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
{"title":"Prediction of stroke severity: systematic evaluation of lesion representations.","authors":"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","doi":"10.1002/acn3.52215","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>To systematically evaluate which lesion-based imaging features and methods allow for the best statistical prediction of poststroke deficits across independent datasets.</p><p><strong>Methods: </strong>We utilized imaging and clinical data from three independent datasets of patients experiencing acute stroke (N<sub>1</sub> = 109, N<sub>2</sub> = 638, N<sub>3</sub> = 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.</p><p><strong>Results: </strong>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 R<sup>2</sup> <sub>N1</sub> = 0.2%). Performance across independent datasets improved using large single-center training data (R<sup>2</sup> <sub>N2</sub> = 15.8%) and improved further using multicenter training data (R<sup>2</sup> <sub>N3</sub> = 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).</p><p><strong>Interpretation: </strong>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.</p>","PeriodicalId":126,"journal":{"name":"Annals of Clinical and Translational Neurology","volume":" ","pages":""},"PeriodicalIF":4.4000,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of Clinical and Translational Neurology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/acn3.52215","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0
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.
期刊介绍:
Annals of Clinical and Translational Neurology is a peer-reviewed journal for rapid dissemination of high-quality research related to all areas of neurology. The journal publishes original research and scholarly reviews focused on the mechanisms and treatments of diseases of the nervous system; high-impact topics in neurologic education; and other topics of interest to the clinical neuroscience community.