A new technology developed at Tel Aviv University will use artificial intelligence to identify patