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.

Physical activity has established health benefits, but motivation and adherence remain challenging. We designed and launched a three-arm randomized trial to test artificial intelligence technology solutions to increase daily physical activity in cancer survivors. A single-center, three-arm randomized clinical trial with an allocation ration of 1:1:1: (A) control, in which participants are provided written materials about the benefits of physical activity; (B) text intervention, where participants receive daily motivation from a fully automated, data-driven algorithmic text message via mobile phone (Coachtext); and (C) Voice Assist intervention, where participants are provided with an in-home on demand autonomous Intelligent Agent using data driven Interactive Digital Voice Assist on the Amazon Alexa/Echo (MyCoach). The study runs for 5 weeks: a one-week run-in to establish baseline, followed by 4 weeks of intervention. Data for study outcomes is collected automatically through a wearable sensor, and data are transferred in real-time to the study server. The recruitment goal is 42 participants, 14 in each arm. Electronic health records are used to prescreen candidates, with 39 participants recruited to date. This study aims to investigate the effects of different types of intelligent technology solutions on promoting physical activity in cancer survivors. This innovative approach can easily be expanded and customized to other interventions. Early lessons from our initial participants are helping us develop additional advanced solutions to improve health outcomes. Retrospectively registered on July 10, 2017 at ClinicalTrials.gov: NCT03212079; https://clinicaltrials.gov/ct2/show/NCT03212079 (Archived by WebCite at http://www.webcitation.org/6wgvqjTji).

Context Higher levels of insulin-like growth factor-1 (IGF-1) are associated with increased risk of cancers and higher mortality. Therapies that reduce IGF-1 have considerable appeal as means to prevent recurrence. Design Randomized, 3-parallel-arm controlled clinical trial. Interventions and Outcomes Cancer survivors with overweight or obesity were randomized to (1) self-directed weight loss (comparison), (2) coach-directed weight loss, or (3) metformin treatment. Main outcomes were changes in IGF-1 and IGF-1:IGFBP3 molar ratio at 6 months. The trial duration was 12 months. Results Of the 121 randomized participants, 79% were women, 46% were African Americans, and the mean age was 60 years. At baseline, the average body mass index was 35 kg/m²; mean IGF-1 was 72.9 (SD, 21.7) ng/mL; and mean IGF1:IGFBP3 molar ratio was 0.17 (SD, 0.05). At 6 months, weight changes were -1.0% (P = 0.07), -4.2% (P < 0.0001), and -2.8% (P < 0.0001) in self-directed, coach-directed, and metformin groups, respectively. Compared with the self-directed group, participants in metformin had significant decreases on IGF-1 (mean difference in change: -5.50 ng/mL, P = 0.02) and IGF1:IGFBP3 molar ratio (mean difference in change: -0.0119, P = 0.011) at 3 months. The significant decrease of IGF-1 remained in participants with obesity at 6 months (mean difference in change: -7.2 ng/mL; 95% CI: -13.3 to -1.1), but not in participants with overweight (P for interaction = 0.045). There were no significant differences in changes between the coach-directed and self-directed groups. There were no differences in outcomes at 12 months. Conclusions In cancer survivors with obesity, metformin may have a short-term effect on IGF-1 reduction that wanes over time.

The “Dietary Approaches to Stop Hypertension” (DASH) diet, rich in fiber and low-fat dairy, effectively lowers blood pressure. DASH’s effect on calcitriol and other markers of bone-mineral metabolism is unknown. This secondary analysis of the DASH trial aimed to determine the effect of dietary patterns on blood concentrations of calcitriol, parathyroid hormone (PTH), ionized calcium, and urinary excretion of calcium and phosphorus. Outcomes were available in 334 participants in the trial. After a 3-week run-in on the control diet, participants were randomized to control, fruits and vegetables (F&V), or DASH diets. Outcomes were assessed at the end of run-in, and during the last week of the intervention period. Mean age of participants was 45.7 ± 10.7 years, 46% female, and 57% African-American. Mean ± Standard Deviation(SD) baseline serum concentrations of calcitriol, PTH, and ionized calcium were 37.8 ± 9.2 pg/mL, 46.1 ± 18.5 pg/mL and 5.2 ± 0.23 mg/dL, respectively. Mean (±SD) urinary calcium and phosphorus excretions were 150.1 ± 77.8 and 708.0 ± 251.8 mg/24 h, respectively. Compared with control, DASH reduced calcitriol −3.32 pg/mL (p = 0.004). Otherwise, there was no significant effect on other biomarkers. DASH lowered serum calcitriol perhaps more among African-Americans. These results raise important questions about the interpretation and clinical significance of low calcitriol concentrations in the setting of recommended diets.