Psychosocial rehabilitation (PSR) is at the core of psychiatric recovery. There is a paucity of evidence regarding how the needs and characteristics of patients guide clinical decisions to refer to PSR interventions. Here, we used explainable machine learning methods to determine how socio-demographic and clinical characteristics contribute to initial referrals to PSR interventions in patients with serious mental illness.

Data were extracted from the French network of rehabilitation centres, REHABase, collected between years 2016 and 2022 and analysed between February and September 2022. Participants presented with serious mental illnesses, including schizophrenia spectrum disorders, bipolar disorders, autism spectrum disorders, depressive disorders, anxiety disorders and personality disorders. Information from 37 socio-demographic and clinical variables was extracted at baseline and used as potential predictors. Several machine learning models were tested to predict initial referrals to four PSR interventions: cognitive behavioural therapy (CBT), cognitive remediation (CR), psychoeducation (PE) and vocational training (VT). Explanatory power of predictors was determined using the artificial intelligence-based SHAP (SHapley Additive exPlanations) method from the best performing algorithm.

Data from a total of 1146 patients were included (mean age, 33.2 years [range, 16–72 years]; 366 [39.2%] women). A random forest algorithm demonstrated the best predictive performance, with a moderate or average predictive accuracy [micro-averaged area under the receiver operating curve from ‘external’ cross-validation: 0.672]. SHAP dependence plots demonstrated insightful associations between socio-demographic and clinical predictors and referrals to PSR programmes. For instance, patients with psychotic disorders were more likely to be referred to PE and CR, while those with non-psychotic disorders were more likely to be referred to CBT and VT. Likewise, patients with social dysfunctions and lack of educational attainment were more likely to be referred to CR and VT, while those with better functioning and education were more likely to be referred to CBT and PE.

A combination of socio-demographic and clinical features was not sufficient to accurately predict initial referrals to four PSR programmes among a French network of rehabilitation centres. Referrals to PSR interventions may also involve service- and clinician-level factors. Considering socio-demographic and clinical predictors revealed disparities in referrals with respect to diagnoses, current clinical and psychological issues, functioning and education.

Bipolar disorder (BD) is a common and disabling condition. Gender differences are potentially important and can manifest in many ways.

To determine the socio-demographic characteristics of women with BD, followed at the department of psychiatry of Gabes (southern of Tunisia).

A retrospective descriptive and analytical study was undertaken including all the patients having consulted for the first time in the department of psychiatry of Gabes, from January 1st, 2010 to December 31, 2016, for whom the diagnosis of a bipolar disorder was established according to the DSM-IV criteria. Sociodemographic and clinical data were assessed. Patients were divided into two groups according to gender. The collected data was compared between the two groups. The statisticalanalysiswasexecuted on the software SPSS (20thedition).

We included 193 patients with BD (women = 103). The mean age of the women studied was 39.9 years. Women with BD had the following characteristics: married (55.3%), unemployed (65.1%), having an urban origin (75.7%), attending the primary or secondary school level (76.7%) and with an middle socioeconomic level (62.1%). Among the women studied, 9 (8.7%) were smokers, 2 (1.9%) consumed alcohol, and one (0.9%) used cannabis. Regarding the socio-demographic differences by gender, bipolar women were significantly less professionally active (p<10-3), less educated (p= 0.009), more frequently married, widowed or divorced (p <10-3) and having dependent children (p=0.008).

Our study made it possible to note the socio-demographic particularities of the woman followed for BD. A better knowledge of these particularities is the best guarantee of adequate care.

No significant relationships.

we aimed to compare socio-demographic and clinical differences between patients with versus without current RC in order to detect clinical factors that may favor early diagnosis and personalized treatment.

A total of 1675 patients (males: n = 714 and females: n = 961; bipolar 1: n = 1042 and bipolar 2: n = 633) from different psychiatric clinics were grouped and compared according to the current presence of RC in terms of socio-demographic and clinical variables. Chi-squared tests for qualitative variables and Student’s t tests for quantitative variables were executed for group comparison, and multivariable logistic regressions were performed, considering the current presence of RC as dependent variable, and socio-demographic/clinical factors as independent variables.

Female gender (male versus female: OR = 0.64, p = 0.04), unidentifiable prevalent polarity (versus depressive polarity: OR = 1.76, p = 0.02; versus manic polarity: OR: 2.86, p < 0.01) and hospitalization in the last year (no versus yes: OR = 0.63, p = 0.02) were found to be associated with RC in the final multivariable regression analysis.

RC in BD seems to be more prevalent in female gender and associated with some unfavorable clinical features, such as an increased risk of hospitalization. These aspects should be taken into account in the management and monitoring of RC versus non-RC patients.