External Validation of a Machine Learning Model for Schizophrenia Classification.

Background and Objective: Excellent generalizability is the precondition for the widespread practical implementation of machine learning models. In our previous study, we developed the schizophrenia classification model (SZ classifier) to identify potential schizophrenia patients in the Japanese population. The SZ classifier has exhibited impressive performance during internal validation. However, ensuring the robustness and generalizability of the SZ classifier requires external validation across independent sample sets. In this study, we aimed to present an external validation of the SZ classifier using outpatient data. Methods: The SZ classifier was trained by using online survey data, which incorporate demographic, health-related, and social comorbidity features. External validation was conducted using an outpatient sample set which is independent from the sample set during the model development phase. The model performance was assessed based on the sensitivity and misclassification rates for schizophrenia, bipolar disorder, and major depression patients. Results: The SZ classifier demonstrated a sensitivity of 0.75 when applied to schizophrenia patients. The misclassification rates were 59% and 55% for bipolar disorder and major depression patients, respectively. Conclusions: The SZ classifier currently encounters challenges in accurately determining the presence or absence of schizophrenia at the individual level. Prior to widespread practical implementation, enhancements are necessary to bolster the accuracy and diminish the misclassification rates. Despite the current limitations of the model, such as poor specificity for certain psychiatric disorders, there is potential for improvement if including multiple types of psychiatric disorders during model development.

Post-marketing surveillance of quetiapine fumarate extended-release tablets in patients with bipolar depression.

AIM: This study aimed to verify the real-world efficacy and safety of quetiapine fumarate extended-release tablets (Bipresso® 50 mg and 150 mg; marketing authorization holder is KYOWA Pharmaceutical Industry Co., Ltd., Osaka, Japan) in patients with bipolar depression. METHODS: We performed a post-marketing surveillance with an observation period of 12 weeks. RESULTS: In the safety analysis group (n = 345), adverse drug reactions (ADRs) occurred in 111 patients (32.17%). The most common ADRs (>1%) were somnolence in 55 patients (15.94%), akathisia in 11 (3.19%), dizziness in 10 (2.90%), weight increase in 6 (1.74%), thirst in 5 (1.45%), and hypersomnia, constipation, and nausea in 4 patients each (1.16%). The only severe ADR was one patient of suicidal ideation, and "longer time since the onset of the first episode" (p = 0.011) and "presence of complications" (p < 0.001) were identified as significant risk factors for the occurrence of ADRs. In the efficacy analysis group (n = 265), the average changes from baseline in the total Montgomery-Åsberg Depression Rating Scale (MADRS) score were -7.3 ± 8.8, -12.2 ± 10.7, -16.8 ± 12.7, and -13.2 ± 12.7 points after 4, 8, and 12 weeks, and at the last evaluation, respectively. The mean MADRS total score decrease had no significant association with maximum daily dose, diagnosis, and presence or absence of prior or concomitant treatment for bipolar disorder with mood stabilizers/antipsychotics/antidepressants. CONCLUSION: The efficacy of quetiapine fumarate extended-release tablets was confirmed in clinical practice, and no new safety concerns or risks were identified.

Antidepressants available in Japan for older people with major depressive disorder: A systematic review and meta-analysis.

