BACKGROUND
Complications related to noncommunicable diseases are among the main causes of mortality. Fostering patients’ access to health-related information through efficient and accessible channels like commercial voice assistants (CVA) such as Amazon Alexa, Apple Siri, or Google Assistant, may support patients’ ability to make health-related decisions and manage their chronic conditions.
OBJECTIVE
This study aims to evaluate the ability of CVAs in providing expertise-based voice responses to questions related to noncommunicable disease management.
METHODS
We collected health-related frequently asked questions from health organizations, government, medical non-profit and popular websites about conditions associated with Alzheimer’s disease (AD), lung cancer (LC), chronic obstructive pulmonary disease (COPD), diabetes mellitus (DM), cardiovascular disease (CVD), kidney disease (KD), and cerebrovascular disease (CV). The questions were then validated with practicing medical specialists and the most frequent ones selected, resulting in a pool of 144. We submitted the selected questions to CVAs in a 3x3 fractional factorial design experiment with three developers (ie, Amazon, Apple, and Google) and three modalities (ie, voice-only, voice-and-display, display-only). The condition Google display-only was operationalized with Google Search (our gold standard of information lookup). We assessed whether the CVA provided a voice response (ie, response rate) and what type of web source was used (ie, Expert, Commercial, Crowdsourced, or Not stated).
RESULTS
Amazon and Google showed a slightly higher voice response rate in voice-only (76.4% and 97.2%, respectively), compared to voice-and-display (74% and 92.4%, respectively). Apple showed the opposite (16% voice-only, 16.7% voice-and-display). Source type was mostly Expert in Amazon (77.3% voice-only, 76.6% voice-and-display) and Google (70.7% voice-only, 73.7% voice-and-display). Apple mostly used Commercial (30.4% voice-only, 29.2% voice-and-display), Crowdsourced (21.7% voice-only, 33.3% voice-and-display) sources, or stated no source (39.1% voice-only, 29.2% voice-and-display). Moreover, Amazon showed the highest response rate for LC (88%), while Apple did so for COPD (20%), and Google for AD (100%). Amazon and Google always used Expert sources for AD, while Apple never did so. However, Apple used the most Expert sources for CD (50%).
CONCLUSIONS
None of the tested CVAs was the absolute best in responding to questions about noncommunicable disease management. CVAs seem to perform differently depending on the noncommunicable disease in question. We urge health organizations to collaborate with Google, Amazon, and Apple to allow their CVAs consistently providing reliable answers to health-related questions on noncommunicable disease management.