AI post-intervention operational and functional outcomes prediction in ischemic stroke patients using MRIs
Abstract Background Despite the potential clinical utility for acute ischemic stroke patients, predicting short-term operational outcomes like length of stay (LOS) and long-term functional outcomes such as the 90-day Modified Rankin Scale (mRS) remain a challenge, with limited current clinical guida...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-08-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-025-01864-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849341981410459648 |
|---|---|
| author | Emily Wittrup John Reavey-Cantwell Aditya S. Pandey Dennis J. Rivet II Kayvan Najarian |
| author_facet | Emily Wittrup John Reavey-Cantwell Aditya S. Pandey Dennis J. Rivet II Kayvan Najarian |
| author_sort | Emily Wittrup |
| collection | DOAJ |
| description | Abstract Background Despite the potential clinical utility for acute ischemic stroke patients, predicting short-term operational outcomes like length of stay (LOS) and long-term functional outcomes such as the 90-day Modified Rankin Scale (mRS) remain a challenge, with limited current clinical guidance on expected patient trajectories. Machine learning approaches have increasingly aimed to bridge this gap, often utilizing admission-based clinical features; yet, the integration of imaging biomarkers remains underexplored, especially regarding whole 2.5D image fusion using advanced deep learning techniques. Methods This study introduces a novel method leveraging autoencoders to integrate 2.5D diffusion weighted imaging (DWI) with clinical features for refined outcome prediction. Results Results on a comprehensive dataset of AIS patients demonstrate that our autoencoder-based method has comparable performance to traditional convolutional neural networks image fusion methods and clinical data alone (LOS $$ > $$ 8 days: AUC 0.817, AUPRC 0.573, F1-Score 0.552; 90-day mRS $$>$$ 2: AUC 0.754, AUPRC 0.685, F1-Score 0.626). Conclusion This novel integration of imaging and clinical data for post-intervention stroke prognosis has numerous computational and operational advantages over traditional image fusion methods. While further validation of the presented models is necessary before adoption, this approach aims to enhance personalized patient management and operational decision-making in healthcare settings. Clinical trial number Not applicable. |
| format | Article |
| id | doaj-art-3b48b07e5f2b42acbc12d5775be02805 |
| institution | Kabale University |
| issn | 1471-2342 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj-art-3b48b07e5f2b42acbc12d5775be028052025-08-20T03:43:31ZengBMCBMC Medical Imaging1471-23422025-08-0125111210.1186/s12880-025-01864-1AI post-intervention operational and functional outcomes prediction in ischemic stroke patients using MRIsEmily Wittrup0John Reavey-Cantwell1Aditya S. Pandey2Dennis J. Rivet II3Kayvan Najarian4Gilbert S. Omenn Computational Medicine and Bioinformatics, University of MichiganDepartment of Neurosurgery, Virginia Commonwealth UniversityDepartment of Neurosurgery, Michigan MedicineDepartment of Neurosurgery, Virginia Commonwealth UniversityGilbert S. Omenn Computational Medicine and Bioinformatics, University of MichiganAbstract Background Despite the potential clinical utility for acute ischemic stroke patients, predicting short-term operational outcomes like length of stay (LOS) and long-term functional outcomes such as the 90-day Modified Rankin Scale (mRS) remain a challenge, with limited current clinical guidance on expected patient trajectories. Machine learning approaches have increasingly aimed to bridge this gap, often utilizing admission-based clinical features; yet, the integration of imaging biomarkers remains underexplored, especially regarding whole 2.5D image fusion using advanced deep learning techniques. Methods This study introduces a novel method leveraging autoencoders to integrate 2.5D diffusion weighted imaging (DWI) with clinical features for refined outcome prediction. Results Results on a comprehensive dataset of AIS patients demonstrate that our autoencoder-based method has comparable performance to traditional convolutional neural networks image fusion methods and clinical data alone (LOS $$ > $$ 8 days: AUC 0.817, AUPRC 0.573, F1-Score 0.552; 90-day mRS $$>$$ 2: AUC 0.754, AUPRC 0.685, F1-Score 0.626). Conclusion This novel integration of imaging and clinical data for post-intervention stroke prognosis has numerous computational and operational advantages over traditional image fusion methods. While further validation of the presented models is necessary before adoption, this approach aims to enhance personalized patient management and operational decision-making in healthcare settings. Clinical trial number Not applicable.https://doi.org/10.1186/s12880-025-01864-1Acute ischemic strokeResnetAutoencoderDeep learningArtificial intelligenceMRI |
| spellingShingle | Emily Wittrup John Reavey-Cantwell Aditya S. Pandey Dennis J. Rivet II Kayvan Najarian AI post-intervention operational and functional outcomes prediction in ischemic stroke patients using MRIs BMC Medical Imaging Acute ischemic stroke Resnet Autoencoder Deep learning Artificial intelligence MRI |
| title | AI post-intervention operational and functional outcomes prediction in ischemic stroke patients using MRIs |
| title_full | AI post-intervention operational and functional outcomes prediction in ischemic stroke patients using MRIs |
| title_fullStr | AI post-intervention operational and functional outcomes prediction in ischemic stroke patients using MRIs |
| title_full_unstemmed | AI post-intervention operational and functional outcomes prediction in ischemic stroke patients using MRIs |
| title_short | AI post-intervention operational and functional outcomes prediction in ischemic stroke patients using MRIs |
| title_sort | ai post intervention operational and functional outcomes prediction in ischemic stroke patients using mris |
| topic | Acute ischemic stroke Resnet Autoencoder Deep learning Artificial intelligence MRI |
| url | https://doi.org/10.1186/s12880-025-01864-1 |
| work_keys_str_mv | AT emilywittrup aipostinterventionoperationalandfunctionaloutcomespredictioninischemicstrokepatientsusingmris AT johnreaveycantwell aipostinterventionoperationalandfunctionaloutcomespredictioninischemicstrokepatientsusingmris AT adityaspandey aipostinterventionoperationalandfunctionaloutcomespredictioninischemicstrokepatientsusingmris AT dennisjrivetii aipostinterventionoperationalandfunctionaloutcomespredictioninischemicstrokepatientsusingmris AT kayvannajarian aipostinterventionoperationalandfunctionaloutcomespredictioninischemicstrokepatientsusingmris |