AIM: To update the major depressive disorder (MDD) treatment guidelines of the Japanese Society of Mood Disorders, we conducted a systematic review and pairwise meta-analysis of double-blind, randomized, placebo-controlled trials of available antidepressants in Japan for older adults with MDD. METHODS: Outcome measures included response rate (primary), improvement in depressive symptom scale score, remission rate, all-cause discontinuation, discontinuation due to adverse events, and at least one adverse event. A random-effects model was used to calculate the risk ratio (RR) and standardized mean difference (SMD) with a 95% confidence interval (95% CI). RESULTS: Nine double-blind, randomized, placebo-controlled trials (n = 2145) were identified. No study has been conducted in Japan. Our meta-analysis included the following antidepressants: duloxetine, escitalopram, imipramine, sertraline, venlafaxine, and vortioxetine. Antidepressants have significantly higher response rates than placebo (RR [95% CI] = 1.38 [1.04, 1.83], p = 0.02). Antidepressants outperformed placebo in terms of improving depressive symptom scale score (SMD [95% CI] = -0.62 [-0.92, -0.33], p < 0.0001). However, antidepressants were associated with a higher discontinuation rate due to adverse events (RR [95% CI] = 1.94 [1.30, 2.88], p = 0.001) and a higher incidence of at least one adverse event (RR [95% CI] = 1.11 [1.02, 1.21], p = 0.02) compared to placebo. The groups did not differ significantly in terms of remission rate or all-cause discontinuation. CONCLUSIONS: Our meta-analysis concluded that treatment with antidepressants available in Japan is only weakly recommended for moderate to severe MDD in older adults.

A comparison of recurrence rates after discontinuation of second-generation antipsychotic long-acting injectable versus corresponding oral antipsychotic in the maintenance treatment of bipolar disorder: A systematic review.

It has been previously reported that among patients with schizophrenia that long-acting injectable (LAI) antipsychotic formulations can delay time to relapse longer when compared to their oral equivalents when patients discontinue therapy. Unanswered is whether this same pattern would be observed for patients with bipolar disorder receiving maintenance treatment. A systematic review was undertaken to identify relevant studies of LAI antipsychotics in maintenance treatment of bipolar disorder, employing a placebo-controlled randomized withdrawal design, and where equivalent studies using the corresponding oral formulation were also available. We found five studies [one aripiprazole monohydrate once monthly (AOM) study, one oral aripiprazole (OARI) study, two 2 weeks risperidone-LAI (RIS-LAI) studies, and one oral paliperidone (OPAL) study]. Numerically lower recurrence rates at 2, 4, 6, 8, 12, 16, 20, and 26 weeks were observed when AOM was discontinued when compared with discontinuation from OARI. Numerically lower recurrence rates at 2, 4, 6, 8, and 16 weeks were observed when RIS-LAI was discontinued when compared with discontinuation from OPAL. These results can be interpreted as a substantial delay in time to recurrence with a LAI antipsychotics formulation compared to the oral equivalent when medication is discontinued in patients with mania who had been stabilized on LAI antipsychotics or corresponding oral antipsychotics.

Comparison of brexpiprazole, aripiprazole, and placebo for Japanese major depressive disorder: A systematic review and network meta-analysis.

AIM: This systematic review and frequentist network meta-analysis used random-effects models is conducted to determine whether there are differences in the efficacy, acceptability, tolerability, and safety profiles of brexpiprazole (BRE) and aripiprazole (ARI) for Japanese with major depressive disorder (MDD) who were inadequately responsive to antidepressants. METHODS: Outcome measures were scores on the Montgomery Åsberg Depression Rating Scale (primary), the Clinical Global Impression severity scale, and social functioning scale; the non-response rate; the non-remission rate; all-cause discontinuation; discontinuation due to adverse events (DAE); at least one adverse event (1AE); serious adverse event, akathisia; tremor; weight gain. RESULTS: A literature search identified three double-blind, randomized, placebo-controlled trials. These comprised one BRE study (with a 1 mg/day [BRE1] and a 2 mg/day [BRE2]) and two ARI studies (with a 3 mg/day arm and a flexible-dose arm[within the dosage range approved in Japan]) (n = 1736). Both BRE and ARI demonstrated better efficacy than the placebo. BRE but not ARI had a higher DAE than the placebo. ARI but not BRE had a higher 1AE than the placebo. BRE and ARI had a higher risk of akathisia and weight gain than the placebo. There were no significant differences between BRE and ARI for any of the outcomes. Although BRE1 had good efficacy, it carried risk of weight gain. Although BRE2 also had efficacy, it carried risks of DAE, akathisia, and weight gain. However, the risk of akathisia in BRE2 was reduced by an initial dose of 0.5 mg/day rather than 1.0 mg/day. CONCLUSIONS: Overall BRE showed similar utility to ARI and a good risk-benefit balance.

