Background: Artificial intelligence–assisted interactive health promotion systems are useful tools for the management of musculoskeletal conditions. Objective: This study aimed to explore the effects of web-based video patient education and strengthening exercise therapy, using a mobile messaging app, on work productivity and pain in patients with chronic low back pain (CLBP) receiving pharmacological treatment. Methods: Patients with CLBP were randomly allocated to either the exercise group, who received education and exercise therapy using a mobile messaging app, or the conventional group. For patient education, a web-based video program was used to provide evidence-based thinking regarding the importance of a cognitive behavioral approach for CLBP. The exercise therapy was developed in accordance with the recommendations for alignment, core muscles, and endogenous activation, including improvement of posture and mobility for proper alignment, stimulation and/or strengthening of deep muscles for spinal stability, and operation of intrinsic pain for the activation of endogenous substances by aerobic exercise. Both groups continued to receive the usual medical care with pharmacological treatment. The end points were changes in work productivity, pain intensity, quality of life, fear of movement, and depression. The observation period for this study was 12 weeks. An analysis adjusted for baseline values, age at the time of consent acquisition, sex, and willingness to strengthen the exercise therapy was performed. Results: The exercise and conventional groups included 48 and 51 patients, with a mean age of 47.9 years (SD 10.2 years; n=27, 56.3% male patients) and 46.9 years (SD 12.3 years; n=28, 54.9% male patients) in the full analysis set, respectively. No significant impact of these interventions on work productivity was observed in the exercise group compared with the conventional group (primary end point: Quantity and Quality method; 0.062 vs 0.114; difference between groups −0.053, 95% CI −0.184 to 0.079; P=.43). However, the exercise group showed consistently better trends for the other end points than did the conventional group. Compared with the conventional group, the exercise group showed a significant improvement in the symptoms of low back pain (3.2 vs 3.8; difference between groups −0.5, 95% CI −1.1 to 0.0; P=.04), quality of life (EuroQoL 5 Dimensions 5 Level: 0.068 vs 0.006; difference between groups 0.061, 95% CI 0.008 to 0.114; P=.03), and fear of movement at week 12 (−2.3 vs 0.5; difference between groups −2.8, 95% CI −5.5 to −0.1; P=.04). Conclusions: This study suggests that patient education and strengthening exercise therapy using a mobile messaging app may be useful for treating CLBP. This study does not reveal the effect of therapeutic interventions on CLBP on work productivity. Thus, further research is required to assess work productivity with therapeutic interventions. Trial Registration: University Hospital Medical Information Network Clinical Trials Registry UMIN000041037; https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000046866

Background: Work characteristics, such as teleworking rate, have been studied in relation to stress. However, the use of work-related data to improve a high-performance stress prediction model that suits an individual’s lifestyle has not been evaluated. Objective: This study aims to develop a novel, high-performance algorithm to predict an employee’s stress among a group of employees with similar working characteristics. Methods: This prospective observational study evaluated participants’ responses to web‑based questionnaires, including attendance records and data collected using a wearable device. Data spanning 12 weeks (between January 17, 2022, and April 10, 2022) were collected from 194 Shionogi Group employees. Participants wore the Fitbit Charge 4 wearable device, which collected data on daily sleep, activity, and heart rate. Daily work shift data included details of working hours. Weekly questionnaire responses included the K6 questionnaire for depression/anxiety, a behavioral questionnaire, and the number of days lunch was missed. The proposed prediction model used a neighborhood cluster (N=20) with working-style characteristics similar to those of the prediction target person. Data from the previous week predicted stress levels the following week. Three models were compared by selecting appropriate training data: (1) single model, (2) proposed method 1, and (3) proposed method 2. Shapley Additive Explanations (SHAP) were calculated for the top 10 extracted features from the Extreme Gradient Boosting (XGBoost) model to evaluate the amount and contribution direction categorized by teleworking rates (mean): low: <0.2 (more than 4 days/week in office), middle: 0.2 to <0.6 (2 to 4 days/week in office), and high: ≥0.6 (less than 2 days/week in office). Results: Data from 190 participants were used, with a teleworking rate ranging from 0% to 79%. The area under the curve (AUC) of the proposed method 2 was 0.84 (true positive vs false positive: 0.77 vs 0.26). Among participants with low teleworking rates, most features extracted were related to sleep, followed by activity and work. Among participants with high teleworking rates, most features were related to activity, followed by sleep and work. SHAP analysis showed that for participants with high teleworking rates, skipping lunch, working more/less than scheduled, higher fluctuations in heart rate, and lower mean sleep duration contributed to stress. In participants with low teleworking rates, coming too early or late to work (before/after 9 AM), a higher/lower than mean heart rate, lower fluctuations in heart rate, and burning more/fewer calories than normal contributed to stress. Conclusions: Forming a neighborhood cluster with similar working styles based on teleworking rates and using it as training data improved the prediction performance. The validity of the neighborhood cluster approach is indicated by differences in the contributing features and their contribution directions among teleworking levels. Trial Registration: UMIN UMIN000046394; https://www.umin.ac.jp/ctr/index.htm

