Machine Learning Algorithm-Based Prediction Model for the Augmented Use of Clozapine with Electroconvulsive Therapy in Patients with Schizophrenia.

The augmentation of clozapine with electroconvulsive therapy (ECT) has been an optimal treatment option for patients with treatment- or clozapine-resistant schizophrenia. Using data from the Research on Asian Psychotropic Prescription Patterns for Antipsychotics survey, which was the largest international psychiatry research collaboration in Asia, our study aimed to develop a machine learning algorithm-based substantial prediction model for the augmented use of clozapine with ECT in patients with schizophrenia in terms of precision medicine. A random forest model and least absolute shrinkage and selection operator (LASSO) model were used to develop a substantial prediction model for the augmented use of clozapine with ECT. Among the 3744 Asian patients with schizophrenia, those treated with a combination of clozapine and ECT were characterized by significantly greater proportions of females and inpatients, a longer duration of illness, and a greater prevalence of negative symptoms and social or occupational dysfunction than those not treated. In the random forest model, the area under the curve (AUC), which was the most preferred indicator of the prediction model, was 0.774. The overall accuracy was 0.817 (95% confidence interval, 0.793−0.839). Inpatient status was the most important variable in the substantial prediction model, followed by BMI, age, social or occupational dysfunction, persistent symptoms, illness duration > 20 years, and others. Furthermore, the AUC and overall accuracy of the LASSO model were 0.831 and 0.644 (95% CI, 0.615−0.672), respectively. Despite the subtle differences in both AUC and overall accuracy of the random forest model and LASSO model, the important variables were commonly shared by the two models. Using the machine learning algorithm, our findings allow the development of a substantial prediction model for the augmented use of clozapine with ECT in Asian patients with schizophrenia. This substantial prediction model can support further studies to develop a substantial prediction model for the augmented use of clozapine with ECT in patients with schizophrenia in a strict epidemiological context.

Empowering health workers and leveraging digital technology to improve access to mental health and epilepsy care: A longitudinal quasi-experimental study in Hlaing Thar Yar Township.

Background: Despite an estimated 8% prevalence of mental disorders in Myanmar, the treatment gap is high, up to 90%. This project aimed to assess the effects of a series of activities implemented by the Myanmar Medical Association over a 2-year period in Hlaing Thar Yar Township involving community health workers (CHWs) and general practitioners (GPs) on the identification, diagnosis and management of people with psychotic disorders, depression and epilepsy. Methods: Seventy-six CHWs were trained to raise awareness, identify people with mental disorders and refer them to GPs. Fifty GPs were upskilled to diagnose and manage patients. Prevalence, treatment gap and general population's Knowledge-Attitudes-Practices (KAP) were evaluated through door-to-door surveys, whilst CHWs' and GPs' KAP were measured pre-, and post-training as well as post-intervention. Patient identification, diagnosis and management were analysed through data collected by CHWs and GPs via smartphones and tablets. Findings: At baseline, the average treatment gap was 79·7%. During the 2 year-intervention, 1,378 suspected cases were referred by CHWs to GPs and 1,186 (86%) of them saw a GP. Among the 1,088 patients (92%) diagnosed, the concordance between GPs' diagnosis and CHWs' screening was 75·6%. For CHWs, knowledge improved post-training (16·9 vs. 15·3; p = 0·0010), whilst attitudes and practices improved post-intervention (17·1 vs. 15·7; p = 0·010 and 19·4 vs. 11·2; p < 0·0001 respectively). GPs' global KAP score improved post-training (14·6 vs. 12·8; p = 0·0010), and remained stable post-intervention. General population's KAP score improved between baseline and end-line (8·3 vs. 12·7; p < 0·0001). Interpretation: This project suggests that a 2-year intervention including the training of frontline health workers and raising awareness among the population can have positive outcomes and lead to a greater number of people with mental disorders being diagnosed and managed. Funding: This project was implemented as part of a partnership involving the Myanmar Medical Association, the Myanmar Mental Health Society, the World Association of Social Psychiatry, the Université Numérique Francophone Mondiale and Sanofi Global Health. It was funded by Sanofi Global Health, within the framework of the Fight Against STigma (FAST) Program.

Psychotropic drug-prescribing correlates of disorganized speech in Asians with schizophrenia: The REAP-AP study.

BACKGROUND: Although disorganized speech is seen as one of the nuclear features of schizophrenia, there have been few reports of disorganized speech-associated psychotropic drug-prescribing patterns in large samples of schizophrenia patients. OBJECTIVE: We aimed to examine the prevalence of disorganized speech and its correlates in terms of psychotropic drug prescribing, using the data from the Research on Asian Psychotropic Patterns for Antipsychotics (REAP-AP) study. METHOD: A total of 3744 patients with the ICD-10 diagnosis of schizophrenia were enrolled from 71 survey centers in 15 Asian countries/areas. An essential criterion of disorganized speech was that it was "severe enough to impair substantially effective communication" as defined in the DSM-5. A binary logistic model was fitted to identify the psychotropic drug-prescribing correlates of disorganized speech. RESULTS: After adjusting for the potential effects of confounding variables, the binary logistic regression model showed that the presence of disorganized speech was directly associated with adjunctive use of mood stabilizers (P < 0.001) and cumulative diazepam equivalent dose (P < 0.0001), and inversely associated with adjunctive use of anti-Parkinson drugs (P < 0.0001). CONCLUSION: The association between disorganized speech and adjunctive use of mood stabilizers could perhaps be understood in the context of a relationship with impulsiveness/aggressiveness, or in terms of deconstructing the Kraepelinian dualism.