Abstract Background and aims To assess and compare health-related quality of life (HRQoL) in patients during the early recovery period after hemorrhagic stroke (HS) developing in the presence of comorbid conditions, using artificial intelligence (AI)-based modeling. Methods 50 patients with hemorrhagic stroke were included. Group I (n = 30) comprised patients with hypertension-related hemorrhagic stroke, while Group II (n = 20) included patients with hemorrhagic stroke and comorbid type 2 diabetes mellitus and hypertension. All patients were evaluated on day 21 after stroke onset using the SF-36 questionnaire. Data were analyzed using an AI-based Random Forest model to assess intergroup differences and identify key determinants of reduced health-related quality of life. Results The Random Forest classification model demonstrated an overall accuracy of 82%, with a sensitivity of 80%, a specificity of 85%. The area under the receiver operating characteristic curve (AUC) was 0.84, indicating good discriminative performance of the model. The SF-36 domains with the greatest impact on HRQoL deterioration were physical functioning (PF) – 0.28, general health (GH) – 0.24, vitality (VT) – 0.19, and mental health (MH) – 0.15. Patients in Group II showed significantly lower scores in these domains compared to Group I, confirming the negative impact of metabolic comorbidity on post-stroke quality of life. Conclusions Integration of SF-36 questionnaire data with AI-based analytical models enables a more precise and comprehensive assessment of health-related quality of life in patients after hemorrhagic stroke. AI-driven approaches represent a promising tool for early identification of high-risk patients, development of individualized rehabilitation strategies, and support of clinical decision-making. Conflict of interest nothing to disclose
Akbaralieva et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: