A predictive analytics model pulls together clinical data including a patient's age, lab results and virus type to see whether a patient is at high-risk for developing complications from Hepatitis C.
This contagious disease that spreads through contact with infected blood inflames the liver and can either be acute or chronic, the latter of which leads to serious health problems. About 3.2 million people in the United States have chronic Hepatitis C virus infections, according to the Center for Disease Control.
These infections are expensive to treat — $1,000 a day for treatments to cure them — and often go undiagnosed because symptoms don't appear for a number of years after exposure. And it's also hard to identify which patients have higher risks of serious liver damage.
So researchers at the University of Michigan designed a model that creates a risk score for each patient and integrates with electronic health records, according to HealthITAnalytics. With the predictive analytics model, doctors can prioritize who to treat, how often to see them and what treatment options will work best. And that means they can focus their time and resources on patients who need it the most.