In the wake of recent advances in artificial intelligence research, precision psychiatry using machine learning techniques represents a new paradigm. The D-amino acid oxidase (DAO) protein and its interaction partner, the D-amino acid oxidase activator (DAOA, also known as G72) protein, have been implicated as two key proteins in the N-methyl-D-aspartate receptor (NMDAR) pathway for schizophrenia. Another potential biomarker in regard to the etiology of schizophrenia is melatonin in the tryptophan catabolic pathway. To develop an ensemble boosting framework with random undersampling for determining disease status of schizophrenia, we established a prediction approach resulting from the analysis of genomic and demographic variables such as DAO levels, G72 levels, melatonin levels, age, and gender of 355 schizophrenia patients and 86 unrelated healthy individuals in the Taiwanese population. We compared our ensemble boosting framework with other state-of-the-art algorithms such as support vector machine, multilayer feedforward neural networks, logistic regression, random forests, naive Bayes, and C4.5 decision tree. The analysis revealed that the ensemble boosting model with random undersampling [area under the receiver operating characteristic curve (AUC) = 0.9242 ± 0.0652; sensitivity = 0.8580 ± 0.0770; specificity = 0.8594 ± 0.0760] performed maximally among predictive models to infer the complicated relationship between schizophrenia disease status and biomarkers. In addition, we identified a causal link between DAO and G72 protein levels in influencing schizophrenia disease status. The study indicates that the ensemble boosting framework with random undersampling may provide a suitable method to establish a tool for distinguishing schizophrenia patients from healthy controls using molecules in the NMDAR and tryptophan catabolic pathways.

Aims More than one-half of betel-quid (BQ) chewers have betel-quid use disorder (BUD). However, no medication has been approved. We performed a randomised clinical trial to test the efficacy of taking escitalopram and moclobemide antidepressants on betel-quid chewing cessation (BQ-CC) treatment. Methods We enrolled 111 eligible male BUD patients. They were double-blinded, placebo-controlled and randomised into three treatment groups: escitalopram 10 mg/tab daily, moclobemide 150 mg/tab daily and placebo. Patients were followed-up every 2 weeks and the length of the trial was 8 weeks. The primary outcome was BQ-CC, defined as BUD patients who continuously stopped BQ use for ⩾6 weeks. The secondary outcomes were the frequency and amount of BQ intake, and two psychological rating scales. Several clinical adverse effects were measured during the 8-week treatment. Results Intention-to-treat analysis shows that after 8 weeks, two (5.4%), 13 (34.2%) and 12 (33.3%) of BUD patients continuously quit BQ chewing for ⩾6 weeks among placebo, escitalopram, moclobemide groups, respectively. The adjusted proportion ratio of BQ-CC was 6.3 (95% CI 1.5–26.1) and 6.8 (95% CI 1.6–28.0) for BUD patients who used escitalopram and moclobemide, respectively, as compared with those who used placebo. BUD patients with escitalopram and moclobemide treatments both exhibited a significantly lower frequency and amount of BQ intake at the 8th week than those with placebo. Conclusions Prescribing a fixed dose of moclobemide and escitalopram to BUD patients over 8 weeks demonstrated treatment benefits to BQ-CC. Given a relatively small sample, this study provides preliminary evidence and requires replication in larger trials.

ObjectivesSeveral studies suggested that antidepressant use may increase or decrease the risk of cancer occurrence, depending on specific cancer types. The possible carcinogenic effect of antidepressants has received substantial attention; however, evidence remains inconclusive. Here we investigated associations between the use of antidepressants and occurrences of oral cancer (OC).MethodsTwo million samples were randomly collected from the National Health Insurance Research Database in Taiwan, which covers 98% of the total population (23 million). All patients from2000 to 2009 were followed up. We identified 5103 patients newly diagnosed with OC after antidepressants use in addition to 20,412 non-OC matched subjects and 95,452 unmatched non-OC subjects.ResultsIn nested case control analysis, factors associating with OC, including age [OR = 1.02; 95% confidence interval (CI) = 1.01–1.03) and male (OR = 5.30; 95% CI = 4.92–5.70) were independently associated with increased risk of OC. Based on the functions of antidepressants, antidepressants treatment medications were further classified to investigate risk of OC. Selective serotonin reuptake inhibitors (OR = 0.61; 95% CI = 0.53–0.70) and tricyclic antidepressants (OR = 0.57; 95% CI = 0.52–0.63) were associated with reduced risk of OC. The risk of developing OC among subjects taking antidepressants was less than 26% [hazard ratio (HR) =0.74; 95% CI = 0.68–0.81] in prospective cohort study. The effect of a cumulative duration and dose was a significantly reduced risk of OC.ConclusionsThe association between antidepressant use and decreasing OC risk were demonstrated by both prospective and nested case–control studies.