Docs predict medication adherence with patient scores

Predicting which patients need the biggest nudge to taking their prescriptions just got a little easier, thanks to the new Medication Adherence Score being introduced by none other than credit-score generator FICO.

A patient's FICO medication score, a number between 0 and 500, is calculated based on publicly available data, such as home ownership and job status. An overall score of 400 or higher indicates strong medication adherence, while patients who score 200 or lower may need reminder calls or emails to fill their prescriptions and take them correctly. The company expects doctors and health insurers to have purchased scores for two million to three million patients by the end of the year, ultimately leading to a total of 10 million scores generated during the next 12 months.

"We started thinking about how do consumers behave as patients," Mark Greene, the chief executive of FICO, based in Minneapolis, told the New York Times. "The problem, from a math standpoint, is not all that different from banking and other industries."

FICO developed its medication scoring system using data from a random sample of nearly 600,000 anonymous patients with diabetes, heart disease, and asthma that it obtained from a large pharmacy benefits manager. It then determined which demographic traits correlated with certain patterns of behavior.

In particular, the analysis found that people in the following circumstances tend to struggle with medication adherence:

  • New to a job or home ownership
  • Unmarried or living alone
  • Without a car
  • In college or older than 80
  • Female

Risks are also weighed differently depending on the patient's diagnosis, the New York Times reports.

Although the tool holds promise to help physicians better target their resources in reaching out to at-risk patients, individuals who commented on the Consumerist blog voiced concern that the information would be used by insurance companies to raise rates or limit coverage. Because the score is generated using publicly available information, it can be obtained without the patient's knowledge or permission.

To learn more:
- read the post in the New York Times' Well blog
- see this post from the Consumerist