Prediction of stroke severity: systematic evaluation of lesion representations
Abstract Objective To systematically evaluate which lesion‐based imaging features and methods allow for the best statistical prediction of poststroke deficits across independent datasets. Methods We utilized imaging and clinical data from three independent datasets of patients experiencing acute str...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | Annals of Clinical and Translational Neurology |
| Online Access: | https://doi.org/10.1002/acn3.52215 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846118529123745792 |
|---|---|
| author | Anna K. Bonkhoff Alexander L. Cohen William Drew Michael A. Ferguson Aaliya Hussain Christopher Lin Frederic L. W. V. J. Schaper Anthony Bourached Anne‐Katrin Giese Lara C. Oliveira Robert W. Regenhardt Markus D. Schirmer Christina Jern Arne G. Lindgren Jane Maguire Ona Wu Sahar Zafar John Y. Rhee Eyal Y. Kimchi Maurizio Corbetta Natalia S. Rost Michael D. Fox MRI‐GENIE and GISCOME Investigators and the International Stroke Genetics Consortium |
| author_facet | Anna K. Bonkhoff Alexander L. Cohen William Drew Michael A. Ferguson Aaliya Hussain Christopher Lin Frederic L. W. V. J. Schaper Anthony Bourached Anne‐Katrin Giese Lara C. Oliveira Robert W. Regenhardt Markus D. Schirmer Christina Jern Arne G. Lindgren Jane Maguire Ona Wu Sahar Zafar John Y. Rhee Eyal Y. Kimchi Maurizio Corbetta Natalia S. Rost Michael D. Fox MRI‐GENIE and GISCOME Investigators and the International Stroke Genetics Consortium |
| author_sort | Anna K. Bonkhoff |
| collection | DOAJ |
| description | Abstract Objective To systematically evaluate which lesion‐based imaging features and methods allow for the best statistical prediction of poststroke deficits across independent datasets. Methods We utilized imaging and clinical data from three independent datasets of patients experiencing acute stroke (N1 = 109, N2 = 638, N3 = 794) to statistically predict acute stroke severity (NIHSS) based on lesion volume, lesion location, and structural and functional disconnection with the lesion location using normative connectomes. Results We found that prediction models trained on small single‐center datasets could perform well using within‐dataset cross‐validation, but results did not generalize to independent datasets (median R2N1 = 0.2%). Performance across independent datasets improved using large single‐center training data (R2N2 = 15.8%) and improved further using multicenter training data (R2N3 = 24.4%). These results were consistent across lesion attributes and prediction models. Including either structural or functional disconnection in the models outperformed prediction based on volume or location alone (P < 0.001, FDR‐corrected). Interpretation We conclude that (1) prediction performance in independent datasets of patients with acute stroke cannot be inferred from cross‐validated results within a dataset, as performance results obtained via these two methods differed consistently, (2) prediction performance can be improved by training on large and, importantly, multicenter datasets, and (3) structural and functional disconnection allow for improved prediction of acute stroke severity. |
| format | Article |
| id | doaj-art-b47f4e7b9dbb4f63b0c29998bd080cde |
| institution | Kabale University |
| issn | 2328-9503 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Annals of Clinical and Translational Neurology |
| spelling | doaj-art-b47f4e7b9dbb4f63b0c29998bd080cde2024-12-17T16:12:21ZengWileyAnnals of Clinical and Translational Neurology2328-95032024-12-0111123081309410.1002/acn3.52215Prediction of stroke severity: systematic evaluation of lesion representationsAnna K. Bonkhoff0Alexander L. Cohen1William Drew2Michael A. Ferguson3Aaliya Hussain4Christopher Lin5Frederic L. W. V. J. Schaper6Anthony Bourached7Anne‐Katrin Giese8Lara C. Oliveira9Robert W. Regenhardt10Markus D. Schirmer11Christina Jern12Arne G. Lindgren13Jane Maguire14Ona Wu15Sahar Zafar16John Y. Rhee17Eyal Y. Kimchi18Maurizio Corbetta19Natalia S. Rost20Michael D. Fox21MRI‐GENIE and GISCOME Investigators and the International Stroke Genetics ConsortiumJ. Philip Kistler Stroke Research Center Massachusetts General Hospital, Harvard Medical School Boston Massachusetts USADepartment of Neurology Boston Children's Hospital, Harvard Medical School Boston Massachusetts USACenter for Brain Circuit Therapeutics, Department of Neurology, Psychiatry, and Radiology Brigham and Women's Hospital, Harvard Medical School Boston Massachusetts USABrigham and Women's Hospital Harvard Medical School, Psychiatry, and Radiology Boston Massachusetts USACenter for Brain Circuit Therapeutics, Department of Neurology, Psychiatry, and Radiology Brigham and Women's Hospital, Harvard Medical School Boston Massachusetts USACenter for Brain Circuit Therapeutics, Department of Neurology, Psychiatry, and Radiology Brigham and Women's Hospital, Harvard Medical School Boston Massachusetts USACenter for Brain Circuit Therapeutics, Department of Neurology, Psychiatry, and Radiology Brigham and Women's Hospital, Harvard Medical School Boston Massachusetts USAJ. Philip Kistler Stroke Research Center Massachusetts General Hospital, Harvard Medical School Boston Massachusetts USADepartment of Neurology University Medical Center Hamburg‐Eppendorf Hamburg GermanyJ. Philip Kistler Stroke Research Center Massachusetts General Hospital, Harvard Medical School Boston Massachusetts USAJ. Philip Kistler Stroke Research Center Massachusetts General Hospital, Harvard Medical School Boston Massachusetts USAJ. Philip Kistler Stroke Research Center Massachusetts General Hospital, Harvard Medical School Boston Massachusetts