Search

Background: Psychosis poses substantial social and healthcare burdens. The analysis of speech is a promising approach for the diagnosis and monitoring of psychosis, capturing symptoms like thought disorder and flattened affect. Recent advancements in Natural Language Processing (NLP) methodologies enable the automated extraction of informative speech features, which has been leveraged for early psychosis detection and assessment of symptomology. However, critical gaps persist, including the absence of standardized sample collection protocols, small sample sizes, and a lack of multi-illness classification, limiting clinical applicability. Our study aimed to (1) identify an optimal assessment approach for the online and remote collection of speech, in the context of assessing the psychosis spectrum and evaluate whether a fully automated, speech-based machine learning (ML) pipeline can discriminate among different conditions on the schizophrenia-bipolar spectrum (SSD-BD-SPE), help-seeking comparison subjects (MDD), and healthy controls (HC) at varying layers of analysis and diagnostic complexity., Methods: We adopted online data collection methods to collect 20 minutes of speech and demographic information from individuals. Participants were categorized as "healthy" help-seekers (HC), having a schizophrenia-spectrum disorder (SSD), bipolar disorder (BD), major depressive disorder (MDD), or being on the psychosis spectrum with sub-clinical psychotic experiences (SPE). SPE status was determined based on self-reported clinical diagnosis and responses to the PHQ-8 and PQ-16 screening questionnaires, while other diagnoses were determined based on self-report from participants. Linguistic and paralinguistic features were extracted and ensemble learning algorithms (e.g., XGBoost) were used to train models. A 70%-30% train-test split and 30-fold cross-validation was used to validate the model performance., Results: The final analysis sample included 1140 individuals and 22,650 minutes of speech. Using 5-minutes of speech, our model could discriminate between HC and those with a serious mental illness (SSD or BD) with 86% accuracy (AUC = 0.91, Recall = 0.7, Precision = 0.98). Furthermore, our model could discern among HC, SPE, BD and SSD groups with 86% accuracy (F1 macro = 0.855, Recall Macro = 0.86, Precision Macro = 0.86). Finally, in a 5-class discrimination task including individuals with MDD, our model had 76% accuracy (F1 macro = 0.757, Recall Macro = 0.758, Precision Macro = 0.766)., 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 demonstrated best-in-class accuracy with remotely collected speech data in the psychosis spectrum, however, further clinical validation is needed to test the reliability of model performance., Competing Interests: Conflict of interest J.O, E.W., R. Ch are co-founders and employees of Psyrin and owns equity for Psyrin. SXT owns equity and serves as a consultant for North Shore Therapeutics, received research funding and serves as a consultant for Winterlight Labs, and is on the advisory board and owns equity for Psyrin.

Cytochrome P450 enzymes including CYP2C19 and CYP2D6 are important for antidepressant metabolism and polymorphisms of these genes have been determined to predict metabolite levels. Nonetheless, more evidence is needed to understand the impact of genetic variations on antidepressant response. In this study, individual clinical and genetic data from 13 studies of European and East Asian ancestry populations were collected. The antidepressant response was clinically assessed as remission and percentage improvement. Imputed genotype was used to translate genetic polymorphisms to metabolic phenotypes (poor, intermediate, normal, and rapid+ultrarapid) of CYP2C19 and CYP2D6. The association of CYP2C19 and CYP2D6 metabolic phenotypes with treatment response was examined using normal metabolizers as the reference. Among 5843 depression patients, a higher remission rate was found in CYP2C19 poor metabolizers compared to normal metabolizers at nominal significance but did not survive after multiple testing correction (OR=1.46, 95% CI [1.03, 2.06], p=0.033, heterogeneity I 2 =0%, subgroup difference p=0.72). No metabolic phenotype was associated with percentage improvement from baseline. After stratifying by antidepressants primarily metabolized by CYP2C19 and CYP2D6, no association was found between metabolic phenotypes and antidepressant response. Metabolic phenotypes showed differences in frequency, but not effect, between European- and East Asian-ancestry studies. In conclusion, metabolic phenotypes imputed from genetic variants using genotype were not associated with antidepressant response. CYP2C19 poor metabolizers could potentially contribute to antidepressant efficacy with more evidence needed. CYP2D6 structural variants cannot be imputed from genotype data, limiting inference of pharmacogenetic effects. Sequencing and targeted pharmacogenetic testing, alongside information on side effects, antidepressant dosage, depression measures, and diverse ancestry studies, would more fully capture the influence of metabolic phenotypes., Competing Interests: Conflict of Interest CML has served on the scientific advisory board for Myriad Neuroscience, and is a consultant for UCB. AS is or has been consultant/speaker for: Abbott, AbbVie, Angelini, AstraZeneca, Clinical Data, Boehringer, Bristol Myers Squibb, Eli Lilly, GlaxoSmithKline, InnovaPharma, Italfarmaco, Janssen, Lundbeck, Naurex, Pfizer, Polifarma, Sanofi, and Servier. AMM has received research support from the Sackler Trust and speakers fees from Janssen and Illumina. MK has received grant funding from the Japanese Ministry of Health, Labor and Welfare, the Japan Society for the Promotion of Science, SENSHIN Medical Research Foundation, the Japan Research Foundation for Clinical Pharmacology and the Japanese Society of Clinical Neuropsychopharmacology and speaker’s honoraria from Sumitomo Pharma, Otsuka, Meiji-Seika Pharma, Eli Lilly, MSD K.K., Pfizer, Janssen Pharmaceutical, Shionogi, Mitsubishi Tanabe Pharma, Takeda Pharmaceutical, Lundbeck Viatris Inc, Eisai Co., Ltd. and Ono Pharmaceutical and participated in an advisory/review board for Otsuka, Sumitomo Pharma, Shionogi and Boehringer Ingelheim. DS has received grant/research support from GlaxoSmithKline and Lundbeck; and served as a consultant or on advisory boards for AstraZeneca, Bristol Myers Squibb, Eli Lilly, Janssen, and Lundbeck. CF was a speaker for Janssen. NP is or has been consultant/speaker for: Takeda, Janssen and Lundbeck All other authors report no biomedical financial interests or potential conflicts of interest.