Implication of Electrophysiological Biomarkers in Psychosis: Focusing on Diagnosis and Treatment Response

Quantifying brain-functional dynamics using deep dynamical systems: Technical considerations

Both mental health and mental illness unfold in complex and unpredictable ways. Novel artificial intelligence approaches from the area of dynamical systems reconstruction can characterize such dynamics and help understand the underlying brain mechanisms, which can also be used as potential biomarkers. However, applying deep learning to model dynamical systems at the individual level must overcome numerous computational challenges to be reproducible and clinically useful. In this study, we performed an extensive analysis of these challenges using generative modeling of brain dynamics from fMRI data as an example and demonstrated their impact on classifying patients with schizophrenia and major depression. This study highlights the tendency of deep learning models to identify functionally unique solutions during parameter optimization, which severely impacts the reproducibility of downstream predictions. We hope this study guides the future development of individual-level generative models and similar machine learning approaches aimed at identifying reproducible biomarkers of mental illness.

New portable device for an examination of visual cognitive evoked potentials might extend their diagnostic applications in psychiatry

Despite positive prior results obtained by using event-related potentials (ERPs) in psychiatric patients, they are not routinely used in the clinical setting. This may in part be due to problems regarding a lack of transportable equipment availability. It can be difficult for these patients to repeatedly visit electrophysiological laboratories. To address this issue, we propose using a new, fully portable device for visually evoked potentials (VEP) and cognitive function assessment, that can be used for quick examinations (https://www.veppeak.com). Our device, called "VEPpeak", is built into a headset with a color LED visual stimulator. It weighs 390 g and is connected to a notebook (PC) with evaluation software via USB. In this pilot study, we verified the device's usability in 31 patients with schizophrenia. We used the oddball paradigm with the recognition of colors for the P300 wave and choice reaction time evaluation. The examination lasted only about ten minutes. The results indicated good reproducibility of large cognitive potentials (P300) with prolonged P300 latencies and reduced amplitudes in patients compared to 15 control subjects. The P300 latency and reaction time prolongation in patients correlated with their age and the sedative effect of the pharmacotherapy.