Few recent trends have had as profound an effect on life sciences organisations as the healthcare industry’s transition to value-based care with its focus on outcomes.
No longer is it enough to deliver drugs and devices that have proven to be effective in clinical trials. Today, life sciences organisations are being asked to assume part of the financial risk for the specific patient outcomes for which healthcare providers are being held accountable.
Current estimates from the Health Care Payment Learning & Action Network (HCP-LAN) show that roughly 25% of healthcare dollars are tied to value-based contracts today. By 2020, it’s expected that we will reach the tipping point, where more than 50% of healthcare dollars are reimbursed through these types of contracts.
What that means in a practical sense is that life sciences organisations cannot merely sell products to healthcare providers. They must also take an active role interest in ensuring patients are using those products as-prescribed. After all, as former US surgeon general C. Everett Koop, said: “Drugs don’t work in patients who don’t take them.”
That seems like a tall order on the surface. How can life sciences organisations that don’t have direct contact with patients help improve compliance?
The answer is by using predictive data analytics to develop personas that help guide providers in understanding their patients better on a human level, and the barriers to compliance they face, so they can work together to develop strategies to overcome those barriers.
The Value of Personas
So, what is a persona? It’s essentially a representation of a group of people who share similar attributes and characteristics. Personas are used extensively in the consumer packaged goods industry to understand what triggers customers to buy more products, which helps them market those products more effectively.
The science behind personas is why the product mix in one store may be significantly different than the product mix in another store just a few miles down the road.
Life sciences organisations have traditionally only had access to claims data to track commercial effectiveness by comparing prescribing patterns to fulfilment. Although these analytics can show where problem are occurring, they don’t offer any insights into what is driving the disparity.
The next-generation analytics used for creating personas solve this issue by accessing a much wider selection of datasets, including de-identified clinical data from electronic medical records (EMRs), zip code, credit card, demographic, psychographic, lab, financial and patient satisfaction data. This wider array of data can be used to build detailed, sophisticated models that show the lifestyles, habits, and behaviors patients who fit a particular persona are likely to exhibit.
Armed with this information, commercial effectiveness teams can show providers not only how well their products work but the levers providers can pull to improve compliance – and ultimately outcomes. In a value-based, risk-based world, this is a huge advantage.
It not only gives commercial effectiveness teams a unique differentiator when competing with similar products. It also helps life sciences organizations gain a better of understanding of how much risk they can realistically assume when negotiating contracts.
Here is an example of how personas can help life sciences organisations demonstrate added value to providers around treatment of patients with type II diabetes.
The standard provider recommendation to help diabetic patients manage their condition is to eat healthier and get more exercise. It is solid, evidence-based advice. Yet many patients will fail to follow it to the frustration (and financial detriment) of their providers, who are uncertain of how to change those behaviors in order to avoid more expensive complications down the road.
A life sciences organisation that has used analytics to model personas for that provider’s patients can provide the answers. Perhaps a zip+4 analysis shows that there is a high density of fast food restaurants near the patient’s home, along with a lack of stores that sell organic foods. That can be a huge barrier to eating healthier; a strategy will need to be developed to introduce more healthy foods into the patient’s diet.
The zip code data may also show there aren’t any gyms or health clubs within a 2-mile radius of the neighborhood. As the patient lives in a cold weather climate, exercise in the winter may be a challenge. Again, a strategy will need to be developed to help this patient (and others in the area) increase their level of exercise.
Credit card data can also be helpful. If the purchase history indicates a sedentary lifestyle, additional motivation may be required to get that patient moving. By contrast, if the patient subscribes to outdoor magazines or has participated in 5K races, that information can inform the plan of care to ensure the proper exercise level.
Personas can also offer clues to compliance issues with medication. For instance, medications for chronic conditions such as diabetes are typically purchased in bulk through mail order pharmacies, as that is often the least expensive option. But if the patient lives in a high population density area, it could be a strong indicator of a small mailbox in an apartment building, which makes mail order pharmaceutical purchases impractical – especially if the patient will be challenged to pick up the order at the post office as well.
Understanding this, providers can work with the patient (and the health plan) to create a program that is workable, helping improve compliance – and ultimately outcomes.
The more precisely the personas are drawn, the better job commercial effectiveness teams can do in helping point out the root causes of non-compliance so they can be addressed. And the more valuable they will become to providers, which may even be enough to overcome minor pricing differences.
We are still early in the transition to value-based care, which has set everyone on edge. Especially life sciences organisations for whom risk-based contracts are uncharted territory.
Data-driven personas can help take the edge off by giving life sciences organizations a new, better understanding of patients to inform their own decisions even as they help providers, and ultimately patients. It’s a true case of everybody wins.
John Pagliuca is Vice President, Life Sciences at SCIO Health Analytics, where he leads the global commercialisation efforts of SCIO’s advanced analytics and SaaS solution suite within the Life Science market. He has more than 18 years of sales, marketing and technology experience in quantitative analytics and SaaS solutions for Life Sciences.