When I left the academic world, by the end of 2015, I had almost finished a review on the state of the art in usage of machine learning methods on neuroscience: how predictive models can be used for certain diseases (Alzheimer’s, Parkinson’s, etc) when the input data comes from structural (not functional) magnetic resonance imaging.
As it turned out it was very difficult for me to actually finish it from outside of academia, the now co-first author took the manuscript, made the necessary changes to turn it from a mess into a readable sequence, and we started sending it around to different journals… which is taking longer than expected. So we have done what we should have done at the beginning of the entire process and we uploaded it to arXiv.org. Here’s the abstract:
In this paper, we provide an extensive overview of machine learning techniques applied to structural magnetic resonance imaging (MRI) data to obtain clinical classifiers. We specifically address practical problems commonly encountered in the literature, with the aim of helping researchers improve the application of these techniques in future works. Additionally, we survey how these algorithms are applied to a wide range of diseases and disorders (e.g. Alzheimer’s disease (AD), Parkinson’s disease (PD), autism, multiple sclerosis, traumatic brain injury, etc.) in order to provide a comprehensive view of the state of the art in different fields.