The Development and Potential Applications of an Automated Method for Detecting and Classifying Continuous Glucose Monitoring Patterns.

INTRODUCTION: Continuous glucose monitoring (CGM) is emerging as a transformative tool for helping people with diabetes self-manage their glucose and supporting clinicians in effective treatment. Unfortunately, many CGM users, and clinicians, find interpreting the large volume of CGM data to be overwhelming and complex. To address this challenge, an efficient, intelligent method for detecting and classifying discernable patterns in CGM data was desired. METHODS: We developed an automated artificial intelligence (AI)-driven method to detect and classify different discernable CGM patterns which called "CGM events." We trained different models using 60 days of CGM data from 27 individuals with diabetes from a publicly available data set and then evaluated model performance using separate test data from the same group. Each event is classified according to clinical significance based on three parameters: (1) glucose category at or near the beginning of the CGM event; (2) a calculated severity score that encompasses both signal shape and temporal characteristics (e.g., how high the CGM curve goes (measured in mg/dL) and how long it stays above target (as established by published consensus guidelines); and (3) the glucose category at or near the end of the event. RESULTS: The system accurately detected and classified events from actual CGM data. This was also validated with expert diabetes clinicians. CONCLUSIONS: Advanced pattern recognition methods can be used to detect and classify CGM events of interest and may be used to provide actionable insights and self-management support to CGM users and decision support to the clinicians caring for them.

Huddling with families after disaster: Human resilience and social disparity.

Disasters, from hurricanes to pandemics, tremendously impact human lives and behaviors. Physical closeness to family post-disaster plays a critical role in mental healing and societal sustainability. Nonetheless, little is known about whether and how family colocation alters after a disaster, a topic of immense importance to a post-disaster society. We analyze 1 billion records of population-scale, granular, individual-level mobile location data to quantify family colocation, and examine the magnitude, dynamics, and socioeconomic heterogeneity of the shift in family colocation from the pre- to post-disaster period. Leveraging Hurricane Florence as a natural experiment, and Geographic Information System (GIS), machine learning, and statistical methods to investigate the shift across the landfall (treated) city of Wilmington, three partially treated cites on the hurricane's path, and two control cities off the path, we uncover dramatic (18.9%), widespread (even among the partially treated cities), and enduring (over at least 3 months) escalations in family colocation. These findings reveal the powerful psychological and behavioral impacts of the disaster upon the broader populations, and simultaneously remarkable human resilience via behavioral adaptations during disastrous times. Importantly, the disaster created a gap across socioeconomic groups non-existent beforehand, with the disadvantaged displaying weaker lifts in family colocation. This sheds important lights on policy making and policy communication to promote sustainable family colocation, healthy coping strategies against traumatic experiences, social parity, and societal recovery.

DI++: A deep learning system for patient condition identification in clinical notes.

Accurately recording a patient's medical conditions in an EHR system is the basis of effectively documenting patient health status, coding for billing, and supporting data-driven clinical decision making. However, patient conditions are often not fully captured in structured EHR systems, but may be documented in unstructured clinical notes. The challenge is that not all disease mentions in clinical notes actually refer to a patient's conditions. We developed a two-step workflow for identifying patient's conditions from clinical notes: disease mention extraction and disease mention classification. We implemented this workflow in a prototype system, DI++, for Disease Identification. An advanced deep learning model, CLSTM-Attention model, is developed for disease mention classification in DI++. Extensive empirical evaluation on about one million pages of de-identified clinical notes demonstrates that DI++ has significant performance advantage over existing systems on F1 Score, Area Under the Curve metrics, and efficiency. The proposed CLSTM-Attention model outperforms the existing deep learning models for disease mention classification.

Engagement and Outcomes Associated with Contextual Annotation Features of a Digital Health Solution.

