While digital twins have become an essential tool in many areas of engineering, they are still relatively rare in brain science. Whereas gradient-descent-based machine learning approaches can model behavior at an aggregate level, they do not replicate neural mechanisms of individual subjects or patients, and therefore cannot serve as twins for them. Other approaches can, such as associatively connected neural maps. For example the BiLex model can be fit to an individual patient's language history and impairment in stroke or dementia, and then used to evaluate different rehabilitation and mitigation strategies. This approach was found promising in an actual clinical trial, paving the way for more digital twin studies in the future.

Selected for a Best Paper Presentation

PDF

In Proceedings of the Chen Institute Symposium for AI Accelerated Science, 2025.

@inproceedings{miikkulainen:aias25, title={Gaining Insight into Brain Damage and Rehabilitation through Digital Twins}, author={Risto Miikkulainen and Swathi Kiran}, booktitle={Proceedings of the Chen Institute Symposium for AI Accelerated Science}, month={ }, url="http://nn.cs.utexas.edu/?miikkulainen:aias25", year={2025} }