A global effort to benchmark predictive models and reveal mechanistic diversity in long-term stroke outcomes

Anna Matsulevits, Pedro Alvez, Manfredo Atzori, Ahmad Beyh, Maurizio Corbetta, Federico Del Pup, Lilit Dulyan, Chris Foulon, Thomas M.h. Hope, Stefano Ioannucci, Gaël Jobard, Hervé Lemaître, Douglas Neville, Victor Nozais, Chris Rorden, Orionas-Vasilis Saprikis, Igor Sibon, Christoph Sperber, Alex Teghipco, Bertrand Thirion, Louis Fabrice Tshimanga, Roza M. Umarova, Ema Birute Vaidelyte, Elise van den Hoven, Eva Rodríguez, Andrea Zanola, Thomas Tourdias, Michel Thiebaut de Schotten

Abstract

Abstract Stroke remains a leading cause of mortality and long-term disability worldwide, with variable recovery trajectories posing substantial challenges in anticipating post-event care and rehabilitation planning. To address these challenges, we established the NeuralCup consortium to benchmark predictive models of stroke outcome through a collaborative, data-driven approach. This study presents findings from 15 international teams who used a comprehensive dataset including clinical and imaging data, to identify and compare predictors of motor, cognitive, and emotional outcomes one year post-stroke. Our analyses integrated traditional statistical approaches and novel machine learning algorithms to uncover ’optimal recipes’ for predicting each domain. The differences in these ‘optimal recipes’ reflect distinct brain mechanisms in response to different tasks. Key predictors across all domains included infarct characteristics, T1-weighted MRI sequences, and demographic factors. Additionally, integrating FLAIR imaging and white matter tract analysis significantly improved the prediction of cognitive and motor outcomes, respectively. These findings support a multifaceted approach to stroke outcome prediction, underscoring the potential of collaborative data science to develop personalized care strategies that enhance recovery and quality of life for stroke survivors. To encourage further model development and validation, we provide access to the training dataset at http://neuralcup.bcblab.com
BibTeX
@inproceedings{matsulevits2025global,
  author = {Anna Matsulevits and Pedro Alvez and Manfredo Atzori and Ahmad Beyh and Maurizio Corbetta and Federico Del Pup and Lilit Dulyan and Chris Foulon and Thomas M.H. Hope and Stefano Ioannucci and Gaël Jobard and Hervé Lemaître and Douglas Neville and Victor Nozais and Chris Rorden and Orionas-Vasilis Saprikis and Igor Sibon and Christoph Sperber and Alex Teghipco and Bertrand Thirion and Louis Fabrice Tshimanga and Roza M. Umarova and Ema Birute Vaidelyte and Elise van den Hoven and Eva Rodríguez and Andrea Zanola and Thomas Tourdias and Michel Thiebaut de Schotten},
  title = {{A global effort to benchmark predictive models and reveal mechanistic diversity in long-term stroke outcomes}},
  booktitle = {Research Square},
  year = {2025},
  doi = {10.21203/rs.3.rs-6254029/v1},
}

Loading related content...

Figure