Objective: The National Diabetes Prevention Program (DPP) reduces diabetes incidence and associated medical costs but is typically staffing-intensive, limiting scalability. We evaluated an alternative delivery method with 3933 members of a program powered by conversational Artificial Intelligence (AI) called Lark DPP that has full recognition from the Centers for Disease Control and Prevention (CDC).Methods: We compared weight loss maintenance at 12 months between two groups: 1) CDC qualifiers who completed ≥4 educational lessons over 9 months (n = 191) and 2) non-qualifiers who did not complete the required CDC lessons but provided weigh-ins at 12 months (n = 223). For a secondary aim, we removed the requirement for a 12-month weight and used logistic regression to investigate predictors of weight nadir in 3148 members.Results: CDC qualifiers maintained greater weight loss at 12 months than non-qualifiers (M = 5.3%, SE = .8 vs. M = 3.3%, SE = .8; p = .015), with 40% achieving ≥5%. The weight nadir of 3148 members was 4.2% (SE = .1), with 35% achieving ≥5%. Male sex ( β = .11; P = .009), weeks with ≥2 weigh-ins ( β = .68; P < .0001), and days with an AI-powered coaching exchange ( β = .43; P < .0001) were associated with a greater likelihood of achieving ≥5% weight loss.Conclusions: An AI-powered DPP facilitated weight loss and maintenance commensurate with outcomes of other digital and in-person programs not powered by AI. Beyond CDC lesson completion, engaging with AI coaching and frequent weighing increased the likelihood of achieving ≥5% weight loss. An AI-powered program is an effective method to deliver the DPP in a scalable, resource-efficient manner to keep pace with the prediabetes epidemic.
Background: Digital health programs have been shown to be feasible and effective for the prevention of chronic diseases such as diabetes. Contrary to expectations, findings also suggest that older adults have higher levels of engagement with digital health programs than younger adults. However, there is a paucity of research examining outcomes among older adults in digital health programs and whether higher engagement is related to better outcomes.Methods: We examined weight loss outcomes for 538 users aged 65 and older participating in one of two app-based prevention programs called the Diabetes Prevention Program and the Prevention Program, respectively. Both programs were available on a single artificial intelligence (AI)-powered digital health platform and shared a common goal of weight loss. We also examined the relationship between key engagement metrics (i.e., conversing with the AI-powered coach, weigh-ins, and initiating educational lessons early in the program) and weight loss outcomes.Results: The average weight loss of all enrollees having a weight measurement after after the 9th week was 4.51%, and the average weight loss of the Diabetes Prevention Program enrollees meeting a minimum engagement level was 8.56%. Greater weight loss was associated with a greater number of days with AI-powered coaching conversations (p = 0.03), more weigh-ins (p = 0.00), and early educational lesson initiation (p = 0.02).Conclusions: Digital health programs powered by AI offer a promising solution for health management among older adults. The results show positive health outcomes using app-based prevention programs, and all three engagement metrics were independently associated with weight loss.
Malaria remains a major public health problem in many countries. Unlike influenza and HIV, where diversity in immunodominant surface antigens is understood geographically to inform disease surveillance, relatively little is known about the global population structure of PfEMP1, the major variant surface antigen of the malaria parasitePlasmodium falciparum. The complexity of thevarmultigene family that encodes PfEMP1 and that diversifies by recombination, has so far precluded its use in malaria surveillance. Recent studies have demonstrated that cost-effective deep sequencing of the region ofvargenes encoding the PfEMP1 DBLα domain and subsequent classification of within host sequences at 96% identity to define unique DBLα types, can reveal structure and strain dynamics within countries. However, to date there has not been a comprehensive comparison of these DBLα types between countries. By leveraging a bioinformatic approach (jumping hidden Markov model) designed specifically for the analysis of recombination withinvargenes and applying it to a dataset of DBLα types from 10 countries, we are able to describe population structure of DBLα types at the global scale. The sensitivity of the approach allows for the comparison of the global dataset to ape samples ofPlasmodium Laveraniaspecies. Our analyses show that the evolution of the parasite population emerging out of Africa underlies current patterns of DBLα type diversity. Most importantly, we can distinguish geographic population structure within Africa between Gabon and Ghana in West Africa and Uganda in East Africa. Our evolutionary findings have translational implications in the context of globalization. Firstly, DBLα type diversity can provide a simple diagnostic framework for geographic surveillance of the rapidly evolving transmission dynamics ofP.falciparum. It can also inform efforts to understand the presence or absence of global, regional and local population immunity to major surface antigen variants. Additionally, we identify a number of highly conserved DBLα types that are present globally that may be of biological significance and warrant further characterization.
