Validating the Benefit of Combining Imaging and Clinical Data for Ischemic Stroke Outcome Prediction

Zeyad Abouyoussef, Johanna Ospel, Roberto Souza
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:3659-3678, 2026.

Abstract

Endovascular treatment (EVT) has been proven to be a successful treatment for some cases of acute ischemic stroke. However, neuro-radiologists rely on a small set of clinical features to select patients for treatment. This leads to the exclusion of patients who would have benefited from treatment and the inclusion of others who would not have benefited from it. Deep learning has been used to predict stroke outcome from baseline imaging and clinical data, with most studies reporting that combining imaging and clinical data slightly outperforms classical methods (e.g., logistic regression) trained on clinical data only. However, it is not clear how much of this improvement is attributed to the imaging data and whether it is robust to larger and more diverse test sets. We use one of the largest multi-center acute ischemic stroke datasets ($n = 1,105$) to determine whether combining imaging and clinical data outperforms classical methods. We show that combining imaging and clinical data matches the performance of logistic regression ($0.72$ Area Under Receiver Operating Characteristic Curve (AUROC)) when evaluated on a multi-center test set of over $600$ samples. We examine the models’ predictions and weights and find that 1) both methods match each other’s prediction for $78%$ of the samples, and 2) the weights associated with the imaging features are small compared to the clinical ones. This suggests that imaging features extracted from the deep learning model do not contribute to the prediction as much as the clinical ones.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-abouyoussef26a, title = {Validating the Benefit of Combining Imaging and Clinical Data for Ischemic Stroke Outcome Prediction}, author = {Abouyoussef, Zeyad and Ospel, Johanna and Souza, Roberto}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {3659--3678}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/abouyoussef26a/abouyoussef26a.pdf}, url = {https://proceedings.mlr.press/v315/abouyoussef26a.html}, abstract = {Endovascular treatment (EVT) has been proven to be a successful treatment for some cases of acute ischemic stroke. However, neuro-radiologists rely on a small set of clinical features to select patients for treatment. This leads to the exclusion of patients who would have benefited from treatment and the inclusion of others who would not have benefited from it. Deep learning has been used to predict stroke outcome from baseline imaging and clinical data, with most studies reporting that combining imaging and clinical data slightly outperforms classical methods (e.g., logistic regression) trained on clinical data only. However, it is not clear how much of this improvement is attributed to the imaging data and whether it is robust to larger and more diverse test sets. We use one of the largest multi-center acute ischemic stroke datasets ($n = 1,105$) to determine whether combining imaging and clinical data outperforms classical methods. We show that combining imaging and clinical data matches the performance of logistic regression ($0.72$ Area Under Receiver Operating Characteristic Curve (AUROC)) when evaluated on a multi-center test set of over $600$ samples. We examine the models’ predictions and weights and find that 1) both methods match each other’s prediction for $78%$ of the samples, and 2) the weights associated with the imaging features are small compared to the clinical ones. This suggests that imaging features extracted from the deep learning model do not contribute to the prediction as much as the clinical ones.} }
Endnote
%0 Conference Paper %T Validating the Benefit of Combining Imaging and Clinical Data for Ischemic Stroke Outcome Prediction %A Zeyad Abouyoussef %A Johanna Ospel %A Roberto Souza %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-abouyoussef26a %I PMLR %P 3659--3678 %U https://proceedings.mlr.press/v315/abouyoussef26a.html %V 315 %X Endovascular treatment (EVT) has been proven to be a successful treatment for some cases of acute ischemic stroke. However, neuro-radiologists rely on a small set of clinical features to select patients for treatment. This leads to the exclusion of patients who would have benefited from treatment and the inclusion of others who would not have benefited from it. Deep learning has been used to predict stroke outcome from baseline imaging and clinical data, with most studies reporting that combining imaging and clinical data slightly outperforms classical methods (e.g., logistic regression) trained on clinical data only. However, it is not clear how much of this improvement is attributed to the imaging data and whether it is robust to larger and more diverse test sets. We use one of the largest multi-center acute ischemic stroke datasets ($n = 1,105$) to determine whether combining imaging and clinical data outperforms classical methods. We show that combining imaging and clinical data matches the performance of logistic regression ($0.72$ Area Under Receiver Operating Characteristic Curve (AUROC)) when evaluated on a multi-center test set of over $600$ samples. We examine the models’ predictions and weights and find that 1) both methods match each other’s prediction for $78%$ of the samples, and 2) the weights associated with the imaging features are small compared to the clinical ones. This suggests that imaging features extracted from the deep learning model do not contribute to the prediction as much as the clinical ones.
APA
Abouyoussef, Z., Ospel, J. & Souza, R.. (2026). Validating the Benefit of Combining Imaging and Clinical Data for Ischemic Stroke Outcome Prediction. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:3659-3678 Available from https://proceedings.mlr.press/v315/abouyoussef26a.html.

Related Material