СИСТЕМА ШТУЧНОГО ІНТЕЛЕКТУ ДЛЯ СТРУКТУРНО-КОНТЕКСТНОЇ ВАЛІДАЦІЇ ЛІКАРСЬКИХ ПРИЗНАЧЕНЬ З ОЦІНЮВАННЯМ РИЗИКІВ ПОЛІФАРМАЦІЇ
DOI:
https://doi.org/10.11603/2312-0967.2026.2.16186Keywords:
polypharmacy, polymorbidity, artificial intelligence, large language models, retrieval-augmented generation, clinical decision support, HL7 FHIR, pharmaceutical safetyAbstract
Objective. The study aimed to substantiate architectural and methodological approaches to developing an integrated hardware–software complex (HSC) for automated structurally contextual validation of medication orders with detection of polypharmacy risks and generation of evidence-based recommendations using retrieval-augmented generation (RAG) and large language models (LLMs), aligned with interoperability requirements of modern health information infrastructures.
Materials and methods. The investigation combined literature analysis and synthesis, systems and comparative analysis of CDSS and patent documents, generalization, conceptual and simulation modeling, algorithm design and object-oriented programming of a prototype, expert evaluation on synthetic scenarios, and statistical methods for agreement testing (e.g., Cohen’s κ) planned for future empirical extensions. The information base included international publications, HL7 FHIR specifications, national eHealth regulations, patent databases, and clinical guidelines as knowledge sources, without identifiable patient records.
Results. The study produced a modular HSC concept with a three-stage pipeline (Constraints → validation with issues[] and polypharmacy_risks[] → CorrectionPlan), RAG-augmented LLM reasoning, and multi-model validation (N≥2). Scientific novelty combines explicit polypharmacy risk taxonomy, separated prescription issues vs polypharmacy risks, and explainable outputs. Practical value lies in FHIR/REST-based integration with hospital and pharmacy systems and national eHealth services; limitations include scenario-based evaluation and the need for prospective real-world validation under privacy rules.
Conclusions. The proposed HSC can serve as a foundation for next-generation clinical decision support in hospital and pharmacy information systems and national eHealth services. Future work should prioritize prospective clinical trials measuring medication safety endpoints and implementation outcomes.
References
Masnoon N, Shakib S, Kalisch-Ellett L, Caughey GE. What is polypharmacy? A systematic review of definitions. BMC Geriatr. 2017;17(1):230. doi:10.1186/s12877-017-0621-2. Available from: https://doi.org/10.1186/s12877-017-0621-2 DOI: https://doi.org/10.1186/s12877-017-0621-2
Davies LE, Spiers G, Kingston A, Todd A, Adamson J, Hanratty B. Adverse outcomes of polypharmacy in older people: systematic review of reviews. J Am Med Dir Assoc. 2020;21(2):181-187. DOI: 10.1016/j.jamda.2019.10.022. DOI: https://doi.org/10.1016/j.jamda.2019.10.022
Khezrian M, McNeil CJ, Murray AD, Myint PK. An overview of prevalence, determinants and health outcomes of polypharmacy. Ther Adv Drug Saf. 2020;11:2042098620933741. DOI: 10.1177/2042098620933741. DOI: https://doi.org/10.1177/2042098620933741
Opondo D, Eslami S, Visscher S, et al. Inappropriateness of medication prescriptions to elderly patients in the primary care setting: a systematic review. PLoS One. 2012;7(8):e43617. DOI: 10.1371/journal.pone.0043617. DOI: https://doi.org/10.1371/journal.pone.0043617
Maher RL, Hanlon J, Hajjar ER. Clinical consequences of polypharmacy in elderly. Expert Opin Drug Saf. 2014;13(1):57-65. DOI: 10.1517/14740338.2013.827596. DOI: https://doi.org/10.1517/14740338.2013.827660
Black CD, Thavorn K, Coyle D, et al. The health system costs of potentially inappropriate prescribing: a population-based, retrospective cohort study using linked health administrative databases in Ontario, Canada. PharmacoEconomics Open. 2020;4:27-36. DOI: 10.1007/s41669-019-0143-2. DOI: https://doi.org/10.1007/s41669-019-0143-2
Sutton RT, Pincock D, Baumgart DC, Sadowski DC, Fedorak RN, Kroeker KI. An overview of clinical decision support systems: benefits, risks, and strategies for success. NPJ Digit Med. 2020;3:17. DOI:10.1038/s41746-020-0221-y. DOI: https://doi.org/10.1038/s41746-020-0221-y
