BACKGROUND
The symptoms and associated characteristics of attention deficit hyperactivity disorder (ADHD) are typically assessed in-person at a clinic or in a research lab. The field of mobile health (mHealth) offers a new approach to obtaining additional, more detailed and longer-term behavioural data in the real world. Using our new ADHD Remote Technology (ART) system, based on the open-source RADAR-base mHealth platform and incorporates both active and passive monitoring measures, we now explore novel digital markers for their potential to distinguish between people with and without ADHD.
OBJECTIVE
The main aim of this study was to investigate whether adults and adolescents with ADHD differ from people without ADHD on eleven digital signals that we hypothesise to capture lapses in attention or restless or impulsive behaviours.
METHODS
As part of a remote monitoring pilot study using the ART system, we collected data over a 10-week period from 20 individuals with ADHD and 20 comparison participants without ADHD between the ages of 16 and 39. Here, we focus on specific features derived from the RADAR-base Active App data (mean and standard deviation of questionnaire notification response latency and questionnaire completion duration ), RADAR-base Passive App data (daily mean and daily standard deviation in response time to social and communication app notifications, standard deviation in ambient (background) light when participants are actively using their smartphones, time participants spend actively using their smartphone, number of new apps added during the study period), and wearable device data (Fitbit: the number of steps taken). The Passive App is a purpose-built passive remote monitoring app that collects sensor data in the background without additional burden to the participant.
RESULTS
Group differences were significant on five of the ten variables. Compared to the participants without ADHD, the participants with ADHD were slower and more variable in their speed of responding to the notifications to complete the questionnaires; took longer to complete the questionnaires; had higher daily mean response time to social and communication app notifications; and the change in ambient (background) light among them when actively using their smartphones was greater, likely indicating more movement from one place to another while using their smartphone. High standard scores (Z>1.64), though with non-significant p-values, were additionally observed for the standard deviation in participants’ duration of completion for the Active App questionnaires; daily standard deviation in responding to social and communication app notifications; and Fitbit step count while active on their smartphones. The groups did not differ in the duration for which participants were active on their smartphones and the number of new apps downloaded.
CONCLUSIONS
In a novel exploration of digital markers of ADHD, we identified candidate digital signals of restlessness, inconsistent attentional focusing and difficulties completing tasks. Larger-scale future studies are needed, firstly, to replicate these findings and, secondly, to assess the potential of such objective digital signals for tracking ADHD severity or predicting outcomes.