An Increase in Food Insecurity Correlated with an Increase in Plasma Triglycerides among Latinx Children.

BACKGROUND: Food insecurity and metabolic diseases both disproportionately affect Hispanic children. Cross-sectional studies have linked food insecurity with adverse cardiometabolic markers, including elevated plasma triglycerides and glucose concentrations. However, the association between changes in food insecurity and changes in cardiometabolic markers in children remains to be explored. Furthermore, few studies have assessed the impact of school-based nutrition interventions on household food insecurity. OBJECTIVE: The objectives of this study are to assess the effect of the TX Sprouts intervention on household food insecurity and to examine the association between changes in household food insecurity and changes in cardiometabolic markers over 1 academic year. METHODS: This secondary analysis used data from TX Sprouts, a cluster-randomized school-based gardening, cooking, and nutrition trial. The study enrolled 3rd-5th-grade students from 16 schools that served primarily (>50%) Hispanic families with low income in Austin, TX. Participants (n = 619) provided household food insecurity data and fasting lipid panels at both baseline and postintervention, ∼9 mo following. RESULTS: There was no intervention effect on household food insecurity. Independent of the intervention, a 1-point increase in food insecurity, indicative of becoming more food insecure, was associated with a 2.61 mg/dL increase in triglycerides (P = 0.001; 95% CI: 1.04, 4.19) at follow-up. Children who were food insecure at baseline and became food secure at follow-up had a mean 5.05 mg/dL decrease in triglycerides compared with a 7.50 mg/dL increase in triglycerides in children who remained food insecure throughout (95% CI: -23.40, -1.71, P = 0.023). There were no other associations between changes in food insecurity and cardiometabolic markers. CONCLUSION: Although the intervention did not improve food insecurity, reductions in food insecurity over 9 mo were associated with improved cardiometabolic markers in high-risk children, emphasizing the need for interventions targeting food insecurity. The study is registered at clinicaltrials.gov under NCT02668744 (https://classic. CLINICALTRIALS: gov/ct2/show/NCT02668744).

Who needs what (features) when? Personalizing engagement with data-driven self-management to improve health equity.

OBJECTIVES: To examine the feasibility of promoting engagement with data-driven self-management of health among individuals from minoritized medically underserved communities by tailoring the design of self-management interventions to individuals' type of motivation and regulation in accordance with the Self-Determination Theory. METHODS: Fifty-three individuals with type 2 diabetes from an impoverished minority community were randomly assigned to four different versions of an mHealth app for data-driven self-management with the focus on nutrition, Platano; each version was tailored to a specific type of motivation and regulation within the SDT self-determination continuum. These versions included financial rewards (external regulation), feedback from expert registered dietitians (RDF, introjected regulation), self-assessment of attainment of one's nutritional goals (SA, identified regulation), and personalized meal-time nutrition decision support with post-meal blood glucose forecasts (FORC, integrated regulation). We used qualitative interviews to examine interaction between participants' experiences with the app and their motivation type (internal-external). RESULTS: As hypothesized, we found a clear interaction between the type of motivation and Platano features that users responded to and benefited from. For example, those with more internal motivation reported more positive experience with SA and FORC than those with more external motivation. However, we also found that Platano features that aimed to specifically address the needs of individuals with external regulation did not create the desired experience. We attribute this to a mismatch in emphasis on informational versus emotional support, particularly evident in RDF. In addition, we found that for participants recruited from an economically disadvantaged community, internal factors, such as motivation and regulation, interacted with external factors, most notably with limited health literacy and limited access to resources. CONCLUSIONS: The study suggests feasibility of using SDT to tailor design of mHealth interventions for promoting data-driven self-management to individuals' motivation and regulation. However, further research is needed to better align design solutions with different levels of self-determination continuum, to incorporate stronger emphasis on emotional support for individuals with external regulation, and to address unique needs and challenges of underserved communities, with particular attention to limited health literacy and access to resources.

Smartphone Applications (Apps) for Nutrition Education: A Qualitative Analysis of Outpatient Dietitian Perspectives.