BACKGROUND: Digital health solutions targeting diabetes self-care are popular and promising, but important questions remain about how these tools can most effectively help patients. Consistent with evidence of the salutary effects of note-taking in education, features that enable annotation of structured data entry might enhance the meaningfulness of the interaction, thereby promoting persistent use and benefits of a digital health solution. METHOD: To examine the potential benefits of note-taking, we explored how patients with type 2 diabetes used annotation features of a digital health solution and assessed the relationship between annotation and persistence in engagement as well as improvements in glycated hemoglobin (A1C). Secondary data from 3142 users of the BlueStar digital health solution collected between December 2013 and June 2017 were analyzed, with a subgroup of 372 reporting A1C lab values. RESULTS: About a third of patients recorded annotations while using the platform. Annotation themes largely reflected self-management behaviors (diet, physical activity, medication adherence) and well-being (mood, health status). Early use of contextual annotations was associated with greater engagement over time and with greater improvements in A1C. CONCLUSIONS: Our research provides preliminary evidence of the benefits of annotation features in a digital health solution. Future research is needed to assess the causal impact of note-taking and the moderating role of thematic content reflected in notes.

Market segmentation of South African adolescent girls and young women to inform HIV prevention product marketing strategy: A mixed methods study.

The uptake of and adherence to HIV prevention products in South Africa has not achieved widespread success. This study aimed to develop a holistic understanding of the psychographics of adolescent girls and young women in South Africa, a primary audience for HIV prevention products, in order to inform market segmentation and marketing strategies. Extensive ethnographic analyses were complemented with a survey (n = 1,500) centered on personal care product journeys. Clustering and qualitative methods yielded six segments with measurable differences, and revealed common themes surrounding empowerment and self-determination, patriarchy, and misinformation risk. The findings enable targeted approaches for HIV prevention product campaigns.

Socioeconomic privilege and political ideology are associated with racial disparity in COVID-19 vaccination.

Vaccine uptake is critical for mitigating the impact of COVID-19 in the United States, but structural inequities pose a serious threat to progress. Racial disparities in vaccination persist despite the increased availability of vaccines. We ask what factors are associated with such disparities. We combine data from state, federal, and other sources to estimate the relationship between social determinants of health and racial disparities in COVID-19 vaccinations at the county level. Analyzing vaccination data from 19 April 2021, when nearly half of the US adult population was at least partially vaccinated, we find associations between racial disparities in COVID-19 vaccination and median income (negative), disparity in high school education (positive), and vote share for the Republican party in the 2020 presidential election (negative), while vaccine hesitancy is not related to disparities. We examine differences in associations for COVID-19 vaccine uptake as compared with influenza vaccine. Key differences include an amplified role for socioeconomic privilege factors and political ideology, reflective of the unique societal context in which the pandemic has unfolded.

Influence of Personality on mHealth Use in Patients with Diabetes: Prospective Pilot Study.

