Computing the structure of language for neuropsychiatric evaluation

Abstract

We describe recent preliminary studies demonstrating that computational analysis of spoken and written language can provide for highly accurate diagnostics over a wide variety of psychiatric and neurologic conditions, including psychosis, drug abuse, Parkinson’s, and Alzheimer’s. These results are based on the mathematical formalization of psychiatric qualitative knowledge related to the characterization of the conditions (e.g., ‘‘derailment’’ in psychosis) and drug effects (e.g., increased intimacy/affection with the use of the recreational drug ecstasy), as well as novel linguistic feature extraction approaches. Moreover, we show novel results using publicly available text sources suggesting that 1) it is possible to define an embedding space that allows modeling of the vast language dimension into a smaller space to map and compare different conditions, and 2) computational studies of a public personality (Ronald Reagan) can likely yield novel insights into normal aging and neurodegenerative disorders. Finally, we discuss the implications for mental health (and possibly, computer science) of a systematic application of this methodology, extended to include similar readily available behavioral data such as voice and video.