AI-Powered Stroke Diagnosis System: Methodological Framework and Implementation
This study introduces an AI-based framework for stroke diagnosis that merges clinical data and curated imaging data. The system utilizes traditional machine learning and advanced deep learning techniques to tackle dataset imbalances and variability in stroke presentations. Our approach involves rigo...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/17/5/204 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850257069402226688 |
|---|---|
| author | Marta Narigina Agris Vindecs Dušanka Bošković Yuri Merkuryev Andrejs Romanovs |
| author_facet | Marta Narigina Agris Vindecs Dušanka Bošković Yuri Merkuryev Andrejs Romanovs |
| author_sort | Marta Narigina |
| collection | DOAJ |
| description | This study introduces an AI-based framework for stroke diagnosis that merges clinical data and curated imaging data. The system utilizes traditional machine learning and advanced deep learning techniques to tackle dataset imbalances and variability in stroke presentations. Our approach involves rigorous data preprocessing, feature engineering, and ensemble techniques to optimize the predictive performance. Comprehensive evaluations demonstrate that gradient-boosted models outperform in accuracy, while CNNs enhance stroke detection rates. Calibration and threshold optimization are utilized to align predictions with clinical requirements, ensuring diagnostic reliability. This multi-modal framework highlights the capacity of AI to accelerate stroke diagnosis and aid clinical decision making, ultimately enhancing patient outcomes in critical care. |
| format | Article |
| id | doaj-art-2731ea49947849f5aa2b9a1b00a35502 |
| institution | OA Journals |
| issn | 1999-5903 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj-art-2731ea49947849f5aa2b9a1b00a355022025-08-20T01:56:31ZengMDPI AGFuture Internet1999-59032025-05-0117520410.3390/fi17050204AI-Powered Stroke Diagnosis System: Methodological Framework and ImplementationMarta Narigina0Agris Vindecs1Dušanka Bošković2Yuri Merkuryev3Andrejs Romanovs4Institute of Information Technology, Riga Technical University, 6A Kipsalas Street, LV-1048 Riga, LatviaInstitute of Information Technology, Riga Technical University, 6A Kipsalas Street, LV-1048 Riga, LatviaFaculty of Electrical Engineering, University of Sarajevo, Zmaja od Bosne bb, 71000 Sarajevo, Bosnia and HerzegovinaInstitute of Information Technology, Riga Technical University, 6A Kipsalas Street, LV-1048 Riga, LatviaInstitute of Information Technology, Riga Technical University, 6A Kipsalas Street, LV-1048 Riga, LatviaThis study introduces an AI-based framework for stroke diagnosis that merges clinical data and curated imaging data. The system utilizes traditional machine learning and advanced deep learning techniques to tackle dataset imbalances and variability in stroke presentations. Our approach involves rigorous data preprocessing, feature engineering, and ensemble techniques to optimize the predictive performance. Comprehensive evaluations demonstrate that gradient-boosted models outperform in accuracy, while CNNs enhance stroke detection rates. Calibration and threshold optimization are utilized to align predictions with clinical requirements, ensuring diagnostic reliability. This multi-modal framework highlights the capacity of AI to accelerate stroke diagnosis and aid clinical decision making, ultimately enhancing patient outcomes in critical care.https://www.mdpi.com/1999-5903/17/5/204stroke diagnosiseICU databasemachine learningdeep learningconvolutional neural networksensemble methods |
| spellingShingle | Marta Narigina Agris Vindecs Dušanka Bošković Yuri Merkuryev Andrejs Romanovs AI-Powered Stroke Diagnosis System: Methodological Framework and Implementation Future Internet stroke diagnosis eICU database machine learning deep learning convolutional neural networks ensemble methods |
| title | AI-Powered Stroke Diagnosis System: Methodological Framework and Implementation |
| title_full | AI-Powered Stroke Diagnosis System: Methodological Framework and Implementation |
| title_fullStr | AI-Powered Stroke Diagnosis System: Methodological Framework and Implementation |
| title_full_unstemmed | AI-Powered Stroke Diagnosis System: Methodological Framework and Implementation |
| title_short | AI-Powered Stroke Diagnosis System: Methodological Framework and Implementation |
| title_sort | ai powered stroke diagnosis system methodological framework and implementation |
| topic | stroke diagnosis eICU database machine learning deep learning convolutional neural networks ensemble methods |
| url | https://www.mdpi.com/1999-5903/17/5/204 |
| work_keys_str_mv | AT martanarigina aipoweredstrokediagnosissystemmethodologicalframeworkandimplementation AT agrisvindecs aipoweredstrokediagnosissystemmethodologicalframeworkandimplementation AT dusankaboskovic aipoweredstrokediagnosissystemmethodologicalframeworkandimplementation AT yurimerkuryev aipoweredstrokediagnosissystemmethodologicalframeworkandimplementation AT andrejsromanovs aipoweredstrokediagnosissystemmethodologicalframeworkandimplementation |