Interactive platform for supporting clinical decision-making using large language models (LLMs)
DOI:
https://doi.org/10.30837/2522-9818.2026.2.173Keywords:
clinical decision support; large language models; fine-tuning; LoRA; symptom-based diagnosis; medical AIAbstract
Current healthcare systems face increasing workload, fragmented communication, and documentation burden, which contributes to delays and diagnostic errors in early triage. The proposed solution is intended to improve consistency, speed, and standardization in early patient assessments overall. This study presents an interactive clinical decision support platform that operationalizes a workflow-constrained, two-step history-taking process to support symptom-based differential diagnosis in the pre-ambulatory phase of care. The system addresses three tasks: (T1) automated patient history elicitation via constrained dialogue (exactly two multiple-choice follow-up questions), (T2) formalization of symptom narratives into structured medical (Latinate) terminology for clinician-facing documentation, and (T3) generation of differential diagnosis recommendations under a fixed and clinically interpretable output schema. We compare a generic large language model baseline (GPT-4, zero-shot) with a domain-adapted model (Llama-3 fine-tuned using LoRA) under identical interaction, prompting, and formatting constraints. Experiments on 903 symptom–diagnosis records and a held-out set of 200 controlled vignettes show that domain adaptation yields a 10–12% macro-F1 improvement and approximately 15% higher Recall on complex cases, while producing more clinically discriminative and diagnostically relevant follow-up questions as assessed by two medical raters . In a workflow-level evaluation, the platform reduced documentation time by 28% compared to standard intake and lowered the administrative effort required to prepare an initial clinician-facing summary for physician review. These results suggest that specialized, locally deployable fine-tuned models, combined with bounded interaction design, standardized output constraints, and workflow-oriented system integration, provide a secure, practical, and effective pathway for incorporating LLM-based decision support into routine pre-ambulatory clinical workflows while preserving safety, usability, and auditability in practice.Downloads
References
References
World Health Organization (2016), "Global strategy on human resources for health: Workforce 2030", Geneva: WHO, 64 p., available at: https://iris.who.int/handle/10665/250368
Zaitseva, E., Levashenko, V., Rabcan, J., Krsak, E. (2020), "Application of the structure function in the evaluation of the human factor in healthcare", Symmetry, Vol.12(1), 93 р. DOI: https://doi.org/10.3390/SYM12010093
Shanafelt, T. D. et al. (2010), "Burnout and medical errors among American surgeons", Annals of Surgery, Vol. 251(6), pp. 995-1000. DOI: https://doi.org/10.1097/SLA.0b013e3181bfdab3
Zaitseva, E., Levashenko, V. (2026), "Reliability engineering in healthcare: Opportunities and challenges", Reliability Engineering and System Safety, Vol. 267, 111933 р. DOI: https://doi.org/10.1016/j.ress.2025.111933
Zaitseva, E., Levashenko, V. (2025), "Reliability Analysis Based on Aleatory and Epistemic Uncertainty Using Binary Decision Diagrams", International Journal of Intelligent Systems, Vol. 1, 6471577 р. DOI: 10.1155/int/6471577
Sutton, R. T. et al. (2020), "An overview of clinical decision support systems: benefits, risks, and strategies for success", NPJ Digital Medicine, Vol. 3(17), pp. 1-10. DOI: https://doi.org/10.1038/s41746-020-0221-y
Chambers, D., Cantrell, A. J., Johnson, M. et al. (2019), "Digital and online symptom checkers and health assessment/triage services for urgent health problems: systematic review", BMJ Open, Vol. 9(8): e027743. DOI: https://doi.org/10.1136/bmjopen-2018-027743
Wallace, W., Chan, C., Chidambaram, S. (2022), "The diagnostic and triage accuracy of digital and online symptom checker tools: a systematic review", NPJ Digital Medicine, Vol. 5(1):18. DOI: https://doi.org/10.1038/s41746-022-00667-w
Hajijama, S., Juneja, D., Nasa, P. (2024), "Large Language Model in Critical Care Medicine: Opportunities and Challenges", Indian Journal of Critical Care Medicine, Vol. 28(6), pp. 523–525. DOI: https://doi.org/10.5005/jp-journals-10071-24743
Asgari, E., Montaña-Brown, N., Dubois, M., et al. (2025), "A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation", NPJ Digital Medicine, Vol. 8(274). DOI: https://doi.org/10.1038/s41746-025-01670-7
Chen, X., Xiang, J., Lu, S., Liu, Y., He, M., Shi, D. (2025), "Evaluating large language models and agents in healthcare: key challenges in clinical applications", Intelligent Medicine, Vol. 5(2), pp. 151–163. DOI: https://doi.org/10.1016/j.imed.2025.03.002
Singhal, K., et al. (2023), "Large language models encode clinical knowledge", Nature, Vol. 620, pp. 172-180. DOI: https://doi.org/10.1038/s41586-023-06291-2
Wang, G. et al. (2023), "ClinicalGPT: Large Language Models Finetuned with Diverse Medical Data and Comprehensive Evaluation", CC BY 4.0. DOI: https://doi.org/10.48550/arXiv.2306.09968