USADepartment of Laboratory Medicine, the Sahlgrenska Academy Institute of Biomedicine, University of Gothenburg Gothenburg SwedenDepartment of Neurology Skåne University Hospital Lund SwedenUniversity of Technology Sydney Sydney AustraliaAthinoula A. Martinos Center for Biomedical Imaging, Department of Radiology Massachusetts General Hospital Charlestown Massachusetts USADepartment of Neurology Massachusetts General Hospital Boston Massachusetts USACenter for Neuro‐oncology, Department of Medical Oncology Dana Farber Cancer Institute, Harvard Medical School Boston Massachusetts USADepartment of Neurology Feinberg School of Medicine, Northwestern University Chicago Illinois USADepartment of Neuroscience and Padova Neuroscience Center University of Padova Padova ItalyJ. Philip Kistler Stroke Research Center Massachusetts General Hospital, Harvard Medical School Boston Massachusetts USACenter for Brain Circuit Therapeutics, Department of Neurology, Psychiatry, and Radiology Brigham and Women's Hospital, Harvard Medical School Boston Massachusetts USAAbstract Objective To systematically evaluate which lesion‐based imaging features and methods allow for the best statistical prediction of poststroke deficits across independent datasets. Methods We utilized imaging and clinical data from three independent datasets of patients experiencing acute stroke (N1 = 109, N2 = 638, N3 = 794) to statistically predict acute stroke severity (NIHSS) based on lesion volume, lesion location, and structural and functional disconnection with the lesion location using normative connectomes. Results We found that prediction models trained on small single‐center datasets could perform well using within‐dataset cross‐validation, but results did not generalize to independent datasets (median R2N1 = 0.2%). Performance across independent datasets improved using large single‐center training data (R2N2 = 15.8%) and improved further using multicenter training data (R2N3 = 24.4%). These results were consistent across lesion attributes and prediction models. Including either structural or functional disconnection in the models outperformed prediction based on volume or location alone (P < 0.001, FDR‐corrected). Interpretation We conclude that (1) prediction performance in independent datasets of patients with acute stroke cannot be inferred from cross‐validated results within a dataset, as performance results obtained via these two methods differed consistently, (2) prediction performance can be improved by training on large and, importantly, multicenter datasets, and (3) structural and functional disconnection allow for improved prediction of acute stroke severity.https://doi.org/10.1002/acn3.52215 |
| spellingShingle | Anna K. Bonkhoff Alexander L. Cohen William Drew Michael A. Ferguson Aaliya Hussain Christopher Lin Frederic L. W. V. J. Schaper Anthony Bourached Anne‐Katrin Giese Lara C. Oliveira Robert W. Regenhardt Markus D. Schirmer Christina Jern Arne G. Lindgren Jane Maguire Ona Wu Sahar Zafar John Y. Rhee Eyal Y. Kimchi Maurizio Corbetta Natalia S. Rost Michael D. Fox MRI‐GENIE and GISCOME Investigators and the International Stroke Genetics Consortium Prediction of stroke severity: systematic evaluation of lesion representations Annals of Clinical and Translational Neurology |
| title | Prediction of stroke severity: systematic evaluation of lesion representations |
| title_full | Prediction of stroke severity: systematic evaluation of lesion representations |
| title_fullStr | Prediction of stroke severity: systematic evaluation of lesion representations |
| title_full_unstemmed | Prediction of stroke severity: systematic evaluation of lesion representations |
| title_short | Prediction of stroke severity: systematic evaluation of lesion representations |
| title_sort | prediction of stroke severity systematic evaluation of lesion representations |
| url | https://doi.org/10.1002/acn3.52215 |
| work_keys_str_mv | AT annakbonkhoff predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT alexanderlcohen predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT williamdrew predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT michaelaferguson predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT aaliyahussain predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT christopherlin predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT fredericlwvjschaper predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT anthonybourached predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT annekatringiese predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT laracoliveira predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT robertwregenhardt predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT markusdschirmer predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT christinajern predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT arneglindgren predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT janemaguire predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT onawu predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT saharzafar predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT johnyrhee predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT eyalykimchi predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT mauriziocorbetta predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT nataliasrost predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT michaeldfox predictionofstrokeseveritysystematicevaluationoflesionrepresentations AT mrigenieandgiscomeinvestigatorsandtheinternationalstrokegeneticsconsortium predictionofstrokeseveritysystematicevaluationoflesionrepresentations |