Newer antidepressant for Japanese adults with major depressive disorder: A systematic review and meta-analysis.

INTRODUCTION: The question remains to be elucidated: "Is treatment with antidepressants at doses approved in Japan effective for Japanese patients with MDD?" It is crucial to confirm this in order to provide appropriate treatments for Japanese patients with major depressive disorder (MDD). Therefore, we conducted a systematic review and random-effects pairwise meta-analysis including these nine double-blind, randomized, placebo-controlled trials. METHODS: We calculated the standardized mean difference (SMD) and risk ratio (RR) with a 95% confidence interval (95% CI). RESULTS: Pooled newer antidepressants outperformed placebo regarding improvement of depressive symptom scale scores [SMD (95% CI) = -0.20 (-0.27, -0.12), p < 0.00001], response to treatment [RR (95% CI) = 1.23 (1.13, 1.32), p < 0.00001], and remission rate [RR (95% CI) = 1.30 (1.16, 1.45), p < 0.00001]. Although all-cause discontinuation was not significantly different between the treatment groups, the pooled antidepressant group showed a higher discontinuation rate due to adverse event [RR (95% CI) = 1.60 (1.13, 2.26), p = 0.007] and a higher incidence of at least one adverse event than the placebo group [RR (95% CI) = 1.13 (1.08, 1.18), p < 0.00001]. DISCUSSION: We concluded that newer antidepressants are effective for Japanese adults with MDD although the clinicians must monitor the health conditions of these individuals.

Classifying Schizophrenia Cases by Artificial Neural Network Using Japanese Web-Based Survey Data: Case-Control Study.

BACKGROUND: In Japan, challenges were reported in accurately estimating the prevalence of schizophrenia among the general population. Retrieving previous studies, we investigated that patients with schizophrenia were more likely to experience poor subjective well-being and various physical, psychiatric, and social comorbidities. These factors might have great potential for precisely classifying schizophrenia cases in order to estimate the prevalence. Machine learning has shown a positive impact on many fields, including epidemiology, due to its high-precision modeling capability. It has been applied in research on mental disorders. However, few studies have applied machine learning technology to the precise classification of schizophrenia cases by variables of demographic and health-related backgrounds, especially using large-scale web-based surveys. OBJECTIVE: The aim of the study is to construct an artificial neural network (ANN) model that can accurately classify schizophrenia cases from large-scale Japanese web-based survey data and to verify the generalizability of the model. METHODS: Data were obtained from a large Japanese internet research pooled panel (Rakuten Insight, Inc) in 2021. A total of 223 individuals, aged 20-75 years, having schizophrenia, and 1776 healthy controls were included. Answers to the questions in a web-based survey were formatted as 1 response variable (self-report diagnosed with schizophrenia) and multiple feature variables (demographic, health-related backgrounds, physical comorbidities, psychiatric comorbidities, and social comorbidities). An ANN was applied to construct a model for classifying schizophrenia cases. Logistic regression (LR) was used as a reference. The performances of the models and algorithms were then compared. RESULTS: The model trained by the ANN performed better than LR in terms of area under the receiver operating characteristic curve (0.86 vs 0.78), accuracy (0.93 vs 0.91), and specificity (0.96 vs 0.94), while the model trained by LR showed better sensitivity (0.63 vs 0.56). Comparing the performances of the ANN and LR, the ANN was better in terms of area under the receiver operating characteristic curve (bootstrapping: 0.847 vs 0.773 and cross-validation: 0.81 vs 0.72), while LR performed better in terms of accuracy (0.894 vs 0.856). Sleep medication use, age, household income, and employment type were the top 4 variables in terms of importance. CONCLUSIONS: This study constructed an ANN model to classify schizophrenia cases using web-based survey data. Our model showed a high internal validity. The findings are expected to provide evidence for estimating the prevalence of schizophrenia in the Japanese population and informing future epidemiological studies.

Serotonin 3 receptor antagonists for obsessive-compulsive disorder: A systematic review and pairwise meta-analysis.

