To treat certain cancers of the blood, doctors may pursue chimeric antigen receptor (CAR) T therapy. This powerful therapy can be highly effective for some patients, but it can also produce severe or life-threatening side effects. Heinz College team worked with the Icahn School of Medicine at Mount Sinai to develop a machine learning system that predicts whether a patient will develop the most common side effect of CAR T therapy. The project aimed to collecting and using multiple automated and manual, real-time and collected, sources of data that already exist.
The students’ machine learning system can predict the likelihood of not only cytokine release syndrome but also its onset within six- or eight-hour windows. The students selected the Random Forest model, which makes its predictions using multiple random “decision trees.” Using the students’ datasets, the model achieved roughly 93% accuracy in identifying patients who were likely to develop cytokine release syndrome within six hours.
【MORE】