NeuroMiner Model Library


The last decade has witnessed the advent of machine learning techniques in clinical neuroscience. These methods hold the great potential to facilitate the translation of research findings into clinical applications following the principles of precision medicine. However, the embedding of models in clinical real-world settings has been challenged by the lack of model transparency, external validation, and hence the lack of model reproducibility. Furthermore, for most predictive models proposed for clinical applications, it remains unclear whether they provide real progress beyond the current state-of the-art, i.e. helping the given patient to better recover by informing more personalized treatment decisions.

To address these issues, the Section for Neurodiagnostic Applications headed by Prof. Nikolaos Koutsouleris at the Ludwig-Maximilian-University Munich has started an online model library that aims at facilitating the fully independent validation of predictive models produced by mental health research. The library is set up to host models which have been described in peer-reviewed companion publications. Currently, all models made available to external researchers have been developed using:
NeuroMiner - an open-source advanced machine learning software for clinical neurosciences

Through a free account, users can access the library and enter data for prediction in a case-by-case fashion. This opens the possibility for external model validation and use of the models in experimental clinical settings, such as risk-stratified clinical trials.

The model library is in a pilot stage both in terms of its computational resources and its capacity to generate predictions using a variety of input data. Future versions of the library will incorporate machine learning software beyond NeuroMiner, such as TensorFlow or Scikit-Learn.
Login

Available models

The current available predictors, descriptions and scientific research references are listed below.

This machine learning model utilizes eight baseline global functioning social and role scores, to predict one-year social functioning outcomes of Clinical High Risk (CHR) patients.
Model Reference
This machine learning model utilizes eight baseline global functioning social and role scores, to predict one-year social functioning outcomes of Recent Onset Depression (ROD) patients.
Model Reference
A machine learning tool to subtype patients with established psychosis into different subgroups based on their clinical profiles.
Model Reference

This machine learning model uses Clinical-Neurocognitive questionnaire, Polygenic Risk Score and Structural MRI to predict whether a Clinical High Risk (CHR) or Recent Onset Depression (ROD) patient will transit into Psychosis.

NeuroMiner
an open-source advanced machine learning software for clinical neurosciences


NeuroMiner comes as free software to facilitate research into better tools for precision medicine. It is constantly updated by the Section for Neurodiagnostic Applications (SNAP) in Psychiatry at the Department of Psychiatry and Psychiatry of Ludwig-Maximilian-University.

It has been highly successful in producing 17 publications in medical and neuroscientific journals. More recently, the tool has been critically used to produce the leading PsyCourse paper as intended in the DFG-sponsored grant application (www.Psy-Course.de; 1603/4-1, 5-1, 7-1) 20.

NeuroMiner provides a wealth of state-of-the-art supervised Machine Learning techniques, such as linear and non-linear support-vector machines, relevance vector machines, random forests, and gradient-boosting algorithms. It also comes with numerous dimensionality reduction methods and feature selection strategies that allow finding optimal combinations of predictive features for the user’s given prediction problem.


Visit software website

Contact the developers

Lead Developer
Mark Sen Dong, M.Sc
Full stack developer, GUI and graphic design, back-end development and maintenance, database management
Section for Neurodiagnostic Applications, Ludwig Maximilian University of Munich
Email: Sen.Dong@med.uni-muenchen.de


Backend Developer (Matlab)
Anne Ruef, Ph.D
Back-end development and maintenance
Section for Neurodiagnostic Applications, Ludwig Maximilian University of Munich
Email: Anne.Ruef@med.uni-muenchen.de


Content Editor
Adriana Herrera, M.D
Provide detailed information about the models from medical and clinical perspectives
Section for Neurodiagnostic Applications, Ludwig Maximilian University of Munich
Email: Adrianna.Herrera@med.uni-muenchen.de


Supervisor
Nikolaos Koutsouleris, Prof. Dr.
Creator of NeuroMiner, back-end script development and evaluation, project supervisor
Head of Section for Neurodiagnostic Applications, Ludwig Maximilian University of Munich
Email: Nikolaos.Koutsouleris@med.uni-muenchen.de


Log in

Please read the Disclaimer before you start!

Disclaimer

If you do not have an account: Sign up

Forgot your password? Reset password

* For optimal user experience, please use Google Chrome Browser.
Mobile App
Also available as an Android app (Only for testing)
Scan the QR Code to Download
Our Supporters
Organisations that have helped us along the way