Utilization of an integrated artificial intelligence system in the diagnosis of acute ischemic strokes and intracranial hemorrhages: а retrospective study

Introduction: Acute cerebrovascular accidents (CVA), including ischemic stroke and intracranial hemorrhage, remain among the leading causes of mortality and long-term disability worldwide. The substantial workload placed on radiologists, combined with the necessity for prompt decision-making under time pressure, underscores the importance of integrating artificial intelligence (AI) technologies into the diagnostic process.

Objectives: To assess the diagnostic performance of an artificial intelligence model developed for the detection of acute ischemic stroke and intracranial hemorrhage on non-contrast brain computed tomography (CT).

Materials and Methods: This paper represents the results of a retrospective study. The test dataset comprised 263 anonymized non-contrast brain CT examinations of patients aged over 18 years, performed under clinical suspicion of acute cerebrovascular accident. Ground truth was established by two independent radiologists. The performance of the AI model was evaluated against the ground truth dataset using sensitivity, specificity, accuracy, and ROC AUC metrics. In addition, the accuracy of lesion localization and segmentation was analyzed.

Results: For ischemic stroke detection, the AI model achieved a sensitivity of 0.85, specificity of 0.82, and overall accuracy of 0.83 (ROC AUC=0.84). For intracranial hemorrhage detection, sensitivity was 0.82, specificity 0.81, and accuracy 0.81 (ROC AUC=0.81). Agreement between radiologists and the model’s proposed lesion contours was observed in 94.2% of cases, while concordance on lesion volume estimation reached 95.7%.

Discussion: The findings demonstrate that the AI model provides high diagnostic accuracy and may serve as a valuable tool for clinical decision-making. Nonetheless, the limited positive predictive value highlights the necessity of employing the model in conjunction with clinical context and expert interpretation.

Conclusion: The «Brain CT” AI model demonstrated strong potential for automated detection of ischemic stroke and intracranial hemorrhage. Its implementation could contribute to reducing the workload of radiologists and improving diagnostic accuracy in routine practice, contingent upon further validation and model retraining on larger and more diverse datasets.

1. Ignatieva V.I., Voznyuk I.A., Shamalov N.A., Reznik A.V., Vinitsky A.A., Derkach E.V. Socio-economic burden of stroke in the Russian Federation. S. S. Korsakov Journal of Neurology and Psychiatry, 2023, Vol. 123, No. 8 (Issue 2), рр. 5–15 (In Russ.). doi: 10.17116/jnevro20231230825.

2. Campbell B.C.V., Lansberg M.G., Broderick J.P., Derdeyn C.P., Khatri P., Sarraj A., Saver J.L., Vagal A., Albers G.W. Acute Stroke Imaging Research Roadmap IV: Imaging Selection and Outcomes in Acute Stroke Clinical Trials and Practice // Stroke. 2021. Vol. 52, No. 8. P. 2723–2733 doi: 10.1161/STROKEAHA.121.035132.

3. European Society of Radiology (ESR), A. P. Brady, P. Graciano, B. Brkljacic, C. Loewe, M. Szucsich, M. Hierath. The future of radiology in Europe under increasing workload and staff shortages: a survey from the European Society of Radiology (ESR) // Insights into Imaging. 2025. Vol. 16. Art. No. 19. P. 1–10. doi: 10.1186/s13244-025-01925-7.

4. Andropova P.L., Gavrilov P.V., Savintseva Zh.I. ASPECTS scale: Inter-expert agreement in usage. Diagnostic radiology and radiotherapy, 2022, Vol. 13, No. 1, рр. 21–27 (In Russ.). doi: 10.22328/2079-5343-2022-13-1-7-13.

5. Andropova P.L., Gavrilov P.V., Savintseva Zh.I., Vovk A.V., Rybin E.V. Application of artificial intelligence systems in neuroimaging of acute ischemic stroke. Diagnostic radiology and radiotherapy, 2021, Vol. 12, No. 2, рр. 30–36 (In Russ.). doi: 10.22328/2079-5343-2021-12-2-30-36.

6. Powers W.J., Rabinstein A.A., Ackerson T. et al. Guidelines for the Early Management of Patients With Acute Ischemic Stroke: 2019 Update to the 2018 Guidelines for the Early Management of Acute Ischemic Stroke // Stroke. 2019. Vol. 50. P. e344–e418. doi: 10.1161/STR.0000000000000211.

7. Shcheglova L.V., Savinova A.V., Kamyshanskaya I.G., Kharitonov N.Yu., Rubleva O.V. Use of artificial intelligence in the diagnosis of acute cerebrovascular accidents (literature review). Medicine: Theory and Practice, 2023, Vol. 8, No. 4, рр. 272–278 (In Russ.). doi: 10.35478/MTP.2023.4.07.

8. Soun J.E., Chow D.S., Nagamine M., Takhtawala R.S., Filippi C.G., Yu W., Chang P.D. Artificial Intelligence and Acute Stroke Imaging // American Journal of Neuroradiology. 2021. Vol. 42, No. 1. P. 2–11. doi: 10.3174/ajnr.A6897.

9. Wang Z., Yang W., Li Z., Rong Z., Wang X., Han J., Ma L. A 25-Year Retrospective of the Use of AI for Diagnosing Acute Stroke: Systematic Review // Journal of Medical Internet Research. 2024. Vol. 26. e51234. doi: 10.2196/51234.

10. Larentzakis A., Lygeros N. Artificial intelligence (AI) in medicine as a strategic valuable tool // Pan African Medical Journal. 2021. Vol. 38. P. 244. doi: 10.11604/pamj.2021.38.244.25354.