Detecting at-risk mental states for psychosis (ARMS) using machine learning ensembles and facial features.

AIMS: Our study aimed to develop a machine learning ensemble to distinguish "at-risk mental states for psychosis" (ARMS) subjects from control individuals from the general population based on facial data extracted from video-recordings. METHODS: 58 non-help-seeking medication-naïve ARMS and 70 healthy subjects were screened from a general population sample. At-risk status was assessed with the Structured Interview for Prodromal Syndromes (SIPS), and "Subject's Overview" section was filmed (5-10 min). Several features were extracted, e.g., eye and mouth aspect ratio, Euler angles, coordinates from 51 facial landmarks. This elicited 649 facial features, which were further selected using Gradient Boosting Machines (AdaBoost combined with Random Forests). Data was split in 70/30 for training, and Monte Carlo cross validation was used. RESULTS: Final model reached 83 % of mean F1-score, and balanced accuracy of 85 %. Mean area under the curve for the receiver operator curve classifier was 93 %. Convergent validity testing showed that two features included in the model were significantly correlated with Avolition (SIPS N2 item) and expression of emotion (SIPS N3 item). CONCLUSION: Our model capitalized on short video-recordings from individuals recruited from the general population, effectively distinguishing between ARMS and controls. Results are encouraging for large-screening purposes in low-resource settings.

Gesticulation in individuals with at risk mental states for psychosis.

Nonverbal communication (NVC) is a complex behavior that involves different modalities that are impaired in the schizophrenia spectrum, including gesticulation. However, there are few studies that evaluate it in individuals with at-risk mental states (ARMS) for psychosis, mostly in developed countries. Given our prior findings of reduced movement during speech seen in Brazilian individuals with ARMS, we now aim to determine if this can be accounted for by reduced gesticulation behavior. Fifty-six medication-naïve ARMS and 64 healthy controls were filmed during speech tasks. The frequency of specifically coded gestures across four categories (and self-stimulatory behaviors) were compared between groups and tested for correlations with prodromal symptoms of the Structured Interview for Prodromal Syndromes (SIPS) and with the variables previously published. ARMS individuals showed a reduction in one gesture category, but it did not survive Bonferroni's correction. Gesture frequency was negatively correlated with prodromal symptoms and positively correlated with the variables of the amount of movement previously analyzed. The lack of significant differences between ARMS and control contradicts literature findings in other cultural context, in which a reduction is usually seen in at-risk individuals. However, gesture frequency might be a visual proxy of prodromal symptoms, and of other movement abnormalities. Results show the importance of analyzing NVC in ARMS and of considering different cultural and sociodemographic contexts in the search for markers of these states.

Inequality and barriers in psychosis prevention: A systematic review on clinical high-risk for psychosis studies from developing countries.

Background: The clinical high-risk for psychosis (CHR) paradigm is one of the best studied preventive paradigms in psychiatry. However, most studies have been conducted in high-income countries. It is unclear if knowledge from such countries applies to low and middle-income countries (LAMIC), and if there are specific limitations hindering CHR research there. Our aim is to systematically review studies on CHR from LAMIC. Methods: A multistep PRISMA-compliant literature search was performed in PubMed and Web of Science for articles published until 1/03/2022, conducted in LAMIC, addressing the concept and correlates of CHR. Study characteristics as well as limitations were reported. Corresponding authors of the included studies were invited to answer an online poll. Quality assessment was done with the MMAT. Results: A total of 109 studies were included in the review: none from low-income countries, 8 from lower middle-income countries, and 101 from upper middle-income countries. The most frequent limitations were small sample size (47.9%), cross-sectional design (27.1%), and follow-up issues (20.8%). Mean quality of included studies was of 4.4. Out of the 43 corresponding authors, 12 (27.9%) completed the online poll. They cited further limitations as few financial resources (66.7%), no involvement of population (58.2%) and cultural barriers (41.7%). Seventy five percent researchers reported that CHR research should be conducted differently in LAMIC compared to high-income countries, due to structural and cultural issues. Stigma was mentioned in three out of five sections of the poll. Discussion: Results show the discrepancy of available evidence on CHR in LAMIC, given the shortage of resources in such countries. Future directions should aim to increase the knowledge on individuals at CHR in such settings, and to address stigma and cultural factors that may play a role in the pathways toward care in psychosis. Systematic Review Registration: https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=316816, CRD42022316816.

Ethical Implications of the Use of Language Analysis Technologies for the Diagnosis and Prediction of Psychiatric Disorders.

Recent developments in artificial intelligence technologies have come to a point where machine learning algorithms can infer mental status based on someone's photos and texts posted on social media. More than that, these algorithms are able to predict, with a reasonable degree of accuracy, future mental illness. They potentially represent an important advance in mental health care for preventive and early diagnosis initiatives, and for aiding professionals in the follow-up and prognosis of their patients. However, important issues call for major caution in the use of such technologies, namely, privacy and the stigma related to mental disorders. In this paper, we discuss the bioethical implications of using such technologies to diagnose and predict future mental illness, given the current scenario of swiftly growing technologies that analyze human language and the online availability of personal information given by social media. We also suggest future directions to be taken to minimize the misuse of such important technologies.

Motion energy analysis during speech tasks in medication-naïve individuals with at-risk mental states for psychosis.

Movement abnormalities are commonly observed in schizophrenia and at-risk mental states (ARMS) for psychosis. They are usually detected with clinical interviews, such that automated analysis would enhance assessment. Our aim was to use motion energy analysis (MEA) to assess movement during free-speech videos in ARMS and control individuals, and to investigate associations between movement metrics and negative and positive symptoms. Thirty-two medication-naïve ARMS and forty-six healthy control individuals were filmed during speech tasks. Footages were analyzed using MEA software, which assesses movement by differences in pixels frame-by-frame. Two regions of interest were defined-head and torso-and mean amplitude, frequency, and coefficient of variability of movements for them were obtained. These metrics were correlated with the Structured Interview for Prodromal Syndromes (SIPS) symptoms, and with the risk of conversion to psychosis-inferred with the SIPS risk calculator. ARMS individuals had significantly lower mean amplitude of head movement and higher coefficients of movement variability for both head and torso, compared to controls. Higher coefficient of variability was related to higher risk of conversion. Negative correlations were seen between frequency of movement and most SIPS negative symptoms. All positive symptoms were correlated with at least one movement variable. Movement abnormalities could be automatically detected in medication-naïve ARMS subjects by means of a motion energy analysis software. Significant associations of movement metrics with symptoms were found, supporting the importance of movement analysis in ARMS. This could be a potentially important tool for early diagnosis, intervention, and outcome prediction.