BACKGROUND: Mobile technology for health (mHealth) interventions are increasingly being used to help improve self-management among patients with diabetes; however, these interventions have not been adopted by a large number of patients and often have high dropout rates. Patient personality characteristics may play a critical role in app adoption and active utilization, but few studies have focused on addressing this question. OBJECTIVE: This study aims to address a gap in understanding of the relationship between personality traits and mHealth treatment for patients with diabetes. We tested the role of the five-factor model of personality traits (openness to experience, conscientiousness, extraversion, agreeableness, and neuroticism) in mHealth adoption preference and active utilization. METHODS: We developed an mHealth app (DiaSocial) aimed to encourage diabetes self-management. We recruited 98 patients with diabetes-each patient freely chose whether to receive the standard care or the mHealth app intervention. Patient demographic information and patient personality characteristics were assessed at baseline. App usage data were collected to measure user utilization of the app. Patient health outcomes were assessed with lab measures of glycated hemoglobin (HbA1c level). Logistic regression models and linear regression were employed to explore factors predicting the relationship between mHealth use (adoption and active utilization) and changes in health outcome. RESULTS: Of 98 study participants, 46 (47%) downloaded and used the app. Relatively younger patients with diabetes were 9% more likely to try and use the app (P=.02, odds ratio [OR] 0.91, 95% CI 0.85-0.98) than older patients with diabetes were. Extraversion was negatively associated with adoption of the mHealth app (P=.04, OR 0.71, 95% CI 0.51-0.98), and openness to experience was positively associated with adoption of the app (P=.03, OR 1.73, 95% CI 1.07-2.80). Gender (P=.43, OR 0.66, 95% CI 0.23-1.88), education (senior: P=.99, OR 1.00, 95% CI 0.32-3.11; higher: P=.21, OR 2.51, 95% CI 0.59-10.66), and baseline HbA1c level (P=.36, OR 0.79, 95% CI 0.47-1.31) were not associated with app adoption. Among those who adopted the app, a low education level (senior versus primary P=.003; higher versus primary P=.03) and a high level of openness to experience (P=.048, OR 2.01, 95% CI 1.01-4.00) were associated with active app utilization. Active users showed a significantly greater decrease in HbA1c level than other users (ΔHbA1c=-0.64, P=.05). CONCLUSIONS: This is one of the first studies to investigate how different personality traits influence the adoption and active utilization of an mHealth app among patients with diabetes. The research findings suggest that personality is a factor that should be considered when trying to identify patients who would benefit the most from apps for diabetes management.

Unpacking mHealth interventions: A systematic review of behavior change techniques used in randomized controlled trials assessing mHealth effectiveness.

OBJECTIVE: Mobile health interventions have surged in popularity but their implementation varies widely and evidence of effectiveness is mixed. We sought to advance understanding of the diversity of behavior change techniques in mHealth interventions, especially those that leverage advanced mobile technologies. METHODS: We conducted a systematic review of articles published between 2007 and 2017 in high-impact journals in medicine, medical informatics, and health psychology to identify randomized controlled trials in which the effectiveness of an mobile health intervention was tested. Search terms included a mix of general (e.g. mobile health), hardware (e.g. Android, iPhone), and format (e.g. SMS, application) terms. RESULTS: In a systematic review of 21 studies, we found the techniques of personalization, feedback and monitoring, and associations were most commonly used in mobile health interventions, but there remains considerable opportunity to leverage more sophisticated aspects of ubiquitous computing. We found that prompts and cues were the most common behavior change techniques used in effective trials, but there was notable overlap in behavior change techniques used in ineffective trials. CONCLUSIONS: Our results identify techniques that are commonly used in mobile health interventions and highlight pathways to advance the science of mobile health.

Individual differences in regulatory mode moderate the effectiveness of a pilot mHealth trial for diabetes management among older veterans.

mHealth tools to help people manage chronic illnesses have surged in popularity, but evidence of their effectiveness remains mixed. The aim of this study was to address a gap in the mHealth and health psychology literatures by investigating how individual differences in psychological traits are associated with mHealth effectiveness. Drawing from regulatory mode theory, we tested the role of locomotion and assessment in explaining why mHealth tools are effective for some but not everyone. A 13-week pilot study investigated the effectiveness of an mHealth app in improving health behaviors among older veterans (n = 27) with poorly controlled Type 2 diabetes. We developed a gamified mHealth tool (DiaSocial) aimed at encouraging tracking of glucose control, exercise, nutrition, and medication adherence. Important individual differences in longitudinal trends of adherence, operationalized as points earned for healthy behavior, over the course of the 13-week study period were found. Specifically, low locomotion was associated with unchanging levels of adherence during the course of the study. In contrast, high locomotion was associated with generally stronger adherence although it exhibited a quadratic longitudinal trend. In addition, high assessment was associated with a marginal, positive trend in adherence over time while low assessment was associated with a marginal, negative trend. Next, we examined the relationship between greater adherence and improved clinical outcomes, finding that greater adherence was associated with greater reductions in glycated hemoglobin (HbA1c) levels. Findings from the pilot study suggest that mHealth technologies can help older adults improve their diabetes management, but a "one size fits all" approach may yield suboptimal outcomes.

