Rehabilitation and recovery for ethnic minority patients with severe mental illness

Enhancing psychiatric rehabilitation outcomes through a multimodal multitask learning model based on BERT and TabNet: An approach for personalized treatment and improved decision-making

Evaluating the rehabilitation status of individuals with serious mental illnesses (SMI) necessitates a comprehensive analysis of multimodal data, including unstructured text records and structured diagnostic data. However, progress in the effective assessment of rehabilitation status remains limited. Our study develops a deep learning model integrating Bidirectional Encoder Representations from Transformers (BERT) and TabNet through a late fusion strategy to enhance rehabilitation prediction, including referral risk, dangerous behaviors, self-awareness, and medication adherence, in patients with SMI. BERT processes unstructured textual data, such as doctor's notes, whereas TabNet manages structured diagnostic information. The model's interpretability function serves to assist healthcare professionals in understanding the model's predictive decisions, improving patient care. Our model exhibited excellent predictive performance for all four tasks, with an accuracy exceeding 0.78 and an area under the curve of 0.70. In addition, a series of tests proved the model's robustness, fairness, and interpretability. This study combines multimodal and multitask learning strategies into a model and applies it to rehabilitation assessment tasks, offering a promising new tool that can be seamlessly integrated with the clinical workflow to support the provision of optimized patient care.

Neighbourhood-level social capital, marginalisation, and the incidence of schizophrenia and schizoaffective disorder in Toronto, Canada: a retrospective population-based cohort study

BACKGROUND

Studies have shown mixed results regarding social capital and the risk of developing a psychotic disorder, and this has yet to be studied in North America. We sought to examine the relationship between neighbourhood-level marginalisation, social capital, and the incidence of schizophrenia and schizoaffective disorder in Toronto, Canada.

METHODS

We used a retrospective population-based cohort to identify incident cases of schizophrenia and schizoaffective disorder over a 10 year period and accounted for neighbourhood-level marginalisation and a proxy indicator of neighbourhood social capital. Mixed Poisson regression models were used to estimate adjusted incidence rate ratios (aIRRs).

RESULTS

In the cohort (n = 649 020) we identified 4841 incident cases of schizophrenia and schizoaffective disorder. A 27% variation in incidence was observed between neighbourhoods. All marginalisation dimensions, other than ethnic concentration, were associated with incidence. Compared to areas with low social capital, areas with intermediate social capital in the second [aIRR = 1.17, 95% confidence interval (CI) 1.03-1.33] and third (aIRR = 1.23, 95% CI 1.08-1.40) quintiles had elevated incidence rates after accounting for marginalisation. There was a higher risk associated with the intermediate levels of social capital (aIRR = 1.18, 95% CI 1.00-1.39) when analysed in only the females in the cohort, but the CI includes the possibility of a null effect.

CONCLUSIONS

The risk of developing schizophrenia and schizoaffective disorder in Toronto varies by neighbourhood and is associated with socioenvironmental exposures. Social capital was not linearly associated with risk, and risk differs by sex and social capital quintile. Future research should examine these relationships with different forms of social capital and examine how known individual-level risk factors impact these findings.