Product information
- Functions:
Data cleaning, Neuroimaging preprocessing, Feature preprocessing, Covariate control, Machine learning model training, Multimodal capacity, Model inference, Results visualisation Model interpretation, Model external validation - Technologies:
Matlab - Website: NeuroMiner website
- Download: NeuroMiner Github repo
Advanced ML modeling tool enabling non-coders to conduct ML research with ease
The challenge
Over the past decade, AI and machine learning technologies have propelled significant advancements in medical research. However, a notable challenge persists within the medical research community: many professionals, including doctors, lack the requisite coding expertise and necessary support to harness the full potential of machine learning technologies for their research endeavours.
The solution
Our scientific director Prof.Nikolaos Koutsouleris developed NeuroMiner: an ML modeling tool designed specifically for medical researches and for non-coding doctors and researchers. NeuroMiner is an open-source free software to facilitate research into better tools for precision medicine. It is currently been actively updated and developed by members of the lab of precision psychiatry at the department of psychiatry and psychotherapy at Ludwig Maximilians University of Munich.
The end result
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. NeuroMiner can analyze different data formats, ranging from tabular clinical and genetic data to 3D voxel-based neuroimages, and combining multiple data modalities into more complex multi-modal prediciton systems.NeuroMiner has been highly successful in producing more than 20 publications in medical and neuroscience 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).