Understanding mental health through computers: An introduction to computational psychiatry.

Computational psychiatry recently established itself as a new tool in the study of mental disorders and problems. Integration of different levels of analysis is creating computational phenotypes with clinical and research values, and constructing a way to arrive at precision psychiatry are part of this new branch. It conceptualizes the brain as a computational organ that receives from the environment parameters to respond to challenges through calculations and algorithms in continuous feedback and feedforward loops with a permanent degree of uncertainty. Through this conception, one can seize an understanding of the cerebral and mental processes in the form of theories or hypotheses based on data. Using these approximations, a better understanding of the disorder and its different determinant factors facilitates the diagnostics and treatment by having an individual, ecologic, and holistic approach. It is a tool that can be used to homologate and integrate multiple sources of information given by several theoretical models. In conclusion, it helps psychiatry achieve precision and reproducibility, which can help the mental health field achieve significant advancement. This article is a narrative review of the basis of the functioning of computational psychiatry with a critical analysis of its concepts.

A Brazilian bottom-up strategy to address mental health in a diverse population over a large territorial area - an inspiration for the use of digital mental health.

Brazil is a continental country with a history of massive immigration waves from around the world. Consequently, the Brazilian population is rich in ethnic, cultural, and religious diversity, but suffers from tremendous socioeconomic inequality. Brazil has a documented history of categorizing individuals with culturally specific behaviors as mentally ill, which has led to psychiatric institutionalization for reasons that were more social than clinical. To address this, a "network for psychosocial care" was created in Brazil, that included mental health clinics and community services distributed throughout the country. This generates local support for mental health rehabilitation, integrating psychiatric care, family support and education/work opportunities. These clinics and community services are tailored to provide care for each specific area, and are more attuned to regional culture, values and neighborhood infrastructure. Here we review existing reports about the Brazilian experience, including advances in public policy on mental health, and challenges posed by the large diversity to the psychosocial rehabilitation.  In addition, we show how new digital technologies in general, and computational speech analysis in particular, can contribute to unbiased assessments, resulting in decreased stigma and more effective diagnosis of the mental diseases, with methods that are free of gender, ethnic, or socioeconomic biases.

Influence of E/I balance and pruning in peri-personal space differences in schizophrenia: A computational approach.

The encoding of the space close to the body, named peri-personal space (PPS), is thought to play a crucial role in the unusual experiences of the self observed in schizophrenia (SCZ). However, it is unclear why SCZ patients and high schizotypal (H-SPQ) individuals present a narrower PPS and why the boundaries of the PPS are more sharply defined in patients. We hypothesise that the unusual PPS representation observed in SCZ is caused by an imbalance of excitation and inhibition (E/I) in recurrent synapses of unisensory neurons or an impairment of bottom-up and top-down connectivity between unisensory and multisensory neurons. These hypotheses were tested computationally by manipulating the effects of E/I imbalance, feedback weights and synaptic density in the network. Using simulations we explored the effects of such impairments in the PPS representation generated by the network and fitted the model to behavioural data. We found that increased excitation of sensory neurons could account for the smaller PPS observed in SCZ and H-SPQ, whereas a decrease of synaptic density caused the sharp definition of the PPS observed in SCZ. We propose a novel conceptual model of PPS representation in the SCZ spectrum that can account for alterations in self-world demarcation, failures in tactile discrimination and symptoms observed in patients.

Tecnologias digitais, subjetividade e psicopatologia: possíveis impactos da pandemia / Digital technologies, subjectivity and psychopathology: possible impacts of the pandemic / Technologies numériques, subjectivité et psychopathologie: impacts possible de la pandémie / Tecnologías digitales, subjetividad y psicopatología: posibles impactos de la pandemia

O artigo aborda o uso de tecnologias digitais na psiquiatria atual, discutindo o impacto dos dispositivos técnicos no horizonte social para além dos limites da clínica, focando a análise no projeto de fenotipagem digital, seu alcance, e nos desafios que ele suscita para o campo psiquiátrico.

The present article addresses the use of digital technologies in current psychiatry, discussing the impact of technical devices on the social horizon, beyond the limits of the clinical field. Our analysis focuses of the digital phenotyping project, its scope and the challenges it poses for the psychiatric field.