The benefits of serotonin 3 receptor antagonists (5-HT3R-As) in obsessive-compulsive disorder (OCD) treatment remain unclear. Thus, this study aimed to perform a systematic review and a random-effects meta-analysis, including double-blind, randomized, placebo-controlled trials (DBRPCTs). The outcomes include the Yale-Brown Obsessive Compulsive Scale (Y-BOCS) total score (primary), Y-BOCS obsession subscale score, Y-BOCS compulsive subscale score, treatment response, remission rate, all-cause discontinuation, and incidence of individual adverse events (nervousness/restlessness/anxiety, insomnia, headache, dizziness/lightheadedness, decreased appetite, constipation, nausea/vomiting, diarrhea, dry mouth, sweating/increased perspiration, itching/pruritus, tremor, and sexual dysfunction/decreased libido). The mean differences (MD) for continuous outcomes and risk ratios for dichotomous outcomes with 95% confidence intervals (CIs) were calculated. Our study included 10 DBRPCTs (n = 628). Pooled 5-HT3R-As outperformed placebo regarding Y-BOCS total score (MD = -5.08, 95% CI = -7.04, -3.12, N = 9, n = 560), Y-BOCS obsession subscale score, Y-BOCS compulsive subscale score, treatment response, and remission rate. Individually, all 5-HT3R-As outperformed placebo regarding Y-BOCS total score (granisetron: MD = -5.59, 95% CI = -8.79, -2.39, N = 3, n = 178, ondansetron: MD = -5.72, 95% CI = -8.06, -3.37, N = 6, n = 331, tropisetron: MD = -2.87, 95% CI = -5.19, -0.550, N = 1, n = 96). However, all-cause discontinuation and incidence of individual adverse events between pooled 5-HT3R-As and placebo were not significantly different. In conclusion, our meta-analysis suggested 5-HT3R-As as efficacious for symptom improvement in individuals with OCD. However, the number of individuals included in each study was small; thus, a replication randomized trial of 5-HT3R-As should be conducted using a larger sample size.

Valbenazine for tardive dyskinesia: a systematic review and network meta-analysis.

To date, the role of valbenazine (VAL) in a dose-dependent increase in efficacy for tardive dyskinesia (TD) and in the worsening of acceptability and tolerability in a dose-dependent manner remains to be elucidated. Thus, in this systematic review and frequentist network meta-analysis, we compared 16 outcomes of VAL80 mg/d (VAL80) with VAL40 mg/d (VAL40) related to the efficacy, acceptability, tolerability, and safety in the treatment of patients with TD. Using a 95% confidence interval, we calculated the standardized mean difference for continuous variables and the risk ratio for dichotomous variables. Our results demonstrated that both VAL80 and VAL40 were superior to the placebo in terms of Abnormal Involuntary Movement Scale (AIMS) total score, Clinical Global Impression of Change-TD, and response to treatment, but VAL80 outperformed VAL40 in terms of AIMS score and response to treatment. However, any active therapy and placebo treatment groups did not have significant differences in acceptability, tolerability, and safety outcomes and similarly between VAL80 and VAL40 in any other outcomes. In conclusions, VAL could be increased from VAL40 to VAL80 if a patient with TD adequately tolerates VAL40 but treatment response is poor.

Intermittent theta burst stimulation vs. high-frequency repetitive transcranial magnetic stimulation for major depressive disorder: A systematic review and meta-analysis.

Our meta-analysis demonstrated that intermittent theta burst stimulation (iTBS)/bilateral-TBS (Bi-TBS) and high-frequency repetitive transcranial magnetic stimulation (HF-rTMS)/bilateral-rTMS (Bi-rTMS) had similar efficacy, acceptability, and safety profiles for antidepressant treatment-resistant major depressive disorder (AD-TRD). In our sensitivity analysis that excluded a study that compared Bi-TBS with Bi-rTMS for older adults, all efficacy outcomes were also comparable between iTBS and HF-rTMS. Because iTBS does not require higher stimulation intensity and a longer stimulus time than conventional HF-rTMS protocols, we speculated that for those with AD-TRD, iTBS/Bi-TBS is a more helpful therapeutic modality in clinical practice than HF-rTMS/Bi-rTMS.

