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.

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.