPA. The AI screening tool achieved impressive accuracy with a precision-recall area under the curve of 0.82 (95% CI 0.75-0.89) and a receiver operator curve area under the curve of 0.89 (95% CI 0.84-0.94). The screening tool reduced the number of patients who would trigger an alert by 20% (240 instead of 300 alerts) and increased alert applicability by 14.8% (218 [90.8%] positive alerts from 240 total alerts instead of 228 [76%] positive alerts from 300 total alerts), compared to nonselectively sending alerts for all patients. Conclusions: These results show a proof of concept on how language models can be used as a screening tool for BPAs. We provide an example AI screening tool that uses a HIPAA (Health Insurance Portability and Accountability Act)–compliant BioMed-RoBERTa model deployed with minimal computing power. Larger models (eg, Generative Pre-trained Transformers–3, Generative Pre-trained Transformers–4, and Pathways Language Model) will exhibit superior performance but require data use agreements to be HIPAA compliant. We anticipate LLMs to revolutionize quality improvement in hospital medicine.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Overriding of Drug Safety Alerts in Computerized Physician Order Entry
van der Sijs, H., Aarts, J., Vulto, A., & Berg, M. (2006) · Journal of the American Medical Informatics Association · doi:10.1197/jamia.m1809 · Cited by 1,117 · cited 1×
“Current BPAs are often overconservative, broadly applied to all possible patients, resulting in up to 49% to 96% of alerts being overridden or ignored [4].”
Backgroundwith the HITEC Investigators, Ancker, J. S., Edwards, A., Nosal, S., Hauser, D., Mauer, E., & Kaushal, R. (2017) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-017-0430-8 · Cited by 709 · cited 1×
“Nevertheless, despite these benefits, the overuse of BPAs can cause alarm fatigue and desensitization that can even lead to patient harm, as described by the Joint Commission Alert System Safety Report of 2014 [2,3].”
BackgroundJohnson, A., Pollard, T., & Mark, R. (2015) · PhysioNet · doi:10.13026/c2xw26 · Cited by 165
Cited by
Bedi, S., Liu, Y., Orr-Ewing, L., Dash, D., Koyejo, S., Callahan, A., Fries, J. A., Wornow, M., Swaminathan, A., Lehmann, L. S., et al. (2024) · doi:10.1101/2024.04.15.24305869 · Cited by 738
Testing and Evaluation of Health Care Applications of Large Language Models: A Systematic Review
Bedi, S., Liu, Y., Orr-Ewing, L., Dash, D., Koyejo, S., Callahan, A., Fries, J. A., Wornow, M., Swaminathan, A., Lehmann, L. S., et al. (2025) · JAMA · doi:10.1001/jama.2024.21700 · Cited by 662
Current applications and challenges in large language models for patient care: a systematic review
Busch, F., Hoffmann, L., Rueger, C., van Dijk, E. H., Kader, R., Ortiz-Prado, E., Makowski, M. R., Saba, L., Hadamitzky, M., Kather, J. N., et al. (2025) · Communications Medicine · doi:10.1038/s43856-024-00717-2 · Cited by 358
Large Language Models in Critical Care Medicine: Scoping Review
Shi, T., Ma, J., Yu, Z., Xu, H., Yang, R., Xiong, M., Xiao, M., Li, Y., Zhao, H., & Kong, G. (2025) · JMIR Medical Informatics · doi:10.2196/76326 · Cited by 21
Metadata
- Authors
- Savage, T., Wang, J., & Shieh, L.
- Venue
- JMIR Medical Informatics
- Publisher
- JMIR Publications Inc.
- Published
- 2023-11-27
- Volume
- 11
- Pages
- e49886
- ISSN
- 2291-9694 (ISSN-L)
- OpenAlex
- W4387914853
- Cited by
- 30
- References
- 3
- FWCI
- 2.64
- Type
- journal article
- Language
- en
- Open access
- gold
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.