The efficacy, safety, and adverse events of azapirones in anxiety disorders: A systematic review and meta-analysis of randomized controlled trials.

Azapirones have been proposed as anxiety and mood modulators. We assessed azapirones' viability in anxiety disorders via systematic review and random-effects meta-analysis, inquiring PubMed/MEDLINE/CENTRAL/WHO-ICTRP/WebOfScience/VIP up-to 05/01/2023. We conducted sensitivity, and subgroup analyses assessing heterogeneity, publication bias, risk of bias, and confidence in the evidence within the GRADE framework. Symptom reduction (mean difference/MD), study-defined response (risk ratios/RRs), and acceptability were co-primary outcomes. Adverse events and withdrawal were secondary. Seventy studies were included. In generalized anxiety disorder (GAD), azapirones largely outperformed placebo (MD=-4.91, 95%C.I.[-5.91, -3.90], Hedges'g -1.37 [-1.02, -0.73]), k = 22, n = 2,567; RR=1.64, 95%C.I.[1.45, 1.86], k = 9, n = 1,346). While azapirones overlapped benzodiazepines in symptom reduction (MD=-0.12, 95%C.I.[-0.70, 0.45], k = 34, n = 3,160), they were slightly outperformed in response rate (RR=0.94, 95%C.I.[0.90, 0.99], k = 18, n = 2,423). Azapirones overlapped SRIs (MD=0.09, 95%C.I.[-0.49, 0.67], k = 8, n = 747; RR=0.97, 95%C.I.[0.89, 1.07], k = 7, n = 737). Confidence in estimates was high/moderate vs. placebo, moderate/low vs. benzodiazepine, very-low vs. SRIs. Azapirones failed to outperform the placebo in panic and social anxiety disorders. Azapirones overlapped placebo and SRIs in drop-out rates, while they showed higher treatment discontinuation rates than benzodiazepines (RR=1.33, 95%C.I.[1.16, 1.53], k = 23, n = 2,768). Azapirones caused less sedation/fatigue/drowsiness/weakness/cognitive issues than benzodiazepines, resembling placebo. They caused more nausea and dizziness than placebo, more headache and nausea than benzodiazepines, and less nausea and xerostomia than SRIs. Azapirones proved effective and relatively well-tolerated for GAD. They should be preferred over benzodiazepines, especially in the long-term, considering their lower sedation and addiction potential, representing a potential SRI alternative. Further research is warranted to prove efficacy in panic and social anxiety.

Physical, Psychiatric, and Social Comorbidities of Individuals with Schizophrenia Living in the Community in Japan.

The physical, psychiatric, and social comorbidities interfere with the everyday activities of community-dwelling individuals with schizophrenia and increase the risk of their readmission. However, these comorbidities have not been investigated comprehensively in Japan. We conducted a self-reported internet survey in February 2022 to identify individuals aged 20-75 years with and without schizophrenia using a prevalence case-control study. The survey compared physical comorbidities such as being overweight, hypertension, and diabetes; psychiatric comorbidities such as depressive symptoms and sleep disturbances; social comorbidities such as employment status, household income, and social support between participants with and without schizophrenia. A total of 223 participants with schizophrenia and 1776 participants without schizophrenia were identified. Participants with schizophrenia were more likely to be overweight and had a higher prevalence of hypertension, diabetes, and dyslipidemia than participants without schizophrenia. Additionally, depressive symptoms, unemployment, and non-regular employment were more prevalent in participants with schizophrenia than those without schizophrenia. These results highlight the necessity of comprehensive support and interventions addressing physical, psychiatric, and social comorbidities in individuals with schizophrenia in the community. In conclusion, effective interventions for managing comorbidities in individuals with schizophrenia are necessary to enable them to continue to live in the community.