Background: The screening process for systematic reviews is resource-intensive. Although previous machine learning solutions have reported reductions in workload, they risked excluding relevant papers. Objective: We evaluated the performance of a 3-layer screening method using GPT-3.5 and GPT-4 to streamline the title and abstract-screening process for systematic reviews. Our goal is to develop a screening method that maximizes sensitivity for identifying relevant records. Methods: We conducted screenings on 2 of our previous systematic reviews related to the treatment of bipolar disorder, with 1381 records from the first review and 3146 from the second. Screenings were conducted using GPT-3.5 (gpt-3.5-turbo-0125) and GPT-4 (gpt-4-0125-preview) across three layers: (1) research design, (2) target patients, and (3) interventions and controls. The 3-layer screening was conducted using prompts tailored to each study. During this process, information extraction according to each study’s inclusion criteria and optimization for screening were carried out using a GPT-4–based flow without manual adjustments. Records were evaluated at each layer, and those meeting the inclusion criteria at all layers were subsequently judged as included. Results: On each layer, both GPT-3.5 and GPT-4 were able to process about 110 records per minute, and the total time required for screening the first and second studies was approximately 1 hour and 2 hours, respectively. In the first study, the sensitivities/specificities of the GPT-3.5 and GPT-4 were 0.900/0.709 and 0.806/0.996, respectively. Both screenings by GPT-3.5 and GPT-4 judged all 6 records used for the meta-analysis as included. In the second study, the sensitivities/specificities of the GPT-3.5 and GPT-4 were 0.958/0.116 and 0.875/0.855, respectively. The sensitivities for the relevant records align with those of human evaluators: 0.867-1.000 for the first study and 0.776-0.979 for the second study. Both screenings by GPT-3.5 and GPT-4 judged all 9 records used for the meta-analysis as included. After accounting for justifiably excluded records by GPT-4, the sensitivities/specificities of the GPT-4 screening were 0.962/0.996 in the first study and 0.943/0.855 in the second study. Further investigation indicated that the cases incorrectly excluded by GPT-3.5 were due to a lack of domain knowledge, while the cases incorrectly excluded by GPT-4 were due to misinterpretations of the inclusion criteria. Conclusions: Our 3-layer screening method with GPT-4 demonstrated acceptable level of sensitivity and specificity that supports its practical application in systematic review screenings. Future research should aim to generalize this approach and explore its effectiveness in diverse settings, both medical and nonmedical, to fully establish its use and operational feasibility.

Monopharmacy with antipsychotics and antidepressants is the first-line treatment for schizophrenia and major depressive disorder (MDD) in most clinical guidelines, while polypharmacy with psychotropic agents in the treatment of schizophrenia is common in clinical practice. There are no detailed data on the prescription patterns for inpatients with mental illness with reliable diagnoses made by treating psychiatrists. We gathered prescription data at discharge from 2177 patients with schizophrenia and 1238 patients with MDD from October 2016 to March 2018. The patients with schizophrenia aged between 60 and 79 were prescribed lower doses of antipsychotics and hypnotics/anxiolytics than those aged between 40 and 59. There were significant differences between the prescription rate of antipsychotics in the patients with schizophrenia and that of antidepressants in the patients with MDD. The frequency of concomitant drugs such as anti-Parkinson drugs, anxiolytics/hypnotics and mood stabilizers in the subjects with schizophrenia prescribed antipsychotic polypharmacy was significantly higher than that with monotherapy. For the patients with schizophrenia, olanzapine, risperidone, aripiprazole, quetiapine, and blonanserin were the five most prescribed antipsychotics. For the patients with MDD, mirtazapine, duloxetine, escitalopram, trazodone and sertraline were the five most prescribed antidepressants. Our results showed the use of high doses of antipsychotics, high percentages of antipsychotic polypharmacy and concurrent use of hypnotics/anxiolytics in patients with schizophrenia. Notably, these data were collected before intensive instruction regarding the guidelines; therefore, we need to assess the change in the prescription pattern post guideline instruction.

Patients with chronic insomnia are prone to long-term use of hypnotics. Reported risk factors include aging, female sex, and comorbid psychiatric disorders. However, most previous studies have been cross-sectional cohort studies. We conducted a retrospective cohort study using medical service payment data for 330,000 people to determine the duration of prescription of hypnotics and the risk factors for long-term use. We followed up 3981 patients (2382 M, 1599 F, age 40.3 ± 12.4 years) who were prescribed hypnotics for the first time between April 2005 and March 2008. Of these 3981 patients, 59.6% were prescribed hypnotics for only 1 month, 11.3% were prescribed hypnotics for 2 consecutive months, and 10.1% of patients continued receiving prescriptions for the entire 12-month observation period. In multiple logistic time-dependent Cox analyses, use of antidepressants, mean dose of hypnotics, and advanced age were significantly associated with long-term use of hypnotics (p < 0.01). In an analysis of the association between long-term use of hypnotics and prescribed dosage, high monthly dose, advanced age, and department of first visit were significantly associated with long-term use (p < 0.01). These clinical indicators may be effective for early identification of patients with insomnia who are at high risk of developing physical dependence on hypnotics.

Aim: This systematic review and meta‐analysis evaluated whether bright light therapy (BLT) is an effective and safe treatment for manic/depressive symptoms and a preventive measure for recurrent mood episodes in patients with bipolar disorder.Methods: A literature search of major electronic databases was conducted in June 2019, including all published articles up to that date. Two researchers independently selected relevant publications, extracted data, and evaluated methodological quality according to the Cochrane criteria.Results: Six randomized controlled trials (RCT) evaluated the efficacy of BLT for bipolar depression. A meta‐analysis found no significant differences between BLT and placebo for the following outcomes: (i) rates of remission from depressive episodes (risk ratio [RR]: 1.81, 95% confidence interval [CI]: 0.43 to 7.64, P = 0.42); (ii) depressive symptom scores (standardized mean difference: −0.25, 95%CI: −0.74 to 0.23, P = 0.30); and (iii) rates of manic switching (RR: 1.00, 95%CI: 0.28 to 3.59, P = 0.26). The sensitivity analysis for studies with low overall indirectness did show a significant antidepressant effect for BLT (RR: 3.09, 95%CI: 1.62 to 5.90, P = 0.006). No RCT investigated the effect of BLT in preventing the recurrence of mood episodes in the euthymic state or in improving manic symptoms in the manic state. No severe adverse events were reported.Conclusion: While a meta‐analysis was unable to demonstrate the efficacy of BLT for bipolar depression, a sensitivity analysis did show a significant effect. Further well‐designed studies are needed to clarify the effectiveness of BLT, not only for the depressive state but also for other states, in the treatment of bipolar disorder.

Long‐term use of benzodiazepines (BZD) is not recommended for the treatment of anxiety disorders. Cognitive behavioral therapy (CBT) is an effective treatment option for discontinuation of BZD in patients with anxiety disorders. This systematic review and meta‐analysis sought to clarify whether CBT is effective for discontinuing BZD anxiolytics in patients with anxiety disorders. This study was preregistered with PROSPERO (registration number: CRD42019125263). A literature search of major electronic databases was conducted in December 2018. Three randomized controlled trials were included in this review, and meta‐analyses were performed. The proportion of discontinuing BZD anxiolytics was significantly higher in the CBT plus gradual tapering group than in the gradual tapering alone group, both in the short term (3 months after allocation; number needed to treat: 3.2, 95% confidence interval [CI]: 2.1 to 7.1; risk ratio: 1.96, 95%CI: 1.29 to 2.98, P = 0.002, three studies) and long term (6 to 12 months after allocation; number needed to treat: 2.8, 95%CI: 1.9 to 5.3; risk ratio: 2.16, 95%CI: 1.41 to 3.32, P = 0.0004, three studies). CBT may be effective for discontinuing BZD anxiolytics, both in the short term and in the long term after the allocation. Further studies with larger sample sizes are necessary to draw definitive conclusions regarding the efficacy and safety of CBT for discontinuing BZD anxiolytics in patients with anxiety disorders.