This machine learning application uses a Random Forest model developed at The University of Texas at Dallas, based on published data from research studies conducted over a period of 47 years to predict if a
set of electrical stimulation parameters will be likely damaging or non-damaging when applied to neural tissue in the central or peripheral nervous systems.
The current model presents an accuracy of approximately 88% and compares the prediction to the traditional Shannon equation, which has an accuracy of approximately 65%.
By using this application, you agree to be contacted in the future regarding the usage and outcomes from the set of electrical stimulation parameters in your inquiry. This will help the developers to increase the dataset of known
stimulation-induced neural tissue outcomes and re-train the machine learning model to achieve higher accuracies over time.
DISCLAIMER: The output of this application is intended as guidance for experimental research and not definitive guidelines for use in regulatory applications. The model is undergoing peer
review and has not yet been accepted for publication. The FDA has not evaluated this model, and it should not be used in lieu of pre-clinical or clinical testing of
medical devices. Neither The University of Texas at Dallas nor the authors of this model are responsible for the outcomes of stimulation protocols tested within
this application.
Citation: Li, Y., Frederick, R. A., George, D., Cogan, S. F., Pancrazio, J. J., Bleris, L., & Hernandez-Reynoso, A. G. (2024). NeurostimML: A machine learning model for predicting neurostimulation-induced tissue damage. Journal of Neural Engineering. https://doi.org/10.1088/1741-2552/ad593e
Please submit experimental measurements for each of following parameters (positive values, e.g., 100.5 or 50), as well as your contact information. Next, click the Calculate button.
For comments and questions please contact:
Ana Hernandez-Reynoso, Ph.D.
Department of Bioengineering
University of Texas at Dallas
E-mail: ana.hernandezreynoso@utdallas.edu