Randomized trial of two artificial intelligence coaching interventions to increase physical activity in cancer survivors

Physical activity (PA) has numerous health benefits. Personalized coaching may increase adherence to PA recommendations, but it is challenging to deliver personalized coaching in a scalable manner. The objective of our study was to determine whether novel artificially intelligent (AI) coaching interventions increase PA among overweight or obese, physically inactive cancer survivors compared to a control arm that receives health information. We conducted a single-center, three-arm randomized trial with equal allocation to (1) voice-assisted AI coaching delivered by smart speaker (MyCoach), (2) autonomous AI coaching delivered by text message (SmartText), and (3) control. Data collection was automated via sensors and voice technology, effectively masking outcome ascertainment. The primary outcome was change in mean steps per day from baseline to the end of follow-up at 4 weeks. Of the 42 randomized participants, 91% were female, and 36% were Black; mean age was 62.1 years, and mean BMI was 32.9 kg/m2. The majority were breast cancer survivors (85.7%). At the end of 4 weeks follow-up, steps increased in the MyCoach arm by an average of 3618.2 steps/day; the net gain in this arm was significantly greater [net difference = 3568.9 steps/day (95% CI: 1483–5655), P value <0.001] compared to control arm, and [net difference = 2160.6 steps/day (95% CI: 11–4310), P value 0.049] compared to SmartText. In conclusion, AI-based voice-assisted coaching shows promise as a practical method of delivering scalable, individualized coaching to increase physical activity in sedentary cancer survivors. Additional research is needed to replicate these findings in a broader population of cancer survivors and to investigate the effects of these interventions in the general population.ClinicalTrials.gov Identifier: NCT03212079, July 11, 2017, https://clinicaltrials.gov/ct2/show/NCT03212079.

Using Smart Speakers in Low-Income Senior Housing to Enhance the Aging in Place Experience: Stakeholder Views

Smart speakers provide a platform that can integrate smart home technology and/or safety devices within the home to enhance quality of life and independent living for older adults. However, few attempts to utilize this technology specifically within low-income senior housing (LISH) residents have been documented. Our purpose was to explore different stakeholder perceptions about the use of smart speakers to support aging in place in older adults living alone in LISH. Smart speakers were deployed in individual LISH apartments, equipped with a voice technology-based aging in place solution for the facility. A qualitative analysis of semi-structured interviews using a constant comparative approach for emerging themes was conducted (n=10: older adult users, n=2: housing staff, n=2: voice technology developers). The three participant groups showed diverging perceptions in terms of benefits, uses, and stakeholder interests. Older adults found smart speakers useful in four main areas: assistance with daily tasks, feeling connected, safety measures, and emotional wellbeing. The two other groups showed a broader interest in the use of the smart speaker device, such as residential management tools and communication channels in addition to its potential use as safety and wellness tools. Older adults experienced significant difficulty setting up desired functions or finding instructions, which restricted utilization of the technology to a limited set of tasks. All stakeholder groups addressed a need for formal training or personalized tech support for older adult users. Findings indicate the importance of developing deployment strategies tailored to the needs and characteristics of the target user group.

Public Perceptions Towards Synthetic Voice Technology

Text-to-Speech (TTS) technologies have provided ways to produce acoustic approximations of human voices. However, recent advancements in machine learning (i.e., neural network TTS) have helped move beyond coarse mimicry and towards more natural-sounding speech. With only a small collection of recorded utterances, it is now possible to generate wholly synthetic voices indistinguishable from those of human speakers. While these new approaches to speech synthesis can help facilitate more seamless experiences with artificial agents, they also lower the barrier to entry for those seeking to perpetrate deception. As such, in the development of these technologies, it is important to anticipate potential harms and devise strategies to help mitigate against misuse. This paper presents findings from a 360-person survey that assessed public perceptions of synthetic voices, with a particular focus on how voice type and social scenarios impact ratings of trust. Findings have implications for the responsible deployment of synthetic speech technologies.