Studies conducted during the COVID-19 pandemic found high occurrence of suicidal thoughts and behaviours (STBs) among healthcare workers (HCWs). The current study aimed to (1) develop a machine learning-based prediction model for future STBs using data from a large prospective cohort of Spanish HCWs and (2) identify the most important variables in terms of contribution to the model’s predictive accuracy.

This is a prospective, multicentre cohort study of Spanish HCWs active during the COVID-19 pandemic. A total of 8,996 HCWs participated in the web-based baseline survey (May–July 2020) and 4,809 in the 4-month follow-up survey. A total of 219 predictor variables were derived from the baseline survey. The outcome variable was any STB at the 4-month follow-up. Variable selection was done using an L1 regularized linear Support Vector Classifier (SVC). A random forest model with 5-fold cross-validation was developed, in which the Synthetic Minority Oversampling Technique (SMOTE) and undersampling of the majority class balancing techniques were tested. The model was evaluated by the area under the Receiver Operating Characteristic (AUROC) curve and the area under the precision–recall curve. Shapley’s additive explanatory values (SHAP values) were used to evaluate the overall contribution of each variable to the prediction of future STBs. Results were obtained separately by gender.

The prevalence of STBs in HCWs at the 4-month follow-up was 7.9% (women = 7.8%, men = 8.2%). Thirty-four variables were selected by the L1 regularized linear SVC. The best results were obtained without data balancing techniques: AUROC = 0.87 (0.86 for women and 0.87 for men) and area under the precision–recall curve = 0.50 (0.55 for women and 0.45 for men). Based on SHAP values, the most important baseline predictors for any STB at the 4-month follow-up were the presence of passive suicidal ideation, the number of days in the past 30 days with passive or active suicidal ideation, the number of days in the past 30 days with binge eating episodes, the number of panic attacks (women only) and the frequency of intrusive thoughts (men only).

Machine learning-based prediction models for STBs in HCWs during the COVID-19 pandemic trained on web-based survey data present high discrimination and classification capacity. Future clinical implementations of this model could enable the early detection of HCWs at the highest risk for developing adverse mental health outcomes.

NCT04556565

The duration of untreated psychosis (DUP) has been associated with negative outcomes in psychosis; however, few studies have focused on the duration of active psychotic symptoms after commencing treatment (DAT). In this study, we aimed to evaluate the effect of DUP and DAT on functional long-term outcomes (3 years) in patients with early psychosis.

We evaluated the Scale for the Assessment of Positive Symptoms (SAPS) at frequent intervals for 3 years after presentation to determine the DAT for 307 individuals with first-episode psychosis together with DUP and clinical variables. The functional outcomes were assessed using the Disability Assessment Scale (DAS) at three years, and functional recovery was defined as minimal impairment and return to activity. Associated variables, DAT and DUP were included in logistic regression models to predict functional outcomes. Receiver operating characteristic curves and Youden’s index were applied to assess the best cut-off values.

DAT, (Wald: 13.974; ExpB: 1.097; p < 0.001), premorbid adjustment, initial BPRS score, gender, age of onset and schizophrenia diagnosis were significant predictors of social functioning, whereas only premorbid adjustment (Wald: 11.383; ExpB:1.009), DAT (Wald: 4.850; ExpB: 1.058; p = 0.028) and education were significant predictors of recovery. The optimal cut-off of DAT for predicting social functioning was 3.17 months for DAT (sensitivity: 0.68; specificity: 0.64; Youden’s index: 0.314).

DAT is strongly related to functional outcomes independent of the DUP period or other variables. As a modifiable variable, the reduction of the DAT should be considered a main focus of intervention from the onset of the illness to improve long-term outcomes.

Long-acting injectable antipsychotic therapies may offer benefits over oral antipsychotics in patients with schizophrenia. However, there is still a lack of real-world studies assessing the effectiveness of these therapies.

This study aimed to explore the safety, tolerability, and treatment response of aripiprazole monohydrate (AOM) once monthly in non-acute but symptomatic adult patients switched from previous therapy with frequently used oral or injectable atypical antipsychotics.

This was a post hoc analysis of a prospective, interventional, single-arm, open-label, 6-month study.

The patients (N=54) were switched to aripiprazole monohydrate once-monthly (AOM) from daily oral treatment or monthly injectable treatment with either aripiprazole (n=25), olanzapine (n=7), paliperidone extended-release (PP1M) (n=10), quetiapine (n=4), or risperidone (n=8). In all groups, mean Positive and Negative Syndrome Scale total (p=0.0001) and Clinical Global Impression-Severity scores improved significantly (p=0.0001). A reduction of ≥50% reduction of BPRS total-score and a CGI severity-score ≤4 in the Positive and Negative Syndrome Scale total score were observed in 16.7% (aripiprazole), 21.2% (olanzapine), 35.1% (PP1M), 27.3% (quetiapine), and 37.2% (risperidone) of patients. The patients showed significant improvements involving safety features as they experienced significant overall weight loss (p=0.0001) and prolactine decrease (risperidone p=0.0001, paliperidone extended-release p=0.0001). AOM once-monthly was well tolerated, presenting no new safety signals. Patient also reported an overall significant improvement on their quality of life measured with the Quality of Life Rating Scale (QLS) (p=0.0004) as well as in sexual functioning PRSexDQ-SALSEX (p=0.0001). In addition, the all cause treatment discontinuation rate after6-month follow-up was small (n=3; 5,55%)

These data illustrate that stable, non-acute but symptomatic patients either on oral antipsychotic therapy or under monthly antipsychotic treatment may show clinically meaningful improvement of psychotic symptoms, tolerability involving relevant side effects and quality of life perception. The findings are limited by the naturalistic study design; thus, further studies are required to confirm the current findings.

Keywords: Long-acting injectable antipsychotic therapy. Oral antipsychotic. Effectiveness- Tolerability-Quality oflife.