Introduction

Living Healthy is a platform that supports a team based approach to diabetes prevention and management platform. It features a fun and easy consumer facing responsive web and mobile app to set healthy lifestyle goals, and track achievements. The app also connects to a powerful practice level dashboard on the backend for caregiver support and feedback. The lifestyle and behavioral goals are evidence based targets that supports shared accountability between patient and caregiver.

Background

The American Diabetes Association commissioned the study The Economic Costs of Diabetes in the US in 2012 which found $176 billion in direct medical costs as a result of diabetes1. Care for people with diagnosed diabetes accounts for slightly more than 20% of total health care dollars spent in the US1.

People with diagnosed diabetes have medical expenditures which average 2.3 times higher than those without diabetes. Hospitalizations and prescription medications account for 61% of direct medical costs for people with diagnosed diabetes. Using the NHANES survey from 2011-2012, we found a significantly higher rates of hospitalization (A) and prescribed medications (B) among persons with diabetes compared to those with prediabetes and without diabetes.

A. Percent hospitalized in the last year Hospitalization B. Average number of prescribed medications Medications

Using the NHANES data sets and the Guiding Principles for the Care of People With or at Risk for Diabetes set forth by the National Diabetes Education Program (NDEP), the Living Healthy platform attempts to provide a communications, data, and personal disease management technology to help chronically ill diabetes patients improve their health and lower medical costs. The app also supports the primary prevention of diabetes.

NHANES

Twelve different NHANES data sets were used from the 2011-2012 survey. Lifestyle management included recent smoking, alcohol use, drug use. diet behavior, consumer behavior, and physical activity. Demographics were included since age and ethnicity are important for diabetes patient management. Hospitalizations and prescription medications data sets were used to model medical expenditures. HbA1c and BMI are critical laboratory and physical diabetes measures. The NHANES data was classified into three groups, with diabetes or prediabetes and without diabetes based on diabetes questionnaire data.

Design Principles

  1. Fun and simple
  2. Positive reinforcement and gamification
  3. Link to health care provider and feedback
  4. Evidence based therapies and targets includes the what the goals are and tips on how to achieve the goals

Rationale for the 5 behavioral and lifestyle targets and goals

The proposed technology is aimed at promoting lifestyle and medication adherence behaviors that have been shown in randomized clinical trials and meta-analyses to prevent or delay diabetes development as well as improve health outcomes for persons with diabetes. It utilizes principles to engender shared accountability3 between patients and health care providers and to support behavioral changes to prevent diabetes, lower hospital admissions and reduce medications use. Targeted behaviors include medication adherence, physical activity, sedentary minutes, weight goals, and smoking secession.

  1. Medication adherence is a prime target for the app since medication nonadherence has been estimated to cost the U.S. health care system between $100-289 billion annually 4. Daily accountability of medication is tracked using a prompt for "Did you take all your medicines today?". The app also captures possible adverse side effects by asking Have you experienced any changes in your health or well-being?. This data can be used by the health care provider to adjust medications and troubleshoot medication adherence immediately upon patient's request or at the next schedule appointment. Immediate reporting may provide a more accurate assessment of possible adverse side effects by minimizing recall bias. Most importantly, it allows for immediate feedback and action from the health care provider.

  2. Smoking cessation is included as Principle #7 of the Guiding Principles for the Care of People With or at Risk for Diabetes from the National Diabetes Education Program of the NIH and CDC.

  3. Sedentary minutes is an independent risk factor for adverse health outcomes (ref). The goal is to have a maximum of 1 hour of continuous sitting per day. The app asks for the "Longest stretch of hours sitting with TV, Computer, mobile devices".

  4. Physical activity is included as Principle #5 of the Guiding Principles for the Care of People With or at Risk for Diabetes from the National Diabetes Education Program of the NIH and CDC. In the Diabetes Prevention Program, the lifestyle intervention reduced the risk for diabetes by 58% compared to placebo5.

