LLM-Based Framework for Administrative Task Automation in Healthcare
The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
Artificial Intelligence (AI) has been transformative in the healthcare sector, leading to enhanced precision in medical diagnosis, more effective treatment options, and a significant improvement in patient safety. However, computer-based administrative tasks, such as retrieval of medical and health records, patient registration, medical billing, filing and documentation, and appointment scheduling, still impose a heavy burden on healthcare professionals, causing a reduced quality of care and efficiency. In light of these challenges, this paper proposes a large language model (LLM)-based multi-agent framework designed to automate some of the administrative work in clinical settings. In our proposed solution, these LLM agents coordinate to parse instructions, breakdown tasks, and execute a sequence of actions in a workflow. They are equipped to not only execute documentation process at the database level but also operate directly on web-based electronic medical record (EMR) platforms. Moreover, the framework integrates data sources through a retrieval-augmented generation (RAG) system to allow streamlined interaction with patient information and medical records, mediated through an agent interface. The framework is designed with security in mind to defend against malicious prompts. We demonstrate the practicality of our solution by testing on various complex tasks that require the use of multiple tools and an EMR website. The result show the framework's effectiveness in handling diverse healthcare administrative tasks.
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
Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., Maningo, J., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000198 · Cited by 4,115 · cited 1×
“5 model, was evaluated on its ability to handle complex medical information considering United States Medical Licensing (USMLE) exam and it was able to achieve a score close to the passing threshold without any prompting [8].”
MethodKung, T. H., Cheatham, M., ChatGPT, Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., et al. (2022) · doi:10.1101/2022.12.19.22283643 · Cited by 4,115
Large Language Models Encode Clinical Knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.13138 · Cited by 4,083
Large language models encode clinical knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2023) · Nature · doi:10.1038/s41586-023-06291-2 · Cited by 4,083 · cited 1×
“Med-PaLM [10] and Med-PaLM 2 [11] are two fine-tuned versions of the Flan-Palm model by Google.”
MethodMetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Zhang, C., Wang, J., Wang, Z., Yau, S. K. S., Lin, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.00352 · Cited by 2,825 · cited 1×
“In contrast the potential of LLMs to power autonomous task-performing agents has been evident through projects such as AutoGPT [3], MetaGPT [4] and AutoGen [5].”
BackgroundToward expert-level medical question answering with large language models
Singhal, K., Tu, T., Gottweis, J., Sayres, R., Wulczyn, E., Amin, M., Hou, L., Clark, K., Pfohl, S. R., Cole-Lewis, H., et al. (2025) · Nature Medicine · doi:10.1038/s41591-024-03423-7 · Cited by 1,734
BioGPT: generative pre-trained transformer for biomedical text generation and mining
Luo, R., Sun, L., Xia, Y., Qin, T., Zhang, S., Poon, H., & Liu, T.-Y. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac409 · Cited by 1,150
The Rise and Potential of Large Language Model Based Agents: A Survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.07864 · Cited by 972 · cited 1×
“There have been numerous projects, like AutoGen, AutoGPT, and ProAgent, developed recently, that move in this direction, where agents exhibit a think-before-you-act behaviour to define goals and perform actions [17].”
BackgroundThe rise and potential of large language model based agents: a survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4222-0 · Cited by 970
Li, Y., Li, Z., Zhang, K., Dan, R., Jiang, S., & Zhang, Y. (2023) · arXiv · doi:10.48550/arxiv.2303.14070 · Cited by 512
Research works printed but not linked: 11
- Toscano, 2020, How physicians spend their work time: an ecological momentary assessment, Journal of General Internal Medicine, 35, 3166, 10.1007/s11606-020-06087-4 · DOI
- 10.1016/j.ajem.2013.06.028 · DOI · Paper page
- 2023, ChatGPT [large language model]
- Achiam, 2023, Gpt-4 technical report
- 10.7759/cureus.40895 · DOI · Paper page
- Han, 2023, Medalpaca - an open-source collection of medical conversational ai models and training data
- Xu, 2023, Elixr: Towards a general purpose x-ray artificial intelligence system through alignment of large language models and radiology vision encoders, arXiv
- 10.1007/978-3-031-47679-2_7 · DOI
- Yao, ReAct: Synergizing reasoning and acting in language models
- Gur, 2023, A real-world webagent with planning, long context understanding, and program synthesis, arXiv
- Hippocrate medical software
Cited by
The Importance of AI Data Governance in Large Language Models
(2025) · doi:10.3390/bdcc9060147 · Cited by 58
The Importance of AI Data Governance in Large Language Models
Pahune, S., Akhtar, Z., Mandapati, V., & Siddique, K. (2025) · doi:10.20944/preprints202504.0219.v1 · Cited by 58
ENTAgents: AI Agents for Complex Knowledge Otolaryngology
Chan, T. K., & Dinh, N.-D. (2025) · doi:10.1101/2025.01.01.25319863 · Cited by 9
Sun, D., Hadjiiski, L., Bruno, G., Gormley, J., Chan, H.-P., Caoili, E. M., Cohan, R. H., Alva, A., Mihalcea, R., Zhou, C., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-27593-7 · Cited by 9
Mugambiwa, T., & Ndlovu, B. (2026) · Journal of Applied Informatics and Computing · doi:10.30871/jaic.v10i1.11900 · Cited by 4
“The retrieval, reasoning, and verification integrated together within coordinated agents, the system would be able to manage heterogeneous tasks such as guideline interpretation, summarisation, and differential diagnosis, all within a single framework[27].”
Metadata
- Authors
- Gebreab, S. A., Salah, K., Jayaraman, R., Habib ur Rehman, M., & Ellaham, S.
- Venue
- 2024 12th International Symposium on Digital Forensics and Security (ISDFS)
- Publisher
- IEEE
- Published
- 2024-04-29
- Pages
- 1-7
- OpenAlex
- W4396918564
- Cited by
- 53
- References
- 21
- FWCI
- 14.88
- Type
- conference paper
- Language
- en
- Open access
- closed
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: LLM-Based Framework for Administrative Task Automation in Healthcare. https://app.cochat.ai/papers/10.1109/isdfs60797.2024.10527275
- The paper
- Gebreab, S. A., Salah, K., Jayaraman, R., Habib ur Rehman, M., & Ellaham, S. (2024). LLM-Based Framework for Administrative Task Automation in Healthcare. 2024 12th International Symposium on Digital Forensics and Security (ISDFS). https://doi.org/10.1109/isdfs60797.2024.10527275
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.