OBJECTIVE: To explore how outpatient dietitians select and use applications (apps) to support nutrition education. METHODS: Qualitative analysis of 20 dietitians who participated in semistructured interviews investigating their app use and recommendation processes. Transcripts were analyzed using thematic analysis. RESULTS: Four themes described how dietitians perceive apps for nutrition education: (1) nutrition education goals focus on long-term lifestyle behavior change while protecting patients' relationship with food, (2) attitudes toward tracking apps influence app selection, (3) dietitians differentiate among patients who will benefit from tracking vs information apps, and (4) barriers to optimal app use result in adaptations by dietitians. CONCLUSIONS AND IMPLICATIONS: Barriers exist to optimal app use for nutrition education. However, accessible app design, app selection guides, and research expounding the effects of apps and their use by dietitians may improve how practitioners incorporate apps into nutrition education.

Effects of a School-Based Gardening, Cooking, and Nutrition Cluster Randomized Controlled Trial on Unprocessed and Ultra-Processed Food Consumption.

BACKGROUND: School-based gardening and nutrition education interventions report improvements in dietary intake, notably through fruit and vegetables. However, gardening, cooking, and nutrition randomized controlled trials are limited in evaluating dietary quality, and none have examined processed food consumption to date. OBJECTIVES: The study examined the effects of Texas Sprouts (TX Sprouts), a gardening, cooking, and nutrition education intervention, compared with control on unprocessed and ultra-processed food (UPF) consumption in predominately low-income Hispanic children. METHODS: TX Sprouts was a school-based cluster randomized controlled trial that consisted of 16 elementary schools randomly assigned to either the TX Sprouts intervention (n = 8 schools) or control (delayed intervention; n = 8 schools) over 3 y (2016-2019). TX Sprouts schools received an outdoor teaching garden and 18 1-h lessons taught by trained educators throughout the school year. Dietary intake data via 2 24-h dietary recalls were collected on a random subsample (n = 468) at baseline and postintervention. All foods and beverages were categorized using the NOVA food classification system (e.g., unprocessed, processed, ultra-processed). Generalized linear mixed effects modeling tested changes in percent calories and grams of NOVA groups between the intervention and control estimates with schools as random clusters. RESULTS: Of the sample, 63% participated in the free and reduced-price lunch program, and 57% were Hispanic, followed by non-Hispanic White (21%) and non-Hispanic Black (12%). The intervention, compared to the control, resulted in an increase in consumption of unprocessed foods (2.3% compared with -1.8% g; P < 0.01) and a decrease in UPF (-2.4% compared with 1.4% g; P = 0.04). In addition, Hispanic children in the intervention group had an increase in unprocessed food consumption and a decrease in UPF consumption compared to non-Hispanic children (-3.4% compared with 1.5% g; P < 0.05). CONCLUSIONS: Study results suggest that school-based gardening, cooking, and nutrition education interventions can improve dietary intake, specifically increasing unprocessed food consumption and decreasing UPF consumption. This trial was registered at clinicaltrials.gov as NCT02668744.

User-Centered Design of a Clinical Tool for Shared Decision-making About Diet in Primary Care.

BACKGROUND: Health information technology is a leading cause of clinician burnout and career dissatisfaction, often because it is poorly designed by nonclinicians who have limited knowledge of clinicians' information needs and health care workflow. OBJECTIVE: Describe how we engaged primary care clinicians and their patients in an iterative design process for a software application to enhance clinician-patient diet discussions. DESIGN: Descriptive study of the steps followed when involving clinicians and their at-risk patients in the design of the content, layout, and flow of an application for collaborative dietary goal setting. This began with individual clinician and patient interviews to detail the desired informational content of the screens displayed followed by iterative reviews of intermediate and final versions of the program and its outputs. PARTICIPANTS: Primary care clinicians practicing in an urban federally qualified health center and two academic primary care clinics, and their patients who were overweight or obese with diet-sensitive conditions. MAIN MEASURES: Descriptions of the content, format, and flow of information from pre-visit dietary history to the display of evidence-based, guideline-driven suggested goals to final display of dietary goals selected, with information on how the patient might reach them and patients' confidence in achieving them. KEY RESULTS: Through three iterations of design and review, there was substantial evolution of the program's content, format, and flow of information. This involved "tuning" of the information desired: from too little, to too much, to the right amount displayed that both clinicians and patients believed would facilitate shared dietary goal setting. CONCLUSIONS: Clinicians' well-founded criticisms of the design of health information technology can be mitigated by involving them and their patients in the design of such tools that clinicians may find useful, and use, in their everyday medical practice.