How Online Quality Ratings Influence Patients' Choice of Medical Providers: Controlled Experimental Survey Study.

BACKGROUND: In recent years, the information environment for patients to learn about physician quality is being rapidly changed by Web-based ratings from both commercial and government efforts. However, little is known about how various types of Web-based ratings affect individuals' choice of physicians. OBJECTIVE: The objective of this research was to measure the relative importance of Web-based quality ratings from governmental and commercial agencies on individuals' choice of primary care physicians. METHODS: In a choice-based conjoint experiment conducted on a sample of 1000 Amazon Mechanical Turk users in October 2016, individuals were asked to choose their preferred primary care physician from pairs of physicians with different ratings in clinical and nonclinical aspects of care provided by governmental and commercial agencies. RESULTS: The relative log odds of choosing a physician increases by 1.31 (95% CI 1.26-1.37; P<.001) and 1.32 (95% CI 1.27-1.39; P<.001) units when the government clinical ratings and commercial nonclinical ratings move from 2 to 4 stars, respectively. The relative log odds of choosing a physician increases by 1.12 (95% CI 1.07-1.18; P<.001) units when the commercial clinical ratings move from 2 to 4 stars. The relative log odds of selecting a physician with 4 stars in nonclinical ratings provided by the government is 1.03 (95% CI 0.98-1.09; P<.001) units higher than a physician with 2 stars in this rating. The log odds of selecting a physician with 4 stars in nonclinical government ratings relative to a physician with 2 stars is 0.23 (95% CI 0.13-0.33; P<.001) units higher for females compared with males. Similar star increase in nonclinical commercial ratings increases the relative log odds of selecting the physician by female respondents by 0.15 (95% CI 0.04-0.26; P=.006) units. CONCLUSIONS: Individuals perceive nonclinical ratings provided by commercial websites as important as clinical ratings provided by government websites when choosing a primary care physician. There are significant gender differences in how the ratings are used. More research is needed on whether patients are making the best use of different types of ratings, as well as the optimal allocation of resources in improving physician ratings from the government's perspective.

A changing landscape of physician quality reporting: analysis of patients' online ratings of their physicians over a 5-year period.

BACKGROUND: Americans increasingly post and consult online physician rankings, yet we know little about this new phenomenon of public physician quality reporting. Physicians worry these rankings will become an outlet for disgruntled patients. OBJECTIVE: To describe trends in patients' online ratings over time, across specialties, to identify what physician characteristics influence online ratings, and to examine how the value of ratings reflects physician quality. METHODS: We used data from RateMDs.com, which included over 386,000 national ratings from 2005 to 2010 and provided insight into the evolution of patients' online ratings. We obtained physician demographic data from the US Department of Health and Human Services' Area Resource File. Finally, we matched patients' ratings with physician-level data from the Virginia Medical Board and examined the probability of being rated and resultant rating levels. RESULTS: We estimate that 1 in 6 practicing US physicians received an online review by January 2010. Obstetrician/gynecologists were twice as likely to be rated (P < .001) as other physicians. Online reviews were generally quite positive (mean 3.93 on a scale of 1 to 5). Based on the Virginia physician population, long-time graduates were more likely to be rated, while physicians who graduated in recent years received higher average ratings (P < .001). Patients gave slightly higher ratings to board-certified physicians (P = .04), those who graduated from highly rated medical schools (P = .002), and those without malpractice claims (P = .1). CONCLUSION: Online physician rating is rapidly growing in popularity and becoming commonplace with no evidence that they are dominated by disgruntled patients. There exist statistically significant correlations between the value of ratings and physician experience, board certification, education, and malpractice claims, suggesting a positive correlation between online ratings and physician quality. However, the magnitude is small. The average number of ratings per physician is still low, and most rating variation reflects evaluations of punctuality and staff. Understanding whether they truly reflect better care and how they are used will be critically important.