Predictive models for response to non-invasive brain stimulation in stroke: A critical review of opportunities and pitfalls

Background: Noninvasive brain stimulation has been successfully applied to improve stroke impairments in different behavioral domains. Yet, clinical translation is limited by heterogenous comes within and across studies. It has been proposed to develop and apply noninvasive lation in a patient-tailored, precision medicine-guided fashion to maximize response rates magnitude. An important prerequisite for this task is the ability to accurately predict the response of the individual patient. Objective: This review aims to discuss current approaches studying noninvasive brain stimulation stroke and challenges associated with the development of predictive models of responsiveness noninvasive brain stimulation. Methods: Narrative review. Results: Currently, the field largely relies on in-sample associational studies to assess the different influencing factors. However, the associational approach is not valid for making prediction, which generalize out-of-sample. We will discuss crucial requirements for valid modeling in particular the presence of sufficiently large sample sizes. Conclusion: Modern predictive models are powerful tools that must be wielded with great science, including data sharing across research units to obtain sufficiently large and unbiased could provide a solid framework for addressing the task of building robust predictive noninvasive brain stimulation responsiveness. (c) 2021 Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license creativecommons.org/licenses/by-nc-nd/4.0/).