Computational Based Neuropsychiatric Research
In my lab, we use advanced computational approaches to discover knowledge that will reduce the misery of those who suffer from neuropsychiatric illnesses.
Discovering knowledge is one thing, and getting it in the hands of caregivers is another. So, we disseminate it any way we can—publications, teaching, seminars, and commercialization.
Answering today's scientific questions requires a diverse team of experts. The questions are just too complex for solo investigation.
Some of our clinical projects include epilepsy, neurosurgery, adolescent suicide classification, Alzheimer’s disease, and veteran suicide prevention. The common thread is that we teach computers how to understand emotions in text and voice. The tools to do this include artificial intelligence, machine learning, natural language processing, computational linguistics, and clinical expertise, to name a few.
In all of our efforts, we are part of teams that include computational and data scientists, clinicians, clinical trial experts, software developers, and project managers from academia and federal agencies.
Together, we have developed new ways to diagnose those we serve.
For example, Dr. Pestian and Drs. Tracy A. Glauser, Richard J. Wenstrup, and Alexander A. Vinks have identified methods that determine the optimal neuropsychiatric drug. Those methods were patented and commercially licensed. By December 2019, this discovery had been used to help more than 1.5 million people, and hundreds more are helped every day.
In another example, Drs. Pestian and Glauser, et al, developed computational algorithms that are based on the human decision-making process. We call this spreading activation, and it now serves as the basis of our approach for computationally based machine learning that is used in our projects.