Predictive Algorithm to identify Medication Adherence/Non Adherence Pattern in chronically ill individuals
Medication adherence is defined by the World Health Organization as “the degree to which the person’s behavior corresponds with the agreed recommendations from a health care provider.” Poor adherence to prescribed regimens can result in serious health consequences. For instance, a recent study found that the risk of hospitalization was more than double in patients with diabetes mellitus, hypercholesterolemia, hypertension, or congestive heart failure who were non adherent to prescribed therapies compared with the general population.
Non adherence to medication costs $290B in avoidable medical spending every year and drives $100B in hospital readmission each year. Medication adherence is difficult with each individual facing different barriers to maintaining adherence that can range from forgetfulness, affordability, distance from the provider/pharmacy, complex drug regimen, toxicity and side effects to drugs, lack of provider engagement, and other myriad conditions.
The business use case is to identify the adherence and non adherence patterns of patients who have been on a drug therapy in the past 365 days to any of the following chronic conditions: Diabetes, Hypertension, Lipid Disorders, Depression, Congestive Heart Failure, Persistent Asthma, Hypothyroidism under the following conditions: First Fill Abandonment, Second Fill, Ongoing Therapy and Therapy drop off.
This predictive analytics algorithm will help identify patients, either new to therapy or on ongoing therapy, that will be adherent or non adherent to their therapy. By knowing which patients will be non adherent to therapy, we can use guided personalized interventions either through education, consumer engagement through provider, pharmacist or community health worker and other methods to help improve adherence in these patients and help them control and manage their condition rather then resulting in an adverse condition stemming from lack of medication.
By: Shaema Talib