Researchers have developed a machine learning method that processes massive amounts of data to help determine which existing drugs could improve outcomes in diseases for which they are not prescribed.
Cheaper new uses
Drug reuse is an interesting activity because it could reduce the risk associated with safety testing of new drugs and dramatically reduce the time it takes to bring a drug to market for clinical use.
But coming up with those new uses usually involves a combination of serendipity and expensive and time-consuming randomized clinical trials.
To combat this problem, Ohio State University researchers created a model that combines huge data sets related to patient care with high-powered computing to arrive at repurposed drug candidates and the estimated effects of those existing drugs in one set. defined results.
The research team used insurance claims data on nearly 1.2 million heart disease patients, which provided information on assigned treatment, disease outcomes, and other values.
The deep learning algorithm can also take into account the passage of time in each patient’s experience, for each visit, prescription and diagnostic test. The model input for drugs is based on their active ingredients .
Although this study focused on the proposed reuse of drugs to prevent heart failure and stroke in patients with coronary artery disease, the model is flexible and could be applied to most diseases .