School-based intervention impacts availability of vegetables and beverages in participants' homes.

As rates of metabolic syndrome rise, children consume too few vegetables and too much added sugar. Because children tend to eat what is available at home, the home environment plays a key role in shaping dietary habits. This secondary analysis evaluated the effects of a school-based gardening, cooking, and nutrition education intervention (TX Sprouts) compared to control on the availability of vegetables, fruit juice, and sugar-sweetened beverages (SSBs) at home. In the TX Sprouts cluster-randomized trial, 16 schools were randomized to TX Sprouts (n = 8 schools) or control (n = 8 schools) for one academic year. All schools served predominately Hispanic families with low incomes. TX Sprouts built school gardens and taught 18 lessons to all 3rd-5th grade students at intervention schools. TX Sprouts also offered monthly caregiver lessons before and/or after school. Caregivers completed questionnaires pre and post, providing demographics and information about home availability of vegetables, fruit juice, and SSBs. Summary statistics were used to describe the sociodemographic characteristics of participants. Linear regression assessed the change in scores (pre to post) for the food/ beverage availability question. The model was adjusted for the caregiver's education, employment status, child's grade, and free or reduced-price lunch eligibility. The analytic sample included 895 participants. Compared to control, the intervention positively changed the home availability of targeted foods and beverages, largely by improving the availability of vegetables and vegetable juice. This study showed that a school gardening, nutrition, and cooking program delivered to elementary children may positively influence the home food environment.

Psychosocial-Behavioral Phenotyping: A Novel Precision Health Approach to Modeling Behavioral, Psychological, and Social Determinants of Health Using Machine Learning.

BACKGROUND: The context in which a behavioral intervention is delivered is an important source of variability and systematic approaches are needed to identify and quantify contextual factors that may influence intervention efficacy. Machine learning-based phenotyping methods can contribute to a new precision health paradigm by informing personalized behavior interventions. Two primary goals of precision health, identifying population subgroups and highlighting behavioral intervention targets, can be addressed with psychosocial-behavioral phenotypes. We propose a method for psychosocial-behavioral phenotyping that models social determinants of health in addition to individual-level psychological and behavioral factors. PURPOSE: To demonstrate a novel application of machine learning for psychosocial-behavioral phenotyping, the identification of subgroups with similar combinations of psychosocial characteristics. METHODS: In this secondary analysis of psychosocial and behavioral data from a community cohort (n = 5,883), we optimized a multichannel mixed membership model (MC3M) using Bayesian inference to identify psychosocial-behavioral phenotypes and used logistic regression to determine which phenotypes were associated with elevated weight status (BMI ≥ 25kg/m2). RESULTS: We identified 20 psychosocial-behavioral phenotypes. Phenotypes were conceptually consistent as well as discriminative; most participants had only one active phenotype. Two phenotypes were significantly positively associated with elevated weight status; four phenotypes were significantly negatively associated. Each phenotype suggested different contextual considerations for intervention design. CONCLUSIONS: By depicting the complexity of psychological and social determinants of health while also providing actionable insight about similarities and differences among members of the same community, psychosocial-behavioral phenotypes can identify potential intervention targets in context.

Nutri: A Behavioral Science-Based Clinical Decision Support for Chronic Disease Management.

Clinical decision support systems (CDSS) for the ongoing decision making required to support health behavior change for chronic disease management should incorporate behavioral science (e.g., a collaborative goal setting workflow) with more common CDSS components (i.e., an evidence-based knowledge base that processes patient data). Given known challenges with CDSS usability and adoption, engaging clinician end-users in designing new CDSS is vital. Therefore, we tested Nutri, a CDSS for collaborative diet goal setting, with 10 clinicians in a simulated primary care appointment with a patient actor. Simulation recordings, usability surveys, and debriefing interviews provided a multi-method view of clinicians' perceptions of Nutri's value and usability. 100% of participating clinicians achieved Nutri's main objective: selecting a high impact diet goal during a collaborative goal setting discussion with the patient; participants found Nutri usable, potentially timesaving, and increased their diet counseling self-efficacy. Insights will improve Nutri's usability and clinical workflow integration.

