Accepted for/Published in: JMIR mHealth and uHealth
Date Submitted: Sep 3, 2020
Date Accepted: Dec 3, 2020
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Voice Assistant Clinical Advice in Postpartum Depression Using Apple Siri, Amazon Alexa, Google Assistant, and Microsoft Cortana: A Cross-sectional Investigation
ABSTRACT
Background:
A voice assistant (VA) is an inanimate audio-interfaced software, augmented with artificial intelligence, capable of two-way dialogue, and increasingly used to access healthcare advice. Postpartum depression (PPD) is a prime candidate for a VA-based digital health intervention.
Objective:
To assess VA responses to PPD questions in terms of accuracy, advice given, and clinical appropriateness.
Methods:
This cross-sectional study examined four VAs installed on two mobile devices in early 2020. We posed 14 questions obtained from the American College of Obstetricians and Gynecologists’ (ACOG) patient-focused Frequently Asked Questions (FAQ) on PPD to each VA. We scored the VA responses according to accuracy of speech recognition, whether advice was given, and clinical agreement with ACOG FAQ. Two board-certified physicians assessed responses given by four major VAs (Apple Siri, Amazon Alexa, Google Assistant, and Microsoft Cortana). The three assessments for each VA response included accurate recognition of the query, presence of advice given, and clinical agreement with the ACOG FAQ.
Results:
Accurate recognition of the query ranged from 78.5% to 100%. Advice given ranged from 35.7% to 78.6%. Clinical agreement with the ACOG FAQ ranged from 14.3% to 28.6%.
Conclusions:
While the best performing VA gave clinically appropriate advice to 28.6% of the PPD questions, all four VAs taken together achieved 64.3% clinically relevant advice. Technology companies and clinical organizations should partner to improve guidance, screen patients for mental health disorders, and educate patients on potential treatment.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.