CONCLUSION: Our ML pipeline demonstrated disorder-specific learning, achieving excellent or good accuracy across several classification tasks. We demonstrated that the screening of mental disorders is possible via a fully automated, remote speech assessment pipeline. We tested our model on relatively high number conditions (5 classes) in the literature and in a stratified sample of psychosis spectrum, including HC, SPE, SSD and BD (4 classes). We tested our model on a large sample (N = 1150) and...

Globally, mental and substance use disorders are a leading cause of disease burden. In low- and middle-income countries, where there is an extreme shortage of trained mental health specialists, validated, brief screening tools for mental and substance use disorders are required for non-specialists to efficiently identify patients in need of mental health care. Mozambique, one of the poorest countries in the world, has fewer than two mental health specialists for every 100,000 people. In the...

CONCLUSION: The pharmacological treatment of BD is linked to psychiatric morbidity preceding its diagnosis. Assuming that these associations reflect well-informed clinical decisions, this knowledge may inform future clinical trials by taking participants' prior morbidity into account in treatment allocation.

Little is known about the prevalence of Conduct Disorder (CD) and symptoms of CD in high risk psychosis persons at both clinical and community populations in LMICs and in particular Kenya. This study aimed to document (1) the prevalence of CD diagnosis and symptoms in youth who screened positive for psychosis and (2) the associated mental disorders and substance use in the same cohort in LMIC. The sample size was 536 students who had screened positive on the Washington Early Recognition Center...