A study by Rema Padman and Yiye Zhang of Carnegie Mellon University in Pennsylvania demonstrated the use of statistics and machine learning algorithms to predict the progression of chronic diseases and optimize treatment.

“We have data on thousands of patients being treated in multiple settings. Why can't we learn current practices from this vast repository of data and associate them with outcomes to learn what works and what doesn't,” says Padman.

Data analytics can shed light on chronic diseases. Credit: Carnegie Mellon UniversityThe goal of this study was to develop methods for treating people with multiple chronic conditions, which is a more usual occurrence then finding a patient presenting with only a single chronic disorder. Padman says that using this data to better understand patients’ conditions and the best method for treating them “requires a combination of analytical approaches – not just machine learning, but operations research, statistics and behavioral economics, as well.”

The researchers examined decision-making in the management of patients with chronic kidney disease. They were able to discern variations in healthcare costs among patients with similar conditions and were able to group patients based on their progress and to identify trends regarding recovery and treatment options.

Padman and Zhang say their goal is to use the information developed in this manner to create computer-based visualizations and automated tools. An automatic display of treatment recommendations and associated risk assessments could become available to physicians as part of their now normal procedure of entering data and checking histories electronically.