To gather readily available data via a platform that is accessible to a very high portion of the US population and quantify it into metrics that enables better patient outcome predictions while reducing the costs associated with the complex care of patients suffering from Heart Failure (HF)
In the United States alone there are 5.8 million HF patients and 550,000 new cases are diagnosed annually. Each year the disease is responsible for 1 million hospital admissions at a mean cost of $10,500 per stay. The number of admissions has remained stable since 2000 despite efforts to control the disease on an outpatient basis and prevent this tremendous health care expenditure. HF is considered an “ambulatory care sensitive condition” meaning that “hospitalizations...could often be avoided if these patients received timely and appropriate medical care in outpatient settings” according to the CDC.
Data from a representative group of patients with comorbidities can play an important role in advancing the care of the greater population of patients with HF for three main reasons. First, the HF population is heterogeneous, comprised of both genders and many ethnicities. Both factors portend different disease outcomes yet the populations studied during pharmaceutical trials are typically homogenous. Second, patients are often polypharmacy patients where large sample sizes versus individual physiology and condition are studied in understanding systemic and long-term drug effects leaving big data opportunities for more customized healthcare. Lastly, predictive analytics are currently isolated to use in electronic health records. HF is a day to day affliction and prediction algorithms must include data that is generated and analyzed more frequently than patients visit their healthcare providers.
We propose gathering non-invasive data via existing cell phone and linked technology from HF patients who consent to participate through our application build with Apple's ResearchKit. With this big data, we will build predictive analytical algorithms in order to understand the subtle changes that provide a broader sense of disease control.
Patients would benefit from this data collection as it would expedite finding the target dose range at a patient-specific level and avoid some negative health trends existing today. There would be less need for visits with their care provider and potentially increased adherence by decreasing the initial complexity of dosing in early-staged disease.
Healthcare providers would be able to rely on real world data rather than data obtained anecdotally or through a homogenous drug study in order to optimize drug choices and doses. They could set more accurate initial dose rates to get patients to their target doses faster and decrease subsequent patient visits for adjustments.
Payers would benefit from decreased admissions and associated costs because patients and providers will be better equipped to avoid exacerbations with improved early detection and appropriate ambulatory treatment of the disease.
The FDA has a very specific list of requirements for designing clinical trials and by analyzing large amounts of polypharmacy data from drugs that are approved will help determine what is useful information for future products coming to market. This would allow for a robust patient and provider driven postmarket data analysis with large patient populations with longer endpoints.
Easy one-click social registrationIs this safe?
We only receive the minimum information necessary to verify your account. We never get access to your friends/contacts or your profile, and we never post on your behalf. Your social account is used for logging in only.ORRegister via email
Send me updates on this Contest
In order to ensure a fair voting process and to make sure that no one votes more than once, we ask that you register either with a social networking account (easiest, only requires one click) or by registering with your email address (this will require you to click on a verification email that we will send you).
You only need to register once.