Sepsis affects more than 30 million people worldwide, causing an estimated six million deaths. It is an extreme response from the human body to an infection and is often life-threatening.
Every hour of delayed treatment can increase the odds of death by 4-8 per cent, so timely and accurate predictions of sepsis are crucial to reduce morbidity and mortality. Various healthcare organisations are already deploying predictive analytics to help identify patients with sepsis by using electronic medical record (EMR) data.
But the new AI, developed by a team of international researchers from McMaster University and St Joseph’s Healthcare Hamilton, both in Canada, could greatly improve the timeliness and accuracy of data-driven sepsis predictions.
“Sepsis can be predicted very accurately and very early using AI with clinical data, but the key questions to the clinician and data scientists are how much historical data these algorithms need to make accurate predictions...