Refining an algorithm-powered just-in-time adaptive weight control intervention: A randomized controlled trial evaluating model performance and behavioral outcomes

Abstract

Suboptimal weight losses are partially attributable to lapses from a prescribed diet. We developed an app (OnTrack) that uses ecological momentary assessment to measure dietary lapses and relevant lapse triggers and provides personalized intervention using machine learning. Initially, tension between user burden and complete data was resolved by presenting a subset of lapse trigger questions per ecological momentary assessment survey. However, this produced substantial missing data, which could reduce algorithm performance. We examined the effect of more questions per ecological momentary assessment survey on algorithm performance, app utilization, and behavioral outcomes. Participants with overweight/obesity ( n = 121) used a 10-week mobile weight loss program and were randomized to OnTrack-short (i.e. 8 questions/survey) or OnTrack-long (i.e. 17 questions/survey). Additional questions reduced ecological momentary assessment adherence; however, increased data completeness improved algorithm performance. There were no differences in perceived effectiveness, app utilization, or behavioral outcomes. Minimal differences in utilization and perceived effectiveness likely contributed to similar behavioral outcomes across various conditions.

Combining ecological momentary assessment, wrist-based eating detection, and dietary assessment to characterize dietary lapse: A multi-method study protocol

“…28,29,43 We supplement the wrist-based eating inference with EMA, which is one of the most valid and reliable tools for assessing individuals' behaviors throughout the course of their daily lives and has been used to study dietary lapses across approximately seven other research studies. 7,15,16,54,59,70,71 Finally, we use a well-established method of dietary assessment, the 24-hour food recall. 52 The combination of these tools is paramount because each method has the potential to overcome weaknesses of the others.…”

The potential of artificial intelligence in enhancing adult weight loss: a scoping review

“…During the screening of full-text articles, two articles were unable to be retrieved even after seeking help from the university librarian and hence were excluded (44,45) . Two separate journal articles included in this review were published from the same dissertation (46)(47)(48) . Among the sixty-five included articles, one reported two studies and hence a total of sixty-six studies were presented in this scoping review.…”

“…Of the studies on enhancing self-monitoring, twenty-nine (43•9 %) were on eating behaviours (58)(59)(60)(61)(62)(63)(64)(65)(66)(67)(68)(69)(70)(71)(72)(73)(74)(75)(76) , seven (10•6 %) were on energy intake (34,(77)(78)(79)(80)(81)(82) , thirty-three (50 %) were on physical activity (26,(51)(52)(53)(54)(55)60,74, and nine (13•6 %) were on energy expenditure (83,85,92,(94)(95)(96)(97)100,101) . Of the studies on optimising goal setting, five were on optimising eating behaviour goals (e.g., eating at a certain time of the day and energy intake) (48,49,53) and six were on optimising physical activity goals (e.g., type of physical activity and energy expenditure) (26,…”

“…Of the studies on optimising goal setting, five were on optimising eating behaviour goals (e.g., eating at a certain time of the day and energy intake) (48,49,53) and six were on optimising physical activity goals (e.g., type of physical activity and energy expenditure) (26,(51)(52)(53)(54)(55) . Of the ten studies on self-control, five were on controlling eating behaviours (48,49,107) , three were on controlling physical activity performance (26,52,54) and two were on both (51,53) . Only six of these studies reported weight loss of which two were significant (26,107) .…”

“…Ten studies evaluated the use of AI-assisted weight management interventions that instantaneously optimise prediction models for behavioural risk profiling (e.g., low, medium and high risk) and enhance behavioural self-control through adaptive and personalised messages/feedback/prompts (Table 4). The interventions were all delivered through smartphone apps, namely OnTrack (used in three of the included studies) (48)(49)(50) , Sweetech app (26) , Calfit app (54) , Lark's AI health coach app (53) , Think Slim app (106) , SmartCare app (51) , MyBehaviour (52) and one without a name. In general, the mobile app interventions used either wrist-worn activity trackers, smartphone in-built accelerometers or EMA to track one's physical activity.…”