Researchers compared four widely used voice assistants — Amazon Alexa, Apple Siri, Google Assistant and Microsoft Cortana — to determine the quality and accuracy of responses to questions about cancer screening. The study was conducted using the smartphones of five investigators. Each voice assistant received two independent reviews. The primary outcome was each device’s response to the query, “Should I get screened for (type of) cancer” for 11 cancer types. The researchers assessed the assistants’ ability to 1) understand the queries; 2) provide accurate information through web searches; and 3) provide accurate information verbally. The team compared the assistants’ responses to the U.S. Preventive Services Task Force’s cancer screening guidelines. A response was deemed accurate if it did not directly contradict guideline information and if the response included a starting age for screening consistent with the guidelines. Siri, Google Assistant and Cortana understood 100% of the queries, consistently generating a web search and/or verbal response, while Alexa was unable to understand or respond to any of the queries. Researchers also found that the top three links to additional resources provided by Siri, Google Assistant and Cortana provided information consistent with USPSTF guidelines roughly 70% of the time. However, the authors noted that the voice assistants’ responses to vocal queries were either unavailable or less accurate than text-based web searches, denoting room for improvement across all voice assistants. The study could have implications for users who rely on voice assistants to retrieve important health information and for those who are sight-impaired, less tech-savvy, or have low health literacy.
/Public Release. This material from the originating organization/author(s) may be of a point-in-time nature, edited for clarity, style and length. The views and opinions expressed are those of the author(s).View in full here.