Visualizing machine learning-based predictions of postpartum depression risk for lay audiences.

OBJECTIVES: To determine if different formats for conveying machine learning (ML)-derived postpartum depression risks impact patient classification of recommended actions (primary outcome) and intention to seek care, perceived risk, trust, and preferences (secondary outcomes). MATERIALS AND METHODS: We recruited English-speaking females of childbearing age (18-45 years) using an online survey platform. We created 2 exposure variables (presentation format and risk severity), each with 4 levels, manipulated within-subject. Presentation formats consisted of text only, numeric only, gradient number line, and segmented number line. For each format viewed, participants answered questions regarding each outcome. RESULTS: Five hundred four participants (mean age 31 years) completed the survey. For the risk classification question, performance was high (93%) with no significant differences between presentation formats. There were main effects of risk level (all P < .001) such that participants perceived higher risk, were more likely to agree to treatment, and more trusting in their obstetrics team as the risk level increased, but we found inconsistencies in which presentation format corresponded to the highest perceived risk, trust, or behavioral intention. The gradient number line was the most preferred format (43%). DISCUSSION AND CONCLUSION: All formats resulted high accuracy related to the classification outcome (primary), but there were nuanced differences in risk perceptions, behavioral intentions, and trust. Investigators should choose health data visualizations based on the primary goal they want lay audiences to accomplish with the ML risk score.

Gender disparity in telehealth usage in Bangladesh during COVID-19.

BACKGROUND AND AIMS: Telehealth allows healthcare workers to see patients virtually in locations that were not accessible previously, which has reduced cost and time and saved lives. The research aims to examine gender disparity among telehealth usage during the pandemic in 2020. This study will leverage a timely national experiment to evaluate the users of telehealth across the Bangladeshi population. METHODS: We obtained de-identified data for 200 patients among outpatient telehealth visits from Global Health Data Exchange as it captured telehealth use throughout Bangladesh. RESULTS: The analysis showed that male patients had a higher dependency on telehealth than female patients. 14% of the female patients opted for telehealth visits only with 57% cases of missed doses of medication, compared to males with 20% of them choosing telehealth visits and 29% missing their doses of medication. We found that the youngest age group, 16-25, had the highest dependence on telehealth compared to any other age group, and the lowest dependence was among the oldest age group of 45 years and above. CONCLUSIONS: There was a strong association between telehealth use and gender disparity with p value â€‹= â€‹0.02 â€‹< â€‹0.05. Longitudinal and geographical data are needed to understand more about the gender disparities and impact in telehealth utilizations.