Predictive Modeling in Healthcare

The opportunity that dig data provides now allows organizations to infer a lot more about someone’s future by analyzing the past of that same person’s cohort. So, while good clean data is an important step, we must remember that dig data has changed the game when it comes to analytics and particularly predictive analytics. A lot more can be analyzed and correlated, sometimes making the idea of ‘sample analysis’ a thing of the past.

What if there was a way to use data to reduce the high cost of readmissions for patients with various levels of acute or non-acute pneumonia symptoms?

This new development has had an impact on many industries but one that affects all of us is healthcare. Hospitals collect tons of data on their patients from various sensors and clinician notes. What if there was a way to use this data to reduce the high cost of readmissions for patients with various levels of acute or non-acute pneumonia symptoms? The main crutch of this problem lies in our ability to identify patients at risk of readmitting before they leave the hospital.

Simple put, using historic admittance records and treatment paths, correlated to length of stay, we can build a model which allows us to ascertain the risks around patient discharge.One study found that, within 30 days after hospital discharge, nearly 13% of medical patients were readmitted to hospital. Using sophisticated algorithms to build a predictive model, they identified a high-risk group of medical patients who had twice the occurrence of readmission and more resource-intensive hospital stays than other patients.

READ  Hacked – Why Your WordPress Sites are Vulnerable

The high-risk group accounted for over half of all readmissions. These findings suggest that the predictive model was a useful tool to aid in the identification of appropriate candidates for post-discharge interventions. However, the fact that only half of all readmitted patients were identified a priori as being at high risk for readmission suggests that additional research may have been helpful in optimizing strategies to identify patients for resource intensive post-discharge intervention.

Big data and predictive analytics plays an important role in helping to reengineer patient discharge and readmission rates which in-turn have the potential of reducing healthcare costs for all of us.

Leave a Reply

Your email address will not be published. Required fields are marked *