Higher Parental Age and Lower Educational Level are Associated with Underweight among Preschool Children in Terengganu, Malaysia.

This cross-sectional study aimed to investigate the determinants of underweight among preschool children. A total of 218 preschool children were enrolled. Their sociodemographic data were collected using self-reported questionnaires whilst body weight and height were measured, recorded and the BMI for-age z-score was calculated using WHO AnthroPlus software. Of all preschool children participants, 47.7% were male and 53.3% were female. Most of them were Malays (99.5%), aged 4 to <5 years (40.8%) and came from low-income household (92.7%). Overall, the prevalence of underweight, normal, overweight and obese was 17.9%, 73.8%, 4.6% and 3.7% respectively. The underweight prevalence was higher than the national prevalence (13.7%). Of all parent participants, 12.4% were male and 87.6% were female. Most of them aged 30-39 years (55.5%) and did not hold a degree (89.4%). Multivariate logistic regression showed that parental age and their level of education were the determinants of childhood underweight. The risk of being underweight increased with the age of parents (p=0.033) and lower level of education of parents (p=0.042). In conclusion, this study found that underweight among preschool children was mainly associated with parental factors. Hence, designing a special nutritional intervention program involving older parents and lower education levels could overcome this problem.

Nasal Feeding Tubes Are Associated with Fewer Adverse Events than Feeding via Ostomy in Hospitalized Patients Receiving Enteral Nutrition.

BACKGROUND: Surgical feeding ostomies (eg, gastrostomy) have become required by many nursing facilities for all patients receiving enteral nutrition, whether for short- or long-term use. These policies lack supportive evidence. Comparisons of adverse event rates between surgical and natural orifice tubes are few and lacking in the inpatient setting. Additionally, we hypothesize that adverse events related to feeding tubes are underreported. We sought to quantify adverse events to test the relative safety of surgical feeding ostomies and natural orifice (eg. nasogastric or orogastric) feeding tubes in hospitalized patients. METHODS: This was a prospective observational cohort study of enterally fed inpatients using semiweekly focused physical examination, scripted survey, and chart review. RESULTS: All tube-fed patients admitted to a large, urban, academic hospital received semiweekly bedside evaluation and chart review over a 9-week period (n = 226 unique patients, mean 6.25 visits each, total 1118 observations). Demographics were comparable between 148 subjects with natural orifice and 113 subjects with surgical feeding tubes. A higher incidence of adverse events was observed with surgical tubes (3.34 vs 1.25 events per 100 subject days, P < .001). Only 50% of all adverse events were documented in the medical record. More patients with surgical tubes were discharged to skilled nursing facilities (58% vs 24%). CONCLUSIONS: Surgical feeding tubes are associated with significantly higher in-hospital adverse event rates when compared with natural orifice (nasal or oral) feeding tubes. Policies requiring surgical feeding ostomies should be reevaluated.

Psychosocial phenotyping as a personalization strategy for chronic disease self-management interventions.

BACKGROUND: As the U.S. population grows older and more diverse, self-management needs are increasingly complicated. In order to deliver effective personalized interventions to those suffer from chronic conditions social determinants of health must be considered. Therefore, psychosocial phenotyping holds strong promise as a tool for tailoring interventions based on precision health principles. PURPOSE: To define psychosocial phenotyping and develop a research agenda that promotes its integration into chronic disease management as a tool for precision self-management interventions. METHODS: Since psychosocial phenotyping is not yet used in interventions for self-management support, we conducted a literature review to identify potential phenotypes for chronic disease self-management. We also reviewed policy intervention case reports from the Centers for Medicare and Medicaid Services to examine factors related to social determinants of health in people with chronic illnesses. Finally, we reviewed methodological approaches for identifying patient profiles or phenotypes. RESULTS: The literature review revealed areas within which to collect data for psychosocial phenotyping that can inform personalized interventions. The findings of our exemplar cases revealed that several environmental or key SDOH such as factors realted with economic stability and neighborhood environment have been closely linked with the success of chronic disease management interventions. We elucidated theory, definitions, and pragmatic conceptual boundaries related to psychosocial phenotyping for precision health. CONCLUSIONS: Our literature review with case example analysis demonstrates the potential usefulness of psychosocial phenotyping as a tool to enhance personalized self-management interventions for people with chronic diseases, with implications for future research.

