Use of machine learning to predict medication adherence in individuals at risk for atherosclerotic cardiovascular disease.

Background: Medication nonadherence is a critical problem with severe implications in individuals at risk for atherosclerotic cardiovascular disease. Many studies have attempted to predict medication adherence in this population, but few, if any, have been effective in prediction, sug-gesting that essential risk factors remain unidentified. Objective: This study's objective was to (1) establish an accurate prediction model of medi-cation adherence in individuals at risk for atherosclerotic cardiovascular disease and (2) identify significant contributing factors to the predictive accuracy of medication adherence. In particular, we aimed to use only the baseline questionnaire data to assess medication adherence prediction feasibility. Methods: A sample of 40 individuals at risk for atherosclerotic cardiovascular disease was recruited for an eight-week feasibility study. After collecting baseline data, we recorded data from a pillbox that sent events to a cloud-based server. Health measures and medication use events were analyzed using machine learning algorithms to identify variables that best predict medication adherence. Results: Our adherence prediction model, based on only the ten most relevant variables, achieved an average error rate of 12.9%. Medication adherence was closely correlated with being encouraged to play an active role in their treatment, having confidence about what to do in an emergency, knowledge about their medications, and having a special person in their life. Conclusions: Our results showed the significance of clinical and psychosocial factors for predicting medication adherence in people at risk for atherosclerotic cardiovascular diseases. Clini-cians and researchers can use these factors to stratify individuals to make evidence-based decisions to reduce the risks.

SARS-CoV-2 acquisition and immune pathogenesis among school-aged learners in four diverse schools.

BACKGROUND: Understanding SARS-CoV-2 infection in children is necessary to reopen schools safely. METHODS: We measured SARS-CoV-2 infection in 320 learners [10.5 ± 2.1 (sd); 7-17 y.o.] at four diverse schools with either remote or on-site learning. Schools A and B served low-income Hispanic learners; school C served many special-needs learners, and all provided predominantly remote instruction. School D served middle- and upper-income learners, with predominantly on-site instruction. Testing occurred in the fall (2020), and 6-8 weeks later during the fall-winter surge (notable for a tenfold increase in COVID-19 cases). Immune responses and mitigation fidelity were also measured. RESULTS: We found SARS-CoV-2 infections in 17 learners only during the surge. School A (97% remote learners) had the highest infection (10/70, 14.3%, p < 0.01) and IgG positivity rates (13/66, 19.7%). School D (93% on-site learners) had the lowest infection and IgG positivity rates (1/63, 1.6%). Mitigation compliance [physical distancing (mean 87.4%) and face-covering (91.3%)] was remarkably high at all schools. Documented SARS-CoV-2-infected learners had neutralizing antibodies (94.7%), robust IFN-γ + T cell responses, and reduced monocytes. CONCLUSIONS: Schools can implement successful mitigation strategies across a wide range of student diversity. Despite asymptomatic to mild SARS-CoV-2 infection, children generate robust humoral and cellular immune responses. IMPACT: Successful COVID-19 mitigation was implemented across a diverse range of schools. School-associated SARS-CoV-2 infections reflect regional rates rather than remote or on-site learning. Seropositive school-aged children with asymptomatic to mild SARS-CoV-2 infections generate robust humoral and cellular immunity.

SARS-CoV-2 Acquisition and Immune Pathogenesis Among School-Aged Learners in Four Diverse Schools.

BACKGROUND: Understanding SARS-CoV-2 infection in children is necessary to reopen schools safely. METHODS: We measured SARS-CoV-2 infection in 320 learners [10.5 ± 2.1(sd); 7-17 y.o.] at four diverse schools with either remote or on-site learning. Schools A and B served low-income Hispanic learners; school C served many special-needs learners; and all provided predominantly remote instruction. School D served middle- and upper-income learners, with predominantly on-site instruction. Testing occurred in the fall (2020), and 6-8 weeks later during the fall-winter surge (notable for a tenfold increase in COVID-19 cases). Immune responses and mitigation fidelity were also measured. RESULTS: We found SARS-CoV-2 infections in 17 learners only during the surge. School A (97% remote learners) had the highest infection (10/70, 14.3%, p<0.01) and IgG positivity rates (13/66, 19.7%). School D (93% on-site learners) had the lowest infection and IgG positivity rates (1/63, 1.6%). Mitigation compliance [physical distancing (mean 87.4%) and face covering (91.3%)] was remarkably high at all schools. Documented SARS-CoV-2-infected learners had neutralizing antibodies (94.7%), robust IFN-γ+ T cell responses, and reduced monocytes. CONCLUSION: Schools can implement successful mitigation strategies across a wide range of student diversity. Despite asymptomatic to mild SARS-CoV-2 infection, children generate robust humoral and cellular immune responses. KEY POINTS: Successful COVID-19 mitigation was implemented across a diverse range of schools.School-associated SARS-CoV-2 infections reflect regional rates rather than remote or on-site learning.Seropositive school-aged children with asymptomatic to mild SARS-CoV-2 infections generate robust humoral and cellular immunity.

Codesign of a cardiovascular disease prevention text message bank for older adults.

OBJECTIVE: Develop and validate a text message bank to support healthier lifestyle behaviors in older adults at risk for cardiovascular disease utilizing a codesign approach. METHODS: Initially, the researchers, based on literature, developed a bank of 68 SMS text messages focusing on healthy eating (24 messages), physical activity (24 messages), and motivational feedback (20 messages), based on a scoping review of the literature on promoting behavioral change to engage in healthy lifestyle behaviors. In the next step, a panel of five experts analyzed every subset of SMS text messages. Further validation was conducted by nine older adults (≥ 60 years). The user demographics, telephone literacy, understanding, and appeal for every SMS text message were evaluated using a 31-item questionnaire. RESULTS: Participants provided an acceptable understanding of the critical concept found in the 49 SMS text message (physical activity M = 1.73 ± 0.18; diet M = 1.73 ± 0.26; motivation M = 1.85 ± 0.25; range 0-2). The average ratings for physical activity (i.e., likability), healthy eating, and motivation were 8.62 ± 0.64, 8.57 ± 0.76, and 8.40 ± 0.83, respectively (range 0-10). CONCLUSION: Co-designers were able to identify the technological and content requirements for each text message and infographic to enhance understanding and appeal. PRACTICE IMPLICATIONS: A feasibility study will need to be conducted as a next step to testing the effectiveness of text messages in a mobile-based intervention to promote healthy behaviors in older adults at high CVD risk.