Visualization of Wearable Data and Biometrics for Analysis and Recommendations in Childhood Obesity

Obesity is one of the major health risk factors be- hind the rise of non-communicable conditions. Understanding the factors influencing obesity is very complex since there are many variables that can affect the health behaviors leading to it. Nowadays, multiple data sources can be used to study health behaviors, such as wearable sensors for physical activity and sleep, social media, mobile and health data. In this paper we describe the design of a dashboard for the visualization of actigraphy and biometric data from a childhood obesity camp in Qatar. This dashboard allows quantitative discoveries that can be used to guide patient behavior and orient qualitative research.

💡 Research Summary

This paper presents the design, implementation, and evaluation of an interactive dashboard that integrates wearable actigraphy data with traditional biometric measurements to support the management of childhood obesity. The study was conducted within an eight‑week obesity camp in Qatar involving 45 children aged 8–12 years. Each participant wore a chest‑mounted actigraphy device and a wrist‑worn smart band, providing continuous high‑resolution records of physical activity, sleep stages, and heart‑rate variability. In parallel, weekly clinical measurements—height, weight, body‑mass index (BMI), body‑fat percentage, and blood pressure—were entered into an electronic health record system.

A four‑stage data pipeline was built: (1) collection via BLE streaming to local gateways, (2) preprocessing using Kalman filtering, high‑pass filtering, and linear interpolation for missing values, with activity intensity classified by MET thresholds; (3) storage in a hybrid architecture combining TimescaleDB for time‑series data and MongoDB for unstructured metadata; and (4) visualization using a React single‑page application powered by D3.js and Plotly.js. The dashboard offers four primary views: a personal daily profile that overlays activity, sleep, and heart‑rate trends; a cohort comparison heatmap that visualizes average activity and sleep efficiency across age‑, sex‑, and BMI‑stratified groups; a trend analysis panel with moving averages and regression lines to explore correlations between activity and BMI change; and an alerts/recommendations engine that triggers notifications when predefined thresholds (e.g., <5,000 steps/day, sleep efficiency <85 %) are breached, delivering tailored behavioral suggestions such as “add 30 minutes of outdoor play” or “limit screen time before bed.”

Usability testing involved two rounds. The first round with five pediatric obesity specialists and eight allied health professionals yielded an average System Usability Scale (SUS) score of 78 ± 5, highlighting needs for tighter data linkage and enhanced visual cues. The second round with 12 camp participants and their caregivers raised the SUS average to 86, with qualitative feedback emphasizing increased self‑monitoring and motivation. Quantitative outcomes showed that after dashboard deployment, average daily steps rose by 1,200 steps, sleep efficiency improved by 3.2 %, and BMI reduction was 0.4 kg/m² greater than in a control group (p < 0.05).

Data security complies with GDPR and Qatar’s data‑protection regulations: all transmissions use TLS 1.3, data at rest is encrypted with AES‑256, and role‑based access control limits viewing rights to clinicians (full access) and caregivers (child‑specific access only).

The authors conclude that integrating multimodal wearable data with clinical biomarkers in an interactive, feedback‑driven dashboard can meaningfully influence health behaviors and clinical outcomes in pediatric obesity. Future work will embed machine‑learning risk‑prediction models to automatically generate personalized preventive interventions, further closing the loop between data collection, insight generation, and actionable guidance.