Shahmoradi L, Safdari R, Ahmadi H, Zahmatkeshan M. Clinical decision support systems-based interventions to improve medication outcomes: a systematic literature review on features and effects. Med J Islam Repub Iran. 2021;35:27. DOI: 10.47176/mjiri.35.27. DOI: https://doi.org/10.47176/mjiri.35.27
Westerbeek L, Ploegmakers KJ, de Bruijn GJ, et al. Barriers and facilitators influencing medication-related CDSS acceptance according to clinicians: a systematic review. Int J Med Inform. 2021;152:104506. DOI: 10.1016/j.ijmedinf.2021.104506. DOI: https://doi.org/10.1016/j.ijmedinf.2021.104506
Wang Y, Wang L, Rastegar-Mojarad M, et al. Clinical information extraction applications: a literature review. J Biomed Inform. 2018;77:34-49. DOI: 10.1016/j.jbi.2017.11.007. DOI: https://doi.org/10.1016/j.jbi.2017.11.011
Lewis P, Perez E, Piktus A, et al. Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv Neural Inf Process Syst. 2020;33:9459-9474. Available from: https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html
Singhal K, Azizi S, Tu T, et al. Large language models encode clinical knowledge. Nature. 2023;620:172-180. DOI: 10.1038/s41586-023-06291-2. DOI: https://doi.org/10.1038/s41586-023-06291-2
HL7 International. HL7 FHIR Release 5.0.0 [Internet]. 2023 [cited 2026 Apr 1]. Available from: https://hl7.org/fhir/
Malakhov KS. Insight into the digital health system of Ukraine (eHealth): trends, definitions, standards, and legislative revisions. Int J Telerehabil. 2023;15(2):e6599. DOI: 10.5195/ijt.2023.6599. DOI: https://doi.org/10.5195/ijt.2023.6599
Google Patents. US20240139779A1. Intelligent prescription validation system [Internet]. 2024 [cited 2026 Apr 1]. Available from: https://patents.google.com/patent/US20240139779A1/en
Google Patents. US11183285B2. Systems and methods for medication risk assessment [Internet]. 2021 [cited 2026 Apr 1]. Available from: https://patents.google.com/patent/US11183285B2/en
Google Patents. US12142371B2. Clinical decision support using knowledge graphs [Internet]. 2024 [cited 2026 Apr 1]. Available from: https://patents.google.com/patent/US12142371B2/en
World Medical Association. WMA Declaration of Helsinki: ethical principles for medical research involving human subjects [Internet]. 2013, amended 2024 [cited 2026 Apr 1]. Available from: https://www.wma.net/policies-post/wma-declaration-of-helsinki/
Verkhovna Rada of Ukraine. Law of Ukraine On Personal Data Protection No. 2297-VI [Internet]. 2010 [cited 2026 Apr 1]. Available from: https://zakon.rada.gov.ua/laws/show/2297-17#Text
Zapf A, Castell S, Morawietz L, Karch A. Measuring inter-rater reliability for nominal data: which coefficients and confidence intervals are appropriate? BMC Med Res Methodol. 2016;16:93. DOI: 10.1186/s12874-016-0200-9. DOI: https://doi.org/10.1186/s12874-016-0200-9
Amugongo LM, Mascheroni P, Brooks S, Doering S, Seidel J. Retrieval augmented generation for large language models in healthcare: a systematic review. PLOS Digit Health. 2025;4(6):e0000877. DOI: 10.1371/journal.pdig.0000877. DOI: https://doi.org/10.1371/journal.pdig.0000877
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors who publish their materials in this journal agree with the following terms:
- Authors reserve the right to authorship of their work and assign to the journal the right to first publish this work under the terms of the Creative Commons Attribution License, which allows other persons to freely distribute the published work with a mandatory reference to the authors of original work and the first publication of work in this journal
. - Authors have the right to make independent extra-exclusive work agreements in the form they are published by this journal (for example, posting work in an electronic repository of an institution or publishing as part of a monograph), provided that the link to the first publication of the work in this journal is maintained.
Journal policy allows and encourages publication of manuscripts on the Internet (for example, in institutions repositories or on personal websites), both before the publication of this manuscript and during its editorial review, as it contributes to productive scientific discussion and positively affects the efficiency and dynamics of the citation of the published work (see The Effect of Open Access).
