Visual Analytics for Health Monitoring and Risk Management in CARRE

Zhao, Youbing; Parvinzamir, Farzad; Wei, Hui; Liu, Enjie; Deng, Zhikun; Dong, Feng; Third, Allan; Lukoševičius, Arūnas; Marozas, Vaidotas; Kaldoudi, Eleni; Clapworthy, Gordon

doi:10.1007/978-3-319-40259-8_33

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Participants were provided with a Withings Body digital scale that transmits weights via Wi-Fi or Bluetooth and has a margin of error on weight <200 g against a gold standard scale [ 43 ]. The participants were encouraged to weigh themselves daily at home.…”

Section: Methodsmentioning

confidence: 99%

A Web-Based mHealth Intervention With Telephone Support to Increase Physical Activity Among Pregnant Patients With Overweight or Obesity: Feasibility Randomized Controlled Trial

Thomas¹,

Xu²,

Sridhar³

et al. 2022

JMIR Form Res

View full text Add to dashboard Cite

Background Pregnant patients with overweight or obesity are at high risk for perinatal complications. Excess gestational weight gain (GWG) further exacerbates this risk. Mobile health (mHealth) lifestyle interventions that leverage technology to facilitate self-monitoring and provide just-in-time feedback may motivate behavior change to reduce excess GWG, reduce intervention costs, and increase scalability by improving access. Objective This study aimed to test the acceptability and feasibility of a pilot mHealth lifestyle intervention for pregnant patients with overweight or obesity to promote moderate intensity physical activity (PA), encourage guideline-concordant GWG, and inform the design of a larger pragmatic cluster randomized controlled trial. Methods We conducted a mixed methods acceptability and feasibility randomized controlled trial among pregnant patients with a prepregnancy BMI of 25 to 40 kg/m2. Patients with singletons at 8 to 15 weeks of gestation who were aged ≥21 years and had Wi-Fi access were recruited via email from 2 clinics within Kaiser Permanente Northern California and randomized to receive usual prenatal care or an mHealth lifestyle intervention. Participants in the intervention arm received wireless scales, access to an intervention website, activity trackers to receive automated feedback on weight gain and activity goals, and monthly calls from a lifestyle coach. Surveys and focus groups with intervention participants assessed intervention satisfaction and ways to improve the intervention. PA outcomes were self-assessed using the Pregnancy Physical Activity Questionnaire, and GWG was assessed using electronic health record data for both arms. Results Overall, 33 patients were randomly assigned to the intervention arm, and 35 patients were randomly assigned to the usual care arm. All participants in the intervention arm weighed themselves at least once a week, compared with 20% (7/35) of the participants in the usual care arm. Participants in the intervention arm wore the activity tracker 6.4 days per week and weighed themselves 5.3 times per week, and 88% (29/33) of them rated the program “good to excellent.” Focus groups found that participants desired more nutrition-related support to help them manage GWG and would have preferred an app instead of a website. Participants in the intervention arm had a 23.46 metabolic equivalent of task hours greater change in total PA per week and a 247.2-minute greater change in moderate intensity PA per week in unadjusted models, but these effects were attenuated in adjusted models (change in total PA: 15.55 metabolic equivalent of task hours per week; change in moderate intensity PA: 199.6 minutes per week). We found no difference in total GWG (mean difference 1.14 kg) compared with usual care. Conclusions The pilot mHealth lifestyle intervention was feasible, highly acceptable, and promoted self-monitoring. Refined interventions are needed to effectively affect PA and GWG among pregnant patients with overweight or obesity. Trial Registration ClinicalTrials.gov NCT03936283; https://clinicaltrials.gov/ct2/show/NCT03936283

show abstract

Section: Methodsmentioning

confidence: 99%

A Web-Based mHealth Intervention With Telephone Support to Increase Physical Activity Among Pregnant Patients With Overweight or Obesity: Feasibility Randomized Controlled Trial

Thomas¹,

Xu²,

Sridhar³

et al. 2022

JMIR Form Res

View full text Add to dashboard Cite

show abstract

“…The role of visual analytics is to visualize health data, risk factor data and the integrated visual analysis of health data and risk factor data. CARRE provides web-based components for interactive health data visualization and risk analysis, including healthline and parallel coordinates for fitness and biomarker data, node-link diagram, chord diagram and sankey diagram for risk factor data visual analysis and a preliminary experiment on personalized risk visualization and disease progression simulation [57]. A healthline is a special form of timeline to visualize multiple variables of continuous fitness statistics and biomedical markers which may cover a long period and in CARRE it is used to display personal sensor data.…”

Section: Visual Analyticsmentioning

confidence: 99%

Personalized Patient Empowerment and Shared Decision Support for Cardiorenal Disease and Comorbidities

Kaldoudi

2016

European Project Space on Intelligent Technologies, Software Engineering, Computer Vision, Graphics, Optics and Photonics

Self Cite

View full text Add to dashboard Cite

The Chronic heart and kidney disease are serious and common amongst the world population. They often appear simultaneously and they can cause each other, while they share a multitude of underlying risk conditions, such as obesity, diabetes, and hypertension. To help tackle cardiorenal disease, the European Commission funded the CARRE interdisciplinary research consortium to compile a variety of personalized alerting, planning and educational services so that patients and professionals alike are empowered and can make shared informed decisions. CARRE project uses commonly available personal sensors, such as activity trackers, scales and personal health records, to collect information about the person, which is then projected against current medical knowledge to produce a personalized risk prediction model. This paper presents an overview of the project outcomes including breakthroughs in sensor technology, semantic technologies, visual analytics, and decision support services.

show abstract