Recurrent outbreaks of coronavirus disease 2019 (COVID-19) in Japan highlight the continued need for effective prevention, particularly household transmission. This study clarifies the epidemiological profile of household transmission of COVID-19 and influenza by quantifying transmission rates according to demographic and relational characteristics. An anonymized health insurance claims database was used to identify index patients diagnosed with COVID-19 or influenza between November 2021 and August 2023. Transmission events were defined as cases in which household members were diagnosed with the same infection in the week following the index patient’s diagnosis (Day 1). Analyses were stratified by the age of the index patients and age-based transmission patterns between index patients and household members. A total of 1,001,509 index patients with COVID-19 and 207,090 with influenza met the inclusion criteria. Transmission rates were highest among index patients aged <12 years (COVID-19, 40.17%; influenza, 33.51%). Transmission from children was disproportionately high, while age-combination analysis demonstrated elevated transmission both from and to children for both diseases. COVID-19 exhibited increased transmission among adults. As the primary drivers of household transmission for both COVID-19 and influenza, preventive strategies should be tailored to children. COVID-19 interventions must also address transmission among adults to strengthen household-level infection control.

Background: Perinatal depression is a global health concern linked to adverse maternal and neonatal outcomes. Although evidence-based psychological interventions, such as interpersonal psychotherapy (IPT), are effective, women lack access to in-person perinatal care. Smartphone-based interventions may offer scalable support; however, evidence from randomized controlled trials (RCTs) evaluating IPT-informed smartphone interventions remains limited. This study assessed the acceptability and efficacy of an IPT-informed smartphone intervention for perinatal mental well-being. Methods: Participants were recruited nationwide through online advertisements and postcards. In this nonblinded RCT, 350 pregnant women were assigned to a fully self-guided smartphone application (intervention) or usual care (control). No minimum depression symptom score was required for participation. Acceptability in the intervention group at 8 weeks after enrolment was indicated by the Japanese version of the Client Satisfaction Questionnaire-8 (CSQ-8J) scores of ≥17. Efficacy was defined as the change in Patient Health Questionnaire-9 (PHQ-9) scores from baseline to 8 weeks following enrolment. Depressive symptoms were assessed at 1 month postpartum. Results: The application achieved acceptability, with 90.2% (157/174) of participants scoring ≥17 on the CSQ-8J. No significant between-group differences in depressive symptoms were observed during pregnancy (standardized mean difference (SMD) = 0.11). At 1 month postpartum, the intervention group exhibited significantly lower depressive symptom scores (SMD = 0.28). Conclusions: The smartphone application was highly acceptable. While no significant differences in depressive symptoms were observed during pregnancy, differences favoring the intervention group were observed at 1 month postpartum. An IPT-informed smartphone intervention may represent a promising approach to perinatal mental health support.

BACKGROUND Work characteristics, such as teleworking rate, have been studied in relation to stress. However, the use of work-related data to improve a high-performance stress prediction model that suits an individual’s lifestyle has not been evaluated. OBJECTIVE This study aims to develop a novel, high-performance algorithm to predict an employee’s stress among a group of employees with similar working characteristics. METHODS This prospective observational study evaluated participants’ responses to web‑based questionnaires, including attendance records and data collected using a wearable device. Data spanning 12 weeks (between January 17, 2022, and April 10, 2022) were collected from 194 Shionogi Group employees. Participants wore the Fitbit Charge 4 wearable device, which collected data on daily sleep, activity, and heart rate. Daily work shift data included details of working hours. Weekly questionnaire responses included the K6 questionnaire for depression/anxiety, a behavioral questionnaire, and the number of days lunch was missed. The proposed prediction model used a neighborhood cluster (N=20) with working-style characteristics similar to those of the prediction target person. Data from the previous week predicted stress levels the following week. Three models were compared by selecting appropriate training data: (1) single model, (2) proposed method 1, and (3) proposed method 2. Shapley Additive Explanations (SHAP) were calculated for the top 10 extracted features from the Extreme Gradient Boosting (XGBoost) model to evaluate the amount and contribution direction categorized by teleworking rates (mean): low: <0.2 (more than 4 days/week in office), middle: 0.2 to <0.6 (2 to 4 days/week in office), and high: ≥0.6 (less than 2 days/week in office). RESULTS Data from 190 participants were used, with a teleworking rate ranging from 0% to 79%. The area under the curve (AUC) of the proposed method 2 was 0.84 (true positive vs false positive: 0.77 vs 0.26). Among participants with low teleworking rates, most features extracted were related to sleep, followed by activity and work. Among participants with high teleworking rates, most features were related to activity, followed by sleep and work. SHAP analysis showed that for participants with high teleworking rates, skipping lunch, working more/less than scheduled, higher fluctuations in heart rate, and lower mean sleep duration contributed to stress. In participants with low teleworking rates, coming too early or late to work (before/after 9 AM), a higher/lower than mean heart rate, lower fluctuations in heart rate, and burning more/fewer calories than normal contributed to stress. CONCLUSIONS Forming a neighborhood cluster with similar working styles based on teleworking rates and using it as training data improved the prediction performance. The validity of the neighborhood cluster approach is indicated by differences in the contributing features and their contribution directions among teleworking levels. CLINICALTRIAL UMIN UMIN000046394; https://www.umin.ac.jp/ctr/index.htm