Cet article discute l'utilisation des technologies numériques en psychiatrie contemporaine, soit l'impact des dispositifs techniques sur l'horizon social au-delà des limites de la clinique. Il se concentre sur l'analyse du projet de phénotypage numérique, sa portée et les défis qu'il pose au domaine psychiatrique.

El artículo aborda el uso de las tecnologías digitales en la psiquiatría actual, discutiendo el impacto de los dispositivos técnicos en el horizonte social más allá de los límites de la clínica, enfocándose en el análisis del proyecto de fenotipado digital, su alcance y los desafíos que plantea para el campo psiquiátrico.

[Autism spectrum disorder biomarkers based on biosignals, virtual reality and artificial intelligence]. / Biomarcadores del trastorno del especto autista basados en bioseñales, realidad virtual e inteligencia artificial.

It has been observed that the stratification of Autism Spectrum Disorders (ASD) generated by the current scales is not effective for the personalization of early treatments. The clinical evaluation of ASD requires its consideration as a continuum of deficits, and there is a need to identify biologically significant parameters (biomarkers) that have the power to automatically characterize each individual at different stages of neurological development. The emerging field of computational psychiatry (CP) attempts to meet the needs of precision diagnosis by developing powerful computational and mathematical techniques. A growing scientific activity proposes the use of implicit measures based on biosignals for the classification of ASD. Virtual reality (VR) technologies have demonstrated potential for ASD interventions, but most of the work has used virtual reality for the learning / objective of interventions. Very few studies have used biological signals for recording and detailed analysis of behavioral responses that can be used to monitor or produce changes over time. In this paper the concept of behavioral biomarkers based on VR or VRBB is introduced. VRBB will allow the classification of ASD using a paradigm of computational psychiatry based on implicit brain processes measured through psychophysiological signals and the behavior of subjects exposed to complex replicas of social conditions using virtual reality interfaces.

Se ha observado que la estratificación de trastornos del espectro autista (TEA) generada por las escalas actuales no es efectiva para la personalización de tratamientos tempranos. La evaluación clínica de TEA requiere su consideración como un continuo de déficits, y existe la necesidad de identificar parámetros biológicamente significativos (biomarcadores) que tengan el poder de caracterizar automáticamente a cada individuo en diferentes etapas del desarrollo neurológico. El incipiente campo de la psiquiatría computacional (CP) intenta satisfacer las necesidades de diagnóstico de precisión mediante el desarrollo de potentes técnicas computacionales y matemáticas. Una creciente actividad científica propone el uso de medidas implícitas basadas en bioseñales para la clasificación de ASD. Las tecnologías de realidad virtual (VR) han demostrado potencial para las intervenciones de TEA, pero la mayoría de los trabajos han utilizado la realidad virtual para el aprendizaje / objetivo de las intervenciones. Muy pocos estudios han utilizado señales biológicas para el registro y el análisis detallado de las respuestas conductuales que se pueden utilizar para monitorear o producir cambios a lo largo del tiempo. En el presente trabajo se introduce el concepto de biomarcadores conductuales basados en VR o VRBB. Los VRBB van a permitir la clasificación de TEA utilizando un paradigma de psiquiatría computacional basado en procesos cerebrales implícitos medidos a través de señales psicofisiológicas y el comportamiento de sujetos expuestos a complejas réplicas de condiciones sociales utilizando interfaces de realidad virtual.

Biomarcadores del trastorno del especto autista basados en bioseñales, realidad virtual e inteligencia artificial / Autism spectrum disorder biomarkers based on biosignals, virtual reality and artificial intelligence

