Google is reportedly developing an AI assistant that recommends workouts and meal plans [Kyle Wiggers | VentureBeat]
Fitness will be Google Coach’s bread and butter, Android Police reports. But unlike Google Fit, Google’s activity-tracking platform, it’ll deliver insights proactively, informed in part by calendar appointments, reminders, and logged activities. If you skip a scheduled gym day, for example, it might nudge you to find another time. And if you’re falling short of a fitness goal, it could suggest workouts and routines that would help you achieve it.
Fitness is just one of several domains in Google Coach, apparently. The wellness assistant will keep track of your nutrition and the foods you consume, and use other signals (like location) to make actionable recommendations. At a restaurant, it might point you toward healthier menu items, and before you go grocery shopping, it could email you a weekly meal plan personalized to your schedule.
With over 10,000 mental health- and psychiatry-related smartphone apps available today and expanding, there is a need for reliable and valid evaluation of these digital tools. However, the updating and nonstatic nature of smartphone apps, expanding privacy concerns, varying degrees of usability, and evolving interoperability standards, among other factors, present serious challenges for app evaluation. In this article, we provide a narrative review of various schemes toward app evaluations, including commercial app store metrics, government initiatives, patient-centric approaches, point-based scoring, academic platforms, and expert review systems. We demonstrate that these different approaches toward app evaluation each offer unique benefits but often do not agree to each other and produce varied conclusions as to which apps are useful or not. Although there are no simple solutions, we briefly introduce a new initiative that aims to unify the current controversies in app elevation called CHART (Collaborative Health App Rating Teams), which will be further discussed in a second article in this series.
FDA Sundaytweetorial on modernizing clinical trials [Scott Gottlieb, FDA Commissioner]
In this tweetstorm, Gottlieb shares the FDA’s plans to modernize clinical trials to reduce the cost of drug development, potentially lower drug costs, and bring more safe, effective therapies to patients.
How the FDA is transforming clinical trials [Bryan Silverman | HCA News]
This is about drugs and other medical interventions, but the ideas are relevant to evaluating mental health interventions.
Surrogate endpoints are readily obtained within the domain of a digital clinical study via real-time, real-world data capture. This facilitates the FDA’s vision for adaptive design by being able to course correct mid-stream within a clinical study for such indices as dosage or population size, rather than waiting for a study to fail. The effects: both time and money saved. Add in the advent of “bring your own device,” which digital clinical studies enable, and the real-world evidence data pool becomes deeper and more insightful in a shorter period via rules-based engines, machine learning and artificial intelligence (AI). That fosters the visionary excellence Gottlieb is espousing.
Compression of the standard three-phase trial into one long and continuous study (Gottlieb’s vision) is empowered by digital and, more specifically, machine learning and AI. Machine learning is ideally suited to longitudinal data insights, speeding the arrival of endpoint goals with mathematical precision while creating new insights into a drug’s use. It also identifies dangerous anomalies earlier than was ever possible before. The tech ultimately results in billions of dollars potentially saved from speed to market, increased patient safety and averted legal issues.
When you add post-marketing surveillance and the ability to monitor a patient’s lifetime use of the drug, then you’ve created the utopia being sought by big pharma, governments, insurers, employer groups and patients — all made possible by the modernized FDA and Gottlieb.