Background: Home blood pressure (BP) monitoring is recommended for people with hypertension; however, meta-analyses have demonstrated that BP improvements are related to additional coaching support in combination with self-monitoring, with little or no effect of self-monitoring alone. High-contact coaching requires substantial resources and may be difficult to deliver via human coaching models. Objective: This observational study assessed changes in BP and body weight following participation in a fully digital program called Lark Hypertension Care with coaching powered by artificial intelligence (AI). Methods: Participants (N=864) had a baseline systolic BP (SBP) ≥120 mm Hg, provided their baseline body weight, and had reached at least their third month in the program. The primary outcome was the change in SBP at 3 and 6 months, with secondary outcomes of change in body weight and associations of changes in SBP and body weight with participant demographics, characteristics, and program engagement. Results: By month 3, there was a significant drop of –5.4 mm Hg (95% CI –6.5 to –4.3; P<.001) in mean SBP from baseline. BP did not change significantly (ie, the SBP drop maintained) from 3 to 6 months for participants who provided readings at both time points (P=.49). Half of the participants achieved a clinically meaningful drop of ≥5 mm Hg by month 3 (178/349, 51.0%) and month 6 (98/199, 49.2%). The magnitude of the drop depended on starting SBP. Participants classified as hypertension stage 2 had the largest mean drop in SBP of –12.4 mm Hg (SE 1.2 mm Hg) by month 3 and –13.0 mm Hg (SE 1.6 mm Hg) by month 6; participants classified as hypertension stage 1 lowered by –5.2 mm Hg (SE 0.8) mm Hg by month 3 and –7.3 mm Hg (SE 1.3 mm Hg) by month 6; participants classified as elevated lowered by –1.1 mm Hg (SE 0.7 mm Hg) by month 3 but did not drop by month 6. Starting SBP (β=.11; P<.001), percent weight change (β=–.36; P=.02), and initial BMI (β=–.56; P<.001) were significantly associated with the likelihood of lowering SBP ≥5 mm Hg by month 3. Percent weight change acted as a mediator of the relationship between program engagement and drop in SBP. The bootstrapped unstandardized indirect effect was –0.0024 (95% CI –0.0052 to 0; P=.002). Conclusions: A hypertension care program with coaching powered by AI was associated with a clinically meaningful reduction in SBP following 3 and 6 months of program participation. Percent weight change was significantly associated with the likelihood of achieving a ≥5 mm Hg drop in SBP. An AI-powered solution may offer a scalable approach to helping individuals with hypertension achieve clinically meaningful reductions in their BP and associated risk of cardiovascular disease and other serious adverse outcomes via healthy lifestyle changes such as weight loss.
The National Diabetes Prevention Program (NDPP) offers lifestyle change education to adults at risk for diabetes across the United States, but its reach is curbed due, in part, to limitations of traditional in-person programs. Diabetes Prevention Programs (DPPs) that are fully digital may increase reach by overcoming these barriers. The aim of this research was to examine the reach of Lark's DPP, a fully digital artificial-intelligence-powered DPP. This study assessed geographic features and demographic characteristics of a sample of Lark DPP commercial health plan members with complete data ( N = 16,327) and compared several demographic features with a large composite sample of members from DPPs across the nation (NDPP; N = 143,489) and a National Health Interview Survey (NHIS) sample of prediabetic adults in the United States (NHIS; N = 2118). Examination of the Lark DPP sample revealed that 24.4% of members lived in rural areas, 30.8% lived in whole county health professional shortage areas, and only 7.6% of members lived in a zip code with an in-person DPP. When comparing the Lark sample with the NDPP and NHIS samples, Lark DPP enrollees tended to be younger and have a higher body mass index (BMI) ( p' s < 0.001). Lark provides convenient access to a DPP for individuals living in hard-to-reach areas who may face barriers to participating in in-person or telephonic DPPs or who prefer a digital program. Compared with the NDPP sample, Lark is also reaching younger and higher BMI users, who are traditionally difficult to enroll and have a high need for intervention.