Tran, H. et al. (2024), "BioInstruct: instruction tuning of large language models for biomedical natural language processing", Journal of the American Medical Informatics Association (JAMIA), Vol. 31(9), pp. 1821–1832. DOI: https://doi.org/10.1093/jamia/ocae122
Hu, E. J. et al. (2021), "LoRA: Low-Rank Adaptation of Large Language Models", arXiv preprint, arXiv:2106.09685. DOI: https://doi.org/10.48550/arXiv.2106.09685
Bender, D., Sartipi, K. (2013), "HL7 FHIR: An Agile and RESTful approach to healthcare information exchange", Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems (CBMS), pp. 326–331. DOI: https://doi.org/10.1109/CBMS.2013.6627810
NIST (2001), "Advanced Encryption Standard (AES), "Federal Information Processing Standards Publication (FIPS PUB)" 197, 38 p. DOI: https://doi.org/10.6028/NIST.FIPS.197-upd1
Dwork, C. (2008), "Differential Privacy: A Survey of Results", Theory and Applications of Models of Computation (TAMC), pp. 1–19. DOI: https://doi.org/10.1007/978-3-540-79228-4_1
Mu, О., Wang, W., Liu, W., et al. (2025), "Multimodal Large Language Model with LoRA Fine-Tuning for Multimodal Sentiment Analysis", ACM Transactions on Intelligent Systems and Technology, Vol. 16, No. 6, 139 р. DOI: https://doi.org/10.1145/3709147
Wei, J., Bosma, M., Zhao, V.Y. et al. (2021), "Finetuned Language Models Are Zero-Shot Learners", ICLR, DOI: https://doi.org/10.48550/arXiv.2109.01652
"GPT-4 Technical Report", Computation and Language, arXiv preprint, 2023. 100 р. DOI: https://doi.org/10.48550/arXiv.2303.08774
"Introducing Llama 3: The most capable openly available LLM to date", Meta AI Blog, 2024, available at: https://ai.meta.com/blog/meta-llama-3
Loshchilov, I., Hutter, F. (2019), "Decoupled Weight Decay Regularization", International Conference on Learning Representations (ICLR), available at: https://openreview.net/forum?id=Bkg6RiCqY7
Semenov, S., Mozhaiev, O., Kuchuk, N., Mozhaiev, M., Tiulieniev, S., Gnusov, Yu., Yevstrat, D.,Chyrva, Y., Kuchuk, H. (2022), "Devising a procedure for defining the general criteria of abnormal behavior of a computer system based on the improved criterion of uniformity of input data samples", Eastern-European Journal of Enterprise Technologies, Vol. 6(4-120), pp. 40–49, DOI: https://doi.org/10.15587/1729-4061.2022.269128
Zaitseva, E., Rabcan, J., Levashenko, V., Kvassay, M. (2023), "Importance analysis of decision-making factors based on fuzzy decision trees", Applied Soft Computing, Vol. 134, 109988 р. DOI: https://doi.org/10.1016/j.asoc.2023.109988
Engeler, J., Stricker, D., Birrenbach, T. et al. (2025), "Designing and validating entrustable professional activities for emergency medicine: a stringent, construct-validity enhancing approach", BMC Medical Education, Vol. 25, 866 р. DOI: https://doi.org/10.1186/s12909-025-07449-4
Raschka, S. (2018), "Model evaluation, model selection, and algorithm selection in machine learning", arXiv preprint. DOI: https://doi.org/10.48550/arXiv.1811.12808
GOLD (2024), "Global Strategy for the Diagnosis, Management, and Prevention of Chronic Obstructive Pulmonary Disease", Global Initiative for Chronic Obstructive Lung Disease, available at: https://goldcopd.org/2024-gold-report/
Dogru-Huzmeli, E., Moore-Vasram, S., Phadke, C. et al. (2025), "Evaluating ChatGPT’s ability to simplify scientific abstracts for clinicians and the public", Scientific Reports, Vol. 15, 33466 р. DOI: https://doi.org/10.1038/s41598-025-11086-8
Gaber, F., Shaik, M., Allega, F. et al. (2025), "Evaluating large language model workflows in clinical decision support for triage and referral and diagnosis", NPJ Digital Medicine, Vol. 8, 263 р. DOI: https://doi.org/10.1038/s41746-025-01684-1
Sox, H. C. et al. (2013), Medical Decision Making, John Wiley & Sons, 328 p. DOI: https://doi.org/10.1002/9781118341544
Gatto, J., Seegmiller, P., Burdick, T. E. et al. (2025), "Follow-up Question Generation For Enhanced Patient-Provider Conversations", Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 25222–25240. DOI: https://doi.org/10.18653/v1/2025.acl-long.1226
Sullivan, G. M., Artino Jr., A. R. (2013), "Analyzing and interpreting data from Likert-type scales", Journal of Graduate Medical Education, Vol. 5(4), pp. 541–542. DOI: https://doi.org/10.4300/JGME-5-4-18
Olson, K. D., Meeker, D., Troup, M. et al. (2025), "Use of Ambient AI Scribes to Reduce Administrative Burden and Professional Burnout", JAMA Network Open, Vol. 8(10):e2534976. DOI: https://doi.org/10.1001/jamanetworkopen.2025.34976
Zaitseva, E., Levashenko, V., Rabcan, J., Kvassay M. (2023), "A New Fuzzy-Based Classification Method for Use in Smart/Precision Medicine", Bioengineering, Vol. 10(7), 838 р. DOI: https://doi.org/10.3390/bioengineering10070838
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Our journal abides by the Creative Commons copyright rights and permissions for open access journals.
Authors who publish with this journal agree to the following terms:
-
Authors hold the copyright without restrictions and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
-
Authors are able to enter into separate, additional contractual arrangements for the non-commercial and non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
-
Authors are permitted and encouraged to post their published work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.
