MAR 14, 2018 06:00 AM PDT

Speech Graphs as a Tool for Psychiatric Diagnosis: A Physicist's Walk into Computational Psychiatry

Presented At Neuroscience 2018
C.E. CREDITS: P.A.C.E. CE | Florida CE
Speakers
  • Associate Professor of Physics, Federal University of Pernambuco
    Biography
      Mauro Copelli is a theoretical physicist who has worked on the applications of techniques from Statistical Mechanics and Nonlinear Dynamics to the understanding of collective
      behavior of neural networks. He and his collaborators have studied how collective
      neural phenomena can account for information processing in sensory
      systems, having emphasized that coding of incoming physical stimuli
      can be optimized if the system is in a critical state. This
      interdisciplinary research theme has fostered his collaborations with
      theoretical physicists and experimental neuroscientists. He has also
      worked on the application of complex graphs to speech, a technique that has shown
      potential for automated psychiatric diagnosis. He obtained his undergraduate and MSc Physics degrees from the University of São Paulo in Brazil, a PhD in Physics from Hasselt University in Belgium and completed postdoctoral training in Physics at the University of California in San Diego and the Fluminense Federal University in Niterói, Brazil.
      He joined the faculty at the UFPE Physics Department in 2002.

    Abstract:

    Psychiatric diagnosis is inherently difficult, due to the lack of clear biomarkers or any other objective assessment. Although quantitative, the psychometric scales employed during the psychiatric interview are subjective, so psychiatrists are required to undergo extensive training before they are properly qualified to diagnose. In search of objective, quantitative insight into the structure of psychotic speech, we applied standard techniques in the field of complex networks to measure speech graph attributes in chronic patients with schizophrenia, bipolar disorder type I, and non-psychotic controls as they reported waking and dream contents. Speech graphs are simply directed graphs of word trajectories, upon which graph-theoretical measures can be applied. We show that the three different groups can be sorted just by looking at a handful of speech graph attributes, after discarding all semantic content. The technique can also be successfully extended to patients during their first clinical contact, objectively classifying diagnosis 6 months in advance and providing a diagnostic-independent “disorganization index” for speech. The results demonstrate the feasibility of the differential diagnosis of psychosis based on the analysis of speech graphs, pointing to a fast, low-cost and language-invariant tool for psychiatric diagnosis and the objective search for biomarkers. 


    Show Resources
    Loading Comments...