Different response patterns in hallucinations and delusions to antipsychotic treatment

Prediction of Clinical Outcomes in Psychotic Disorders Using Artificial Intelligence Methods: A Scoping Review

BACKGROUND

Psychotic disorders are major psychiatric disorders that can impact multiple domains including physical, social, and psychological functioning within individuals with these conditions. Being able to better predict the outcomes of psychotic disorders will allow clinicians to identify illness subgroups and optimize treatment strategies in a timely manner.

OBJECTIVE

In this scoping review, we aimed to examine the accuracy of the use of artificial intelligence (AI) methods in predicting the clinical outcomes of patients with psychotic disorders as well as determine the relevant predictors of these outcomes.

METHODS

This review was guided by the PRISMA Guidelines for Scoping Reviews. Seven electronic databases were searched for relevant published articles in English until 1 February 2024.

RESULTS

Thirty articles were included in this review. These studies were mainly conducted in the West (63%) and Asia (37%) and published within the last 5 years (83.3%). The clinical outcomes included symptomatic improvements, illness course, and social functioning. The machine learning models utilized data from various sources including clinical, cognitive, and biological variables such as genetic, neuroimaging measures. In terms of main machine learning models used, the most common approaches were support vector machine, random forest, logistic regression, and linear regression models. No specific machine learning approach outperformed the other approaches consistently across the studies, and an overall range of predictive accuracy was observed with an AUC from 0.58 to 0.95. Specific predictors of clinical outcomes included demographic characteristics (gender, socioeconomic status, accommodation, education, and employment); social factors (activity level and interpersonal relationships); illness features (number of relapses, duration of relapses, hospitalization rates, cognitive impairments, and negative and disorganization symptoms); treatment (prescription of first-generation antipsychotics, high antipsychotic doses, clozapine, use of electroconvulsive therapy, and presence of metabolic syndrome); and structural and functional neuroimaging abnormalities, especially involving the temporal and frontal brain regions.

CONCLUSIONS

The current review highlights the potential and need to further refine AI and machine learning models in parsing out the complex interplay of specific variables that contribute to the clinical outcome prediction of psychotic disorders.

Developmental influences on symptom expression in antipsychotic-naïve first-episode psychosis

BACKGROUND

The neurodevelopmental model of psychosis was established over 30 years ago; however, the developmental influence on psychotic symptom expression - how age affects clinical presentation in first-episode psychosis - has not been thoroughly investigated.

METHODS

Using generalized additive modeling, which allows for linear and non-linear functional forms of age-related change, we leveraged symptom data from a large sample of antipsychotic-naïve individuals with first-episode psychosis (N = 340, 12-40 years, 1-12 visits), collected at the University of Pittsburgh from 1990 to 2017. We examined relationships between age and severity of perceptual and non-perceptual positive symptoms and negative symptoms. We tested for age-associated effects on change in positive or negative symptom severity following baseline assessment and explored the time-varying relationship between perceptual and non-perceptual positive symptoms across adolescent development.

RESULTS

Perceptual positive symptom severity significantly decreased with increasing age (F = 7.0, p = 0.0007; q = 0.003) while non-perceptual positive symptom severity increased with age (F = 4.1, p = 0.01, q = 0.02). Anhedonia severity increased with increasing age (F = 6.7, p = 0.00035; q = 0.0003), while flat affect decreased in severity with increased age (F = 9.8, p = 0.002; q = 0.006). Findings remained significant when parental SES, IQ, and illness duration were included as covariates. There were no developmental effects on change in positive or negative symptom severity (all p > 0.25). Beginning at age 18, there was a statistically significant association between severity of non-perceptual and perceptual symptoms. This relationship increased in strength throughout adulthood.

CONCLUSIONS

These findings suggest that as maturation proceeds, perceptual symptoms attenuate while non-perceptual symptoms are enhanced. Findings underscore how pathological brain-behavior relationships vary as a function of development.

Clinical validation of the Symptom Self-rating Scale for Schizophrenia (4S) among inpatients

PURPOSE

Self-reports of psychosis-related symptoms may be a valuable supplement to clinician-ratings, but more validation studies are required. The aim of this study was to conduct clinical validation for the Symptom Self-rating Scale for Schizophrenia (4S) in an inpatient setting.

MATERIALS AND METHODS

Inpatients diagnosed with schizophrenia were invited to participate in the study. The participants completed the 4S, the 5-item World Health Organization Wellbeing Index (WHO-5) and the Sheehan Disability Scale (SDS) at two time points. Trained raters assessed participants using the 6-item Positive And Negative Syndrome Scale (PANSS-6). The relationship between the 4S and PANSS-6, self-reported side effects, functioning and wellbeing was assessed using Spearman's correlation coefficient (rho).

RESULTS

Sixty-one participants completed the 4S at least once (yielding a total of 91 completed 4S questionnaires). The 4S total score was weakly correlated with the PANSS-6 total score (rho = 0.37, p < 0.001). The rho's for individual 4S and PANSS-6 subscales and item comparisons ranged from -0.24 (thought disorder) to 0.69 (hallucinations). Finally, the 4S hallucination subscale was also sensitive to change. The 4S was strongly inversely correlated with wellbeing (WHO-5) and moderately inversely correlated with functioning (SDS total score).

CONCLUSION

The 4S holds promise as a valid self-report of core schizophrenia symptoms among inpatients. While the hallucination subscale seems superior to existing scales, the thought disorder subscale needs to be re-developed.