The tool serves as an early warning tool to doctors and patients.

A team of researchers from the laboratory of Prof. Noam Shomron from Tel Aviv University’s Sackler Faculty of Medicine, in collaboration with other researchers, including Dr. Ahuva Weiss Meilik, head of the I-Medata AI Center at Ichilov Hospital, have developed an AI tool that identifies patients who could fall seriously ill due to blood infection. Blood infections are a significant cause of deaths across the globe. (NoCamels)

According to the research team, “bloodstream infections (BSI) can lead to prolonged hospital stays, and life-threatening and aggressive complications, in addition to high costs to the health care system.”

AI tool for warnings on blood infection (BSI)

The research team trained the AI by inputting the medical files of about 8,000 Ichilov patients who were found to be positive for blood infections between the years 2014 and 2020, during their hospitalization and up to 30 days after, whether the patient died or not.

“We wanted to see if the AI would identify patterns of information in the files that would allow us to automatically predict which patients would develop serious illness, or even death, as a result of the infection,” said Prof. Noam Shomron of Tel Aviv University.

“Using artificial intelligence, the algorithm was able to find patterns that surprised us, parameters in the blood that we hadn’t even thought about taking into account,” said Prof. Shomron. “Albumin and creatine [levels] in the blood are strong markers of potential mortality due to infection.”

“Also monocytes, platelets volume. In fact, a few of these were indicators of infection severity, but the quantitation and the combination of them all in one algorithm were not performed,” he added.

The AI is now able to identify risk factors based on a patient’s information including demographic data, blood test results, medical history, and diagnosis.

The output of the algorithm would be a risk factor, which when evaluated together with the physician’s advice, could flag the actions to be taken to save the patient.

The AI program achieved an accuracy level of 82% in predicting the course of the disease in the patient.

“We can use the software to help doctors detect the patients who are at maximum risk,” said Prof Shomron, because the program’s results can be used to rank patients in terms of the severity of the infection.

Related Story: MIT Researcher Develops Mirai – An AI To Accurately Predict Breast Cancer