JMIR Publications

ABSTRACT

Background:

Hypoglycemia is a frequent and acute complication in type-1 diabetes mellitus (T1DM) and is associated with a higher risk of car mishaps. Currently, hypoglycemia can be detected and signaled through flash glucose monitoring (FGM) or continuous glucose monitoring (CGM) devices, which require manual and visual interaction, removing the focus of attention from the driving task. Hypoglycemia is known to cause a decrease in attention, challenging the safety of using such devices behind the wheel. Here, we present an investigation of hands-free technology: a voice warning that can potentially be delivered via the in-vehicle voice assistant.

Objective:

Designing and assessing a voice–assistant–based health warning for hypoglycemia while driving.

Methods:

We designed a voice warning and evaluated it in three studies. In all studies, participants received a voice warning while driving. Study 0 (n=10), assessed the feasibility of using a voice warning with healthy participants driving in a simulator. Study 1 (n=18), assessed the voice warning with participants with T1DM. Study 2, (n=20) assessed it with participants with T1DM undergoing hypoglycemia while driving in a real car. We measured participants’ self-reported technology affinity, perception of the voice warning (with a user experience scale in Study 0 and with Acceptance, Alliance and Trust scales in Studies 1 and 2), compliance behavior (whether they stopped the car and reaction time), and collected participants’ verbal feedback.

Results:

Technology affinity was similar across studies (Study 0: Mean=4.2/6, SD=1; Study 1: Mean=3.4/5, SD=0.6; Study 2: Mean=3.4/5, SD=0.7). Perception of the voice warning decreased in value between the simulated (Study 0: user experience Mean=6.4/10, SD=1.6; Study 1: Acceptance Mean=3.9/5, SD=0.8, Alliance Mean=3.7/5, SD=0.5, Trust Mean=3.1/5, SD=0.7) and real-world driving (Study 2: Acceptance Mean=1.7/5, SD=1.3, Alliance Mean=2.8/5, SD=0.8, Trust Mean=1.9/5, SD=1). Compliance was at 100% in all studies while reaction time was higher in Study 1 (Mean=23, SD=5.2) than in Study 0 (Mean=12.6, SD=5.7) and Study 2 (Mean=14.6, SD=4.3). Finally, verbal feedback showed that participants preferred the voice warning to be less verbose and interactive.

Conclusions:

Drivers find such an implementation useful and effective in a simulated environment, while improvements are still needed for the real-world driving context. To the best of the authors’ knowledge, this is the first study investigating the feasibility of an in-vehicle voice warning for hypoglycemia. This research is a kickoff for the use of in-vehicle voice assistants for digital health interventions.