Medical decision support model for diagnosing and rehabilitating patients with disabilities

Relevance. The goal of rehabilitation is to maximize the restoration of lost functions, reduce disability, and return the patient to an active life in society. The effectiveness of rehabilitation depends on the comprehensiveness, validity, and individualized approach to each patient.

Objective. Rehabilitation aims to maximize the restoration of lost functions, minimize disability, and help patients return to an active life in society.

Methods. System analysis of various sources of rehabilitation knowledge is used to identify and organize cause-andeffect relationships. Ontological knowledge modeling includes a semantic representation structure and a set of ontological agreements that define the reasoning principles when solving current rehabilitation problems. Ontological modeling ensures transparency, verifiability, and interpretability of knowledge.

Results. The semantic model of cause-and-effect relationships in this subject area was constructed, encompassing the interrelationships between observations, diagnostic profiles, and rehabilitation measures. This model considers the combined influence of symptoms, factors, and standard scale ratings on human functioning, linking specific impairments and their severity to elements of the ICF profile, rehabilitation goals, and recovery methods. A consistent set of concept types and their relationships enable the structural and verbal representation of knowledge from two types of sources — clinical guidelines and expert materials.

Conclusions. The novelty of these results in terms of developing methods for constructing and using ontological models lies in the development of a new ontological knowledge model that incorporates a semantic representation structure from the most reliable sources and automatic processing in clinical decision support systems. The proposed ontological model with IACPaaS technology forms a flexible tool for combining heterogeneous data and enabling explainable artificial intelligence, which is critical for medical applications. This allows for the development of intelligent services that enhance rehabilitation quality by standardizing approaches, incorporating best practices, and customizing processes.

1. Bolezn' Sheiermana. Klinicheskie rekomendatsii RF 2024 (In Russ.). Available at: https://diseases.medelement.com/disease/%D0%B1%D0%BE%D0%BB%D0%B5%D0%B7%D0%BD%D1%8C-%D1%88%D0%B5%D0%B9%D0%B5%D1%80%D0%BC%D0%B0%D0%BD%D0%B0-%D0%BA%D1%80-%D1%80%D1%84-2024/18406 (accessed 13.10.2025).

2. Clinical Guidelines. Proximal Femoral Fractures. Year of approval: 2021]. (In Russ.). Available at: https://cr.minzdrav.gov.ru/preview-cr/980_1 (accessed 13.10.2025).

3. Shmonin AA, Maltseva MN, Melnikova EV, Ivanova GE. Basic principles of medical rehabilitation, rehabilitation diagnosis in the ICF categories and rehabilitation plan. Vestnik vosstanovitel`noj mediciny`=Bulletin of Restorative Medicine. 2017;16(2):16-22. (In Russ.).

4. Omeljanovskij VV, Avksent'eva MV, Zhelezniakova IA, et al. Clinical guidelines as a tool for improving the quality of medical care delivery. Onkopediatriya. 2017;4(4):246-259 (In Russ.).] DOI: 10.15690/onco.v4i4.1811.

5. Putilo NV, Malichenko VS. The role of clinical recommendations in organization of medical care support. Problemy` social`noj gigieny`, zdravooxraneniya i istorii mediciny`=Problems of Social Hygiene, Public Health and History of Medicine. 2021;29(2):331-338 (In Russ.). DOI: 10.32687/0869-866X-2021-29-2-331-338.

6. Gordeev MN, Polyaev BB, Ivanova GE, et al. Personality rehabilitation potential in acute cerebrovascular accident patients: factors and drivers of recovery. Fizicheskaya i reabilitacionnaya medicina, medicinskaya reabilitaciya=Physical and rehabilitation medicine, medical rehabilitation. 2024;6(4):369-378 (In Russ.). DOI: 10.36425/rehab636622.

7. Zolotukhina IU., Kasimova AR. Review of data sources used in real-world traumatology and orthopedic. Real-world data & evidence. 2023;3(4):9-14 (In Russ.). DOI: 10.37489/2782-3784-myrwd-42.

8. Karpov OE, Subbotin SA, Shishkanov DV. Medical data usage to create medical decision support systems. Information technologies for the Physician. 2019;(2):11-18 (In Russ.).

9. Stroke in adults: central paresis of the upper limb. Clinical guidelines. ICD10: I60/I61/ I62/I63/I64/I69. Year of approval: 2017 (In Russ.). Available at: https://rehabrus.ru/Docs/2018/02/Insult_u_vzrsl_centr_parez_konech.pdf (accessed 13.10.2025).

10. Shmonin AA, Balandina IN, Balashova IN, et al. Practical Application of Assessment Scales in Medical Rehabilitation. Study Guide. 3d edition. Sankt-Petersburg: Politekhnika, 2024:184. (In Russ.).

11. Galyavich AS, Tereshchenko SN, Uskach TM, et al. Clinical practice guidelines for Chronic heart failure. Russian Journal of Cardiology. 2024;29(11):251-349. (In Russ.). DOI: 10.15829/1560-4071-2024-6162.

12. Gribova VV, Moskalenko PhM, Timchenko VA, Shalfeyeva EA. The IACPaaS Platform for Developing Systems Based on Ontologies: a Decade of Use. Artificial Intelligence and Decision Making. 2022;(4):55-65. (In Russ.). DOI: 10.14357/20718594220406.

13. Bova VV. Conceptual model of knowledge representation in the constructing intelligent information systems. Izvestiya YUFU. Engineering sciences. 2014;7(156):109-117 (In Russ.).

14. Gribova VV, Petryaeva MV, Okun' DB, et al. Database of Medical Terminology and Observations. Copyright certificate no. 2019621179. 2019. (In Russ.).