Barriers, Strategies, and Resources to Thriving School Gardens.

OBJECTIVE: To identify school garden attributes and practices that most strongly contribute to garden use and sustainability and translate them into recommendations for improving garden-based nutrition education. DESIGN: Surveys were developed and administered to school stakeholders to assess the barriers, strategies, and resources for successful school garden-based nutrition education. A panel of school garden experts identified thriving school gardens. Logistic regression was used to identify which attributes predicted thriving school garden programs. SETTING: Approximately 109 schools across Greater Austin, TX. PARTICIPANTS: A total of 523 school teachers and 174 administrators. OUTCOMES: Barriers, strategies, and resources relevant to successful school gardening nutrition programs. RESULTS: Thriving school gardens were 3-fold more likely to have funding and community partner use (P = 0.022 and P = 0.024), 4 times more likely to have active garden committees (P = 0.021), available garden curriculum (P = 0.003), teacher training (P = 0.045), ≥ 100 students who used the garden annually (P = 0.047), and 12 times more likely to have adequate district and administrator support (P = 0.018). CONCLUSIONS AND IMPLICATIONS: Adequate administrative and district support is fundamental when implementing a school garden. Schools may benefit from finding additional funding, providing teacher garden training, providing garden curriculum, forming garden leadership committees, and partnering with local community organizations to improve garden-based nutrition education.

From Reflection to Action: Combining Machine Learning with Expert Knowledge for Nutrition Goal Recommendations.

Self-tracking can help personalize self-management interventions for chronic conditions like type 2 diabetes (T2D), but reflecting on personal data requires motivation and literacy. Machine learning (ML) methods can identify patterns, but a key challenge is making actionable suggestions based on personal health data. We introduce GlucoGoalie, which combines ML with an expert system to translate ML output into personalized nutrition goal suggestions for individuals with T2D. In a controlled experiment, participants with T2D found that goal suggestions were understandable and actionable. A 4-week in-the-wild deployment study showed that receiving goal suggestions augmented participants' self-discovery, choosing goals highlighted the multifaceted nature of personal preferences, and the experience of following goals demonstrated the importance of feedback and context. However, we identified tensions between abstract goals and concrete eating experiences and found static text too ambiguous for complex concepts. We discuss implications for ML-based interventions and the need for systems that offer more interactivity, feedback, and negotiation.

Extended Reality Technologies in Nutrition Education and Behavior: Comprehensive Scoping Review and Future Directions.

The use of Extended Reality (XR) (i.e. Virtual and Augmented Reality) for nutrition education and behavior change has not been comprehensively reviewed. This paper presents findings from a scoping review of current published research. Articles (n = 92) were extracted from PubMed and Scopus using a structured search strategy and selection approach. Pertinent study information was extracted using a standardized data collection form. Each article was independently reviewed and coded by two members of the research team, who then met to resolve any coding discrepancies. There is an increasing trend in publication in this area, mostly regarding Virtual Reality. Most studies used developmental testing in a lab setting, employed descriptive or observational methods, and focused on momentary behavior change like food selection rather than education. The growth and diversity of XR studies suggest the potential of this approach. There is a need and opportunity for more XR technology focused on children and other foundational theoretical determinants of behavior change to be addressed within nutrition education. Our findings suggest that XR technology is a burgeoning approach in the field of nutrition, but important gaps remain, including inadequate methodological rigor, community application, and assessment of the impact on dietary behaviors.

Adapting the stage-based model of personal informatics for low-resource communities in the context of type 2 diabetes.

