Hyperactivity Sensing and Intervention for Children: LemurDx Project

Attention-Deficit Hyperactivity Disorder (ADHD) affects approximately 5% of children and adolescents worldwide [ref]. Children with ADHD often exhibit increased inattentiveness, impulsivity, and hyperactivity, with symptoms appearing as early as four years of age. In school-age children, more than half of ADHD cases involve hyperactivity symptoms [ref]. Current assessment of hyperactivity primarily relies on questionnaires completed by parents or teachers. While convenient, these reports often suffer from low inter-rater reliability and limited contextual awareness [ref]. As a result, clinicians may struggle to accurately evaluate the severity and patterns of hyperactivity in everyday environments. Our research explores how wearable sensing and interactive systems can support both objective measurement and real-time intervention for children with hyperactivity. Through the LemurDx and CalmReminder projects, we investigate how passive sensing can quantify hyperactivity in daily life and how real-time feedback can support parents in managing challenging situations.

Our first step focused on objectively measuring hyperactivity using passive mobile sensing ([J.5] LemurDx). In collaboration with the University of Pittsburgh Medical Center, we collected data from 61 children (25 diagnosed with hyperactivity) who wore a smartwatch for up to seven days during their normal routines.

In unconstrained environments, however, raw motion levels alone are insufficient to assess hyperactivity. For example, children may move frequently during exercise or play regardless of their clinical status. To address this challenge, we developed models that estimate the child's activity context using multimodal sensor signals. This contextual information allows us to interpret motion patterns more accurately when assessing hyperactivity severity.

Our analysis shows that this context-aware sensing approach can reliably quantify hyperactivity patterns in daily life. Building on this pipeline, we also developed models that generate a real-time hyperactivity risk score from incoming sensor data. We are currently exploring clinician-facing interfaces that visualize these signals to support diagnosis and longitudinal monitoring.

While objective measurement is valuable for diagnosis, parents and caregivers often need support during everyday situations when hyperactivity escalates. To explore this opportunity, we developed [C.25] CalmReminder, a sensing-based intervention system that builds on the LemurDx sensing pipeline.

CalmReminder continuously estimates the child's hyperactivity level from smartwatch motion signals and notifies parents when the system detects a potential escalation. These notifications are designed as gentle prompts that help parents intervene early, for example by redirecting attention or suggesting calming activities.

We deployed CalmReminder as a design probe with families of children with hyperactivity to understand how parents engage with real-time sensing systems in everyday life. Our study revealed that parents value early awareness of hyperactivity patterns but also differ widely in their preferred notification frequency and timing.

From the initial CalmReminder study, we learned that parents exhibit different adoption patterns and preferences for the assistant's notifications, which can be influenced by their own stress levels and the child's hyperactivity severity. We are currently exploring ways to personalize the assistant's notifications based on these factors, aiming to enable the assistant's adaptability to the unique needs of each family.

We thank Sam Shaaban from NuRelm, Inc. and his team for their support in advancing the deployment of our system.