Se ha observado que la estratificación de trastornos del espectro autista (TEA) generada por las escalas actuales no es efectiva para la personalización de tratamientos tempranos. La evaluación clínica de TEA requiere su consideración como un continuo de déficits, y existe la necesidad de identificar parámetros biológicamente significativos (biomarcadores) que tengan el poder de caracterizar automáticamente a cada individuo en diferentes etapas del desarrollo neurológico. El incipiente campo de la psiquiatría computacional (CP) intenta satisfacer las necesidades de diagnóstico de precisión mediante el desarrollo de potentes técnicas computacionales y matemáticas. Una creciente actividad científica propone el uso de medidas implícitas basadas en bioseñales para la clasificación de ASD. Las tecnologías de realidad virtual (VR) han demostrado potencial para las intervenciones de TEA, pero la mayoría de los trabajos han utilizado la realidad virtual para el aprendizaje / objetivo de las intervenciones. Muy pocos estudios han utilizado señales biológicas para el registro y el análisis detallado de las respuestas conductuales que se pueden utilizar para monitorear o producir cambios a lo largo del tiempo. En el presente trabajo se introduce el concepto de biomarcadores conductuales basados en VR o VRBB. Los VRBB van a permitir la clasificación de TEA utilizando un paradigma de psiquiatría computacional basado en procesos cerebrales implícitos medidos a través de señales psicofisiológicas y el comportamiento de sujetos expuestos a complejas réplicas de condiciones sociales utilizando interfaces de realidad virtual.

It has been observed that the stratification of Autism Spectrum Disorders (ASD) generated by the current scales is not effective for the personalization of early treatments. The clinical evaluation of ASD requires its consideration as a continuum of deficits, and there is a need to identify biologically significant parameters (biomarkers) that have the power to automatically characterize each individual at different stages of neurological development. The emerging field of computational psychiatry (CP) attempts to meet the needs of precision diagnosis by developing powerful computational and mathematical techniques. A growing scientific activity proposes the use of implicit measures based on biosignals for the classification of ASD. Virtual reality (VR) technologies have demonstrated potential for ASD interventions, but most of the work has used virtual reality for the learning / objective of interventions. Very few studies have used biological signals for recording and detailed analysis of behavioral responses that can be used to monitor or produce changes over time. In this paper the concept of behavioral biomarkers based on VR or VRBB is introduced. VRBB will allow the classification of ASD using a paradigm of computational psychiatry based on implicit brain processes measured through psychophysiological signals and the behavior of subjects exposed to complex replicas of social conditions using virtual reality interfaces.

Using Machine Learning in Psychiatry: The Need to Establish a Framework That Nurtures Trustworthiness.

The rapid embracing of artificial intelligence in psychiatry has a flavor of being the current "wild west"; a multidisciplinary approach that is very technical and complex, yet seems to produce findings that resonate. These studies are hard to review as the methods are often opaque and it is tricky to find the suitable combination of reviewers. This issue will only get more complex in the absence of a rigorous framework to evaluate such studies and thus nurture trustworthiness. Therefore, our paper discusses the urgency of the field to develop a framework with which to evaluate the complex methodology such that the process is done honestly, fairly, scientifically, and accurately. However, evaluation is a complicated process and so we focus on three issues, namely explainability, transparency, and generalizability, that are critical for establishing the viability of using artificial intelligence in psychiatry. We discuss how defining these three issues helps towards building a framework to ensure trustworthiness, but show how difficult definition can be, as the terms have different meanings in medicine, computer science, and law. We conclude that it is important to start the discussion such that there can be a call for policy on this and that the community takes extra care when reviewing clinical applications of such models..

Using deep autoencoders to identify abnormal brain structural patterns in neuropsychiatric disorders: A large-scale multi-sample study.

Machine learning is becoming an increasingly popular approach for investigating spatially distributed and subtle neuroanatomical alterations in brain-based disorders. However, some machine learning models have been criticized for requiring a large number of cases in each experimental group, and for resembling a "black box" that provides little or no insight into the nature of the data. In this article, we propose an alternative conceptual and practical approach for investigating brain-based disorders which aim to overcome these limitations. We used an artificial neural network known as "deep autoencoder" to create a normative model using structural magnetic resonance imaging data from 1,113 healthy people. We then used this model to estimate total and regional neuroanatomical deviation in individual patients with schizophrenia and autism spectrum disorder using two independent data sets (n = 263). We report that the model was able to generate different values of total neuroanatomical deviation for each disease under investigation relative to their control group (p < .005). Furthermore, the model revealed distinct patterns of neuroanatomical deviations for the two diseases, consistent with the existing neuroimaging literature. We conclude that the deep autoencoder provides a flexible and promising framework for assessing total and regional neuroanatomical deviations in neuropsychiatric populations.