MIT CASE STUDY
Sepsis strikes one million patients in the United States every year. Up to 50-percent of those afflicted die—far more than from prostate cancer, breast cancer and AIDS combined—and it costs $20 billion every year in treatment and preventative care.
The good news: Physiologic data, specifically arterial blood pressure and heart rates, can be used to predict the onset of sepsis. The bad news: The sheer size of that data makes it too expensive and complex for healthcare providers to continuously monitor and analyze.
The big question
Can distributed artificial intelligence accurately predict the onset of sepsis?
Yes, and here’s how we proved it.
Over a one-year period, Sentient Labs worked with MIT’s Computer Science and Artificial Intelligence Laboratory team (CSAIL) to apply evolutionary algorithms on a massive scale to evolve classification rule-sets with high accuracy and acceptable false-positives over unseen data.
Applying these rule-sets to more than 6,000 patient records (representing 4TB of data), St. Michael’s Hospital at the University of Toronto was able to predict thirty minutes ahead of time, with greater than 90 percent accuracy, whether a patient would get sepsis. This provided caregivers valuable time to proactively treat the infection and save patients’ lives.
UNA-MAY O-REILLY, PRINCIPAL RESEARCH SCIENTIST, MIT CSAI