Growing availability of self-monitoring technologies creates new opportunities for collection of personal health data and their use in personalized health informatics interventions. However, much of the previous empirical research and existing theories of individuals' engagement with personal data focused on early adopters and data enthusiasts. Less is understood regarding ways individuals from medically underserved low-income communities who live with chronic diseases engage with self-monitoring in health. In this research, we adapted a widely used theoretical framework, the stage-based model of personal informatics, to the unique attitudes, needs, and constraints of low-income communities. We conducted a qualitative study of attitudes and perceptions regarding tracking and planning in health and other contexts (e.g., finances) among low-income adults living with type 2 diabetes. This study showed distinct differences in participants' attitudes and behaviors around tracking and planning, as well as wide variability in their sense of being in charge of different areas of one's life. Ultimately, we found a strong connection between these two: perceptions of being in charge seems to be strongly connected to an individual's proactive or reactive tracking and planning in that area. Whereas individuals with a greater sense of being in charge of their health were more proactive, meaning they were likely to engage with all the stages of personal informatics model on their own, those with less of a sense of being in charge were more likely to be reactive-relying on their healthcare providers for several critical stages of self-monitoring (deciding what data to collect, integrating data from multiple sources, reflecting over patterns in collected data, and arriving at conclusions and implications for action). Perhaps as a result, these individuals were less likely to experience increases in self-awareness and self-knowledge, common motivating factors to engaging in self-monitoring in the future. We argue that adapting this framework in a way that highlights gaps in individuals' engagement has a number of important implications for future research in biomedical informatics and for the design of new interventions that promote engagement with self-monitoring, and that are robust in light of fragmented engagement.

Dietary Sodium Restriction for Heart Failure: A Systematic Review of Intervention Outcomes and Behavioral Determinants.

The 1500 mg/d dietary sodium restriction commonly recommended for patients with heart failure has recently been questioned. Poor adherence to sodium-restricted diets makes assessing the efficacy of sodium restriction challenging. Therefore, successful behavioral interventions are needed. We reviewed sodium restriction trials and descriptive studies of sodium restriction to: 1) determine if sodium restriction was achieved in interventions among heart failure patients; and 2) characterize predictors of successful dietary sodium restriction. Among 638 identified studies, 10 intervention trials, and 25 descriptive studies met inclusion criteria. We used content analysis to extract information about sodium restriction and behavioral determinants of sodium restriction. Dietary sodium was reduced in 7 trials; none achieved 1500 mg/d (range 1938-4564 mg/d). The interventions implemented in the interventional trials emphasized knowledge, skills, and self-regulation strategies, but few addressed the determinants correlated with successful sodium restriction in the descriptive studies (eg, social/cultural norms, social support, taste preferences, food access, self-efficacy). Findings suggest that incorporating determinants predictive of successful dietary sodium restriction may improve the success of interventional trials. Without effective interventions to deploy in trials, the safety and efficacy of sodium restriction remains unknown.

Barriers to Preparing and Cooking Vegetables Are Associated with Decreased Home Availability of Vegetables in Low-Income Households.

Knowing which barriers to buying and preparing/cooking vegetables at home are linked with the home availability of vegetables and how food-security status impacts this relationship will facilitate the tailoring of future public health interventions. Baseline data were used from an elementary-school-based intervention. Data on household food-security status, availability of vegetables at home, and barriers to buying and preparing/cooking vegetables were collected from 1942 parents. Differences between food-secure and food-insecure households were examined for barriers to buying and preparing/cooking vegetables. Mixed-effects linear regression was used to estimate the associations between barriers to buying and preparing/cooking vegetables and food-security status on the home availability of vegetables. Food insecurity was reported in 27% of households. Food-insecure households were significantly more likely to report barriers to buying and preparing/cooking vegetables. The barriers to purchasing/cooking vegetables score was associated with a decrease in the home availability of vegetables score (ß = -0.77; 95% CI: -0.88, -0.65; p < 0.001). Compared to food-secure households, food-insecure households were 15% less likely to have home vegetable availability (ß = -1.18; 95% CI: -1.45, -0.92; p < 0.001). Although home availability of vegetables does not guarantee consumption, this study identified specific barriers that were associated with availability that can be targeted in future interventions seeking to improve vegetable consumption in the homes of low-income families.

The potential of digital phenotyping to advance the contributions of mobile health to self-management science.

Digital phenotyping consists of moment-by-moment quantification of behavioral data from individual people, typically collected passively from smartphones and other sensors. Within the evolving context of precision health, digital phenotyping can advance the use of mobile health -based self-management tools and interventions by enabling more accurate prediction for prevention and treatment, facilitating supportive strategies, and informing the development of features to motivate self-management behaviors within real-world conditions. This represents an advancement in self-management science: with digital phenotyping, nurse scientists have opportunities to tailor interventions with increased precision. In this paper, we discuss the emergence of digital phenotyping, the historical background of ecological momentary assessment, and the current state of the science of digital phenotyping, with implications for research design, computational requirements, and ethical considerations in self-management science, as well as limitations.

A new approach to integrating patient-generated data with expert knowledge for personalized goal setting: A pilot study.

INTRODUCTION: Self-monitoring technologies produce patient-generated data that could be leveraged to personalize nutritional goal setting to improve population health; however, most computational approaches are limited when applied to individual-level personalization with sparse and irregular self-monitoring data. We applied informatics methods from expert suggestion systems to a challenging clinical problem: generating personalized nutrition goals from patient-generated diet and blood glucose data. MATERIALS AND METHODS: We applied qualitative process coding and decision tree modeling to understand how registered dietitians translate patient-generated data into recommendations for dietary self-management of diabetes (i.e., knowledge model). We encoded this process in a set of functions that take diet and blood glucose data as an input and output diet recommendations (i.e., inference engine). Dietitians assessed face validity. Using four patient datasets, we compared our inference engine's output to clinical narratives and gold standards developed by expert clinicians. RESULTS: To dietitians, the knowledge model represented how recommendations from patient data are made. Inference engine recommendations were 63 % consistent with the gold standard (range = 42 %-75 %) and 74 % consistent with narrative clinical observations (range = 63 %-83 %). DISCUSSION: Qualitative modeling and automating how dietitians reason over patient data resulted in a knowledge model representing clinical knowledge. However, our knowledge model was less consistent with gold standard than narrative clinical recommendations, raising questions about how best to evaluate approaches that integrate patient-generated data with expert knowledge. CONCLUSION: New informatics approaches that integrate data-driven methods with expert decision making for personalized goal setting, such as the knowledge base and inference engine presented here, demonstrate the potential to extend the reach of patient-generated data by synthesizing it with clinical knowledge. However, important questions remain about the strengths and weaknesses of computer algorithms developed to discern signal from patient-generated data compared to human experts.

Designing for engagement with self-monitoring: A user-centered approach with low-income, Latino adults with Type 2 Diabetes.

BACKGROUND AND SIGNIFICANCE: Data-driven interventions for health can help to personalize self-management of Type 2 Diabetes (T2D), but lack of sustained engagement with self-monitoring among disadvantaged populations may widen existing health disparities. Prior work developing approaches to increase motivation and engagement with self-monitoring holds promise, but little is known about applicability of these approaches to underserved populations. OBJECTIVE: To explore how low-income, Latino adults with T2D respond to different design concepts for data-driven solutions in health that require self-monitoring, and what features resonate with them the most. MATERIAL AND METHODS: We developed a set of mockups that incorporated different design features for promoting engagement with self-monitoring in T2D. We conducted focus groups to examine individuals' perceptions and attitudes towards mockups. Multiple interdisciplinary researchers analyzed data using directed content analysis. RESULTS: We conducted 14 focus groups with 25 English- and Spanish-speaking adults with T2D. All participants reacted positively to external incentives. Social connectedness and healthcare expert feedback were also well liked because they enhanced current social practices and presented opportunities for learning. However, attitudes were more mixed towards goal setting, and very few participants responded positively to self-discovery and personalized decision support features. Instead, participants wished for personalized recommendations for meals and other health behaviors based on their personal health data. CONCLUSION: This study suggests connections between individuals' degree of internal motivation and motivation for self-monitoring in health and their attitude towards designs of self-monitoring apps. We relate our findings to the self-determination continuum in self-determination theory (SDT) and propose it as a blueprint for aligning incentives for self-monitoring to different levels of motivation.