HealthPrism: A Visual Analytics System for Exploring Children's Physical and Mental Health Profiles with Multimodal Data.

The correlation between children's personal and family characteristics (e.g., demographics and socioeconomic status) and their physical and mental health status has been extensively studied across various research domains, such as public health, medicine, and data science. Such studies can provide insights into the underlying factors affecting children's health and aid in the development of targeted interventions to improve their health outcomes. However, with the availability of multiple data sources, including context data (i.e., the background information of children) and motion data (i.e., sensor data measuring activities of children), new challenges have arisen due to the large-scale, heterogeneous, and multimodal nature of the data. Existing statistical hypothesis-based and learning model-based approaches have been inadequate for comprehensively analyzing the complex correlation between multimodal features and multi-dimensional health outcomes due to the limited information revealed. In this work, we first distill a set of design requirements from multiple levels through conducting a literature review and iteratively interviewing 11 experts from multiple domains (e.g., public health and medicine). Then, we propose HealthPrism, an interactive visual and analytics system for assisting researchers in exploring the importance and influence of various context and motion features on children's health status from multi-levelperspectives. Within HealthPrism, a multimodal learning model with a gate mechanism is proposed for health profiling and cross-modality feature importance comparison. A set of visualization components is designed for experts to explore and understand multimodal data freely. We demonstrate the effectiveness and usability of HealthPrism through quantitative evaluation of the model performance, case studies, and expert interviews in associated domains.

Identifying the High-Risk Population for COVID-19 Transmission in Hong Kong Leveraging Explainable Machine Learning.

The worldwide spread of COVID-19 has caused significant damage to people's health and economics. Many works have leveraged machine learning models to facilitate the control and treatment of COVID-19. However, most of them focus on clinical medicine and few on understanding the spatial dynamics of the high-risk population for transmission of COVID-19 in real-world settings. This study aims to investigate the association between population features and COVID-19 transmission risk in Hong Kong, which can help guide the allocation of medical resources and the implementation of preventative measures to control the spread of the pandemic. First, we built machine learning models to predict the number of COVID-19 cases based on the population features of different tertiary planning units (TPUs). Then, we analyzed the distribution of cases and the prediction results to find specific characteristics of TPUs leading to large-scale outbreaks of COVID-19. We further evaluated the importance and influence of various population features on the prediction results using SHAP values to identify indicators for high-risk populations for COVID-19 transmission. The evaluation of COVID-19 cases and the TPU dataset in Hong Kong shows the effectiveness of the proposed methods. The top three most important indicators are identified as people in accommodation and food services, low income, and high population density.

Association Between Objectively Assessed Sleep and Depressive Symptoms During Pregnancy and Post-partum.

INTRODUCTION: Sleep problems are common in pregnancy but many studies have relied only on self-reported sleep measures. We studied the association between objectively measured sleep and peripartum depressive symptoms in pregnant women. MATERIAL AND METHODS: Sleep was assessed using Actiwatch accelerometers in a sample of 163 pregnant women in the late first (weeks 11-15) or early second trimester (weeks 16-19). Depressive symptoms were assessed in gestational weeks 17, 32 and at 6 weeks post-partum using the Edinburgh Postnatal Depression Scale (EPDS). Multiple linear regression and logistic regression analyses, adjusting for age, BMI, pre-pregnancy smoking, ongoing mental health problems, trimester and season of sleep assessment were carried out to test the association between sleep and depression. Sleep was measured by total sleep time and sleep efficiency, whereas depression was indicated by depressive symptoms and depression caseness. Results are presented as unstandardized beta (B) coefficients or adjusted odds ratios (AOR) and 95% confidence intervals (CI). RESULTS: Total sleep time ranged from 3 to 9 h (mean 7.1, SD 0.9) and average sleep efficiency was 83% (SD 6.0). Women with the shortest total sleep time, i.e., in the lowest quartile (<6.66 h), reported higher depressive symptoms during pregnancy (week 17, B = 2.13, 95% CI 0.30-3.96; week 32, B = 1.70, 95% CI 0.03-3.37) but not post-partum. Their probability to screen positive for depression in gestational week 17 was increased more than 3-fold (AOR = 3.46, 95% CI 1.07-11.51) but unchanged with regards to gestational week 32 or 6 weeks post-partum. Sleep efficiency was not associated with depressive symptoms at any stage of pregnancy or post-partum. DISCUSSION: In one of the few studies to use objective sleep measures to date, mental health of pregnant women appeared to be affected by shortened sleep, with total sleep time being negatively associated with depressive symptoms in the early second and third trimester. This finding highlights the relevance of identifying and treating sleep impairments in pregnant women early during antenatal care to reduce the risk of concomitant depression.

Energy-Efficient Collaborative Outdoor Localization for Participatory Sensing.

Location information is a key element of participatory sensing. Many mobile and sensing applications require location information to provide better recommendations, object search and trip planning. However, continuous GPS positioning consumes much energy, which may drain the battery of mobile devices quickly. Although WiFi and cell tower positioning are alternatives, they provide lower accuracy compared to GPS. This paper solves the above problem by proposing a novel localization scheme through the collaboration of multiple mobile devices to reduce energy consumption and provide accurate positioning. Under our scheme, the mobile devices are divided into three groups, namely the broadcaster group, the location information receiver group and the normal participant group. Only the broadcaster group and the normal participant group use their GPS. The location information receiver group, on the other hand, makes use of the locations broadcast by the broadcaster group to estimate their locations. We formulate the broadcaster set selection problem and propose two novel algorithms to minimize the energy consumption in collaborative localization. Simulations with real traces show that our proposed solution can save up to 68% of the energy of all of the participants and provide more accurate locations than WiFi and cellular network positioning.