Hossein Mohammadian Foroushani1, Ali Hamzehloo2, Atul Kumar2, Yasheng Chen2, Laura Heitsch3, Agnieszka Slowik4, Daniel Strbian5, Jin-Moo Lee2, Daniel S Marcus6, Rajat Dhar7. 1. Department of Electrical and Systems Engineering, Washington University in St. Louis, Saint Louis, USA. 2. Department of Neurology, Washington University in St. Louis School of Medicine, 660 S Euclid Avenue, Campus Box 8111, Saint Louis, MO, 63110, USA. 3. Department of Emergency Medicine, Washington University School of Medicine, Washington, USA. 4. Department of Neurology, Jagiellonian University Medical College, Kraków, Poland. 5. Department of Neurology, Helsinki University Hospital, Helsinki, Finland. 6. Department of Radiology, Washington University School of Medicine, Saint Louis, USA. 7. Department of Neurology, Washington University in St. Louis School of Medicine, 660 S Euclid Avenue, Campus Box 8111, Saint Louis, MO, 63110, USA. dharr@wustl.edu.
Abstract
INTRODUCTION: Malignant cerebral edema develops in a small subset of patients with hemispheric strokes, precipitating deterioration and death if decompressive hemicraniectomy (DHC) is not performed in a timely manner. Predicting which stroke patients will develop malignant edema is imprecise based on clinical data alone. Head computed tomography (CT) imaging is often performed at baseline and 24-h. We determined the incremental value of incorporating imaging-derived features from serial CTs to enhance prediction of malignant edema. METHODS: We identified hemispheric stroke patients at three sites with NIHSS ≥ 7 who had baseline as well as 24-h clinical and CT imaging data. We extracted quantitative imaging features from baseline and follow-up CTs, including CSF volume, intracranial reserve (CSF/cranial volume), as well as midline shift (MLS) and infarct-related hypodensity volume. Potentially lethal malignant edema was defined as requiring DHC or dying with MLS over 5-mm. We built machine-learning models using logistic regression first with baseline data and then adding 24-h data including reduction in CSF volume (ΔCSF). Model performance was evaluated with cross-validation using metrics of recall (sensitivity), precision (predictive value), as well as area under receiver-operating-characteristic and precision-recall curves (AUROC, AUPRC). RESULTS: Twenty of 361 patients (6%) died or underwent DHC. Baseline clinical variables alone had recall of 60% with low precision (7%), AUROC 0.59, AUPRC 0.15. Adding baseline intracranial reserve improved recall to 80% and AUROC to 0.82 but precision remained only 16% (AUPRC 0.28). Incorporating ΔCSF improved AUPRC to 0.53 (AUROC 0.91) while all imaging features further improved prediction (recall 90%, precision 38%, AUROC 0.96, AUPRC 0.66). CONCLUSION: Incorporating quantitative CT-based imaging features from baseline and 24-h CT enhances identification of patients with malignant edema needing DHC. Further refinements and external validation of such imaging-based machine-learning models are required.
INTRODUCTION: Malignant cerebral edema develops in a small subset of patients with hemispheric strokes, precipitating deterioration and death if decompressive hemicraniectomy (DHC) is not performed in a timely manner. Predicting which stroke patients will develop malignant edema is imprecise based on clinical data alone. Head computed tomography (CT) imaging is often performed at baseline and 24-h. We determined the incremental value of incorporating imaging-derived features from serial CTs to enhance prediction of malignant edema. METHODS: We identified hemispheric stroke patients at three sites with NIHSS ≥ 7 who had baseline as well as 24-h clinical and CT imaging data. We extracted quantitative imaging features from baseline and follow-up CTs, including CSF volume, intracranial reserve (CSF/cranial volume), as well as midline shift (MLS) and infarct-related hypodensity volume. Potentially lethal malignant edema was defined as requiring DHC or dying with MLS over 5-mm. We built machine-learning models using logistic regression first with baseline data and then adding 24-h data including reduction in CSF volume (ΔCSF). Model performance was evaluated with cross-validation using metrics of recall (sensitivity), precision (predictive value), as well as area under receiver-operating-characteristic and precision-recall curves (AUROC, AUPRC). RESULTS: Twenty of 361 patients (6%) died or underwent DHC. Baseline clinical variables alone had recall of 60% with low precision (7%), AUROC 0.59, AUPRC 0.15. Adding baseline intracranial reserve improved recall to 80% and AUROC to 0.82 but precision remained only 16% (AUPRC 0.28). Incorporating ΔCSF improved AUPRC to 0.53 (AUROC 0.91) while all imaging features further improved prediction (recall 90%, precision 38%, AUROC 0.96, AUPRC 0.66). CONCLUSION: Incorporating quantitative CT-based imaging features from baseline and 24-h CT enhances identification of patients with malignant edema needing DHC. Further refinements and external validation of such imaging-based machine-learning models are required.
Authors: Thomas W K Battey; Mahima Karki; Aneesh B Singhal; Ona Wu; Saloomeh Sadaghiani; Bruce C V Campbell; Stephen M Davis; Geoffrey A Donnan; Kevin N Sheth; W Taylor Kimberly Journal: Stroke Date: 2014-10-21 Impact factor: 7.914
Authors: Götz Thomalla; Frank Hartmann; Eric Juettler; Oliver C Singer; Fritz-Georg Lehnhardt; Martin Köhrmann; Jan F Kersten; Anna Krützelmann; Marek C Humpich; Jan Sobesky; Christian Gerloff; Arno Villringer; Jens Fiehler; Tobias Neumann-Haefelin; Peter D Schellinger; Joachim Röther Journal: Ann Neurol Date: 2010-10 Impact factor: 10.422
Authors: Rajat Dhar; Yasheng Chen; Ali Hamzehloo; Atul Kumar; Laura Heitsch; June He; Ling Chen; Agnieszka Slowik; Daniel Strbian; Jin-Moo Lee Journal: Stroke Date: 2019-12-10 Impact factor: 7.914
Authors: Katayoun Vahedi; Jeannette Hofmeijer; Eric Juettler; Eric Vicaut; Bernard George; Ale Algra; G Johan Amelink; Peter Schmiedeck; Stefan Schwab; Peter M Rothwell; Marie-Germaine Bousser; H Bart van der Worp; Werner Hacke Journal: Lancet Neurol Date: 2007-03 Impact factor: 44.182
Authors: Hossein Mohammadian Foroushani; Ali Hamzehloo; Atul Kumar; Yasheng Chen; Laura Heitsch; Agnieszka Slowik; Daniel Strbian; Jin-Moo Lee; Daniel S Marcus; Rajat Dhar Journal: Neurocrit Care Date: 2021-08-20 Impact factor: 3.210
Authors: Hossein Mohammadian Foroushani; Rajat Dhar; Yasheng Chen; Jenny Gurney; Ali Hamzehloo; Jin-Moo Lee; Daniel S Marcus Journal: Front Neuroinform Date: 2021-06-24 Impact factor: 3.739