  5. Weight loss is a prime target for intervention to reduce risk of diabetes5 and improve outcomes for those with diabetes6. In the Look AHEAD study, the lifestyle intervention aimed at weight loss reduced sleep apnea and need for diabetes medications, and improved mobility and quality of life. In the DPP, the risk for developing diabetes is reduced by 16% per 1kg of weight lost.

From the NHANES data, we describe the current estimates of the behavioral targets by diabetes status. Persons with diabetes had significantly higher sedentary minutes, BMI and lower physical activity.

Cigarette use
Sedentary minutes
Physical activity mins
BMI

Behavioral Modeling Engine

Analyses were conducted using the NHANES data to give further support for the behavioral targets. Ordered logistic regression models7 were used to assess the the age adjusted relationship between number of hospitalizations and number of medications used and the 5 goals. All five behavioral targets were independently associated with prescription use but only cigarette use and physical activity were associated with hospitalization. The significant reductions in the odds of hospitalization by 36% and in the use of prescription medications by 80% among those with pre-diabetes compared to those without diabetes highlights the importance of diabetes prevention efforts.

The models can also be used to predict the probability of getting hospitalized or receiving a new medication to help healthcare providers identify high risk subjects. Each patient in the practice is assigned a probability of progressing from their current hospitalization number to the next (for example, from none to 1 or from hospitalization 3 to 4) and thresholds can be put in place to identify high risk subjects. For example, patients with a probability of 80% or greater for hospitalization can be easily identified and proactive management can be initiated.

Patient App

Living Healthy is a fun and easy consumer facing responsive web app that can be used on a smartphone, tablet or PC. User submit the five key diabetes behavior data. Features include a gamification mode where the users can earn badges through active app use and encouraging message notifications from the platform and their caregivers. Patients can track how they are doing with their personalized goals, get healthy living tips and send notifications to their caregivers.

Caregiver Support Admin

The caregiver admin dashboard provides overview statistics of the diabetes patients for the primary healthcare provider in the healthcare system. These include the daily active app users by diabetes cohort group, hospital use, medication adherence, critical diabetes management vitals, and behavioral goals. Caregivers can also read and respond to their patient's notifications sent through the app. Data from the high risk patients identified by the predictive model can be viewed and caregivers can send them notifications.

References

  1. American Diabetes Association. Economic costs of diabetes in the U.S. in 2012. Diabetes Care. 2013;36(4):1033–46.
  2. Centers for Disease Control and Prevention. National Diabetes Statistics Report: Estimates of Diabetes and Its Burden in the United States, 2014. Atlanta, GA: U.S. Department of Health and Human Services; 2014.
  3. Peterson, Eric D., et al. "ACC/AHA/AACVPR/AAFP/ANA Concepts for Clinician–Patient Shared Accountability in Performance Measures: A Report of the American College of Cardiology/American Heart Association Task Force on Performance Measures." Journal of the American College of Cardiology 64.20 (2014): 2133-2145.
  4. Viswanathan M, Golin CE, Jones CD, Ashok M, Blalock SJ, Wines RC, Coker-Schwimmer EJ, Rosen DL, Sista P, Lohr KN. Interventions to improve adherence to self-administered medications for chronic diseases in the United States: a systematic review. Annals of Internal Medicine 2012; 157(11): 785-795.
  5. Knowler WC, Barrett-Connor E, Fowler SE, et al. Reduction in the incidence of type 2 diabetes with lifestyle intervention or metformin. N Engl J Med. 2002;346(6):393–403.
  6. Rejeski WJ, Ip EH, Bertoni AG, et al. Lifestyle change and mobility in obese adults with type 2 diabetes. N Engl J Med. 2012;366(13):1209–17.
  7. Agresti, Alan, and Maria Kateri. Categorical data analysis. Springer Berlin Heidelberg, 2011.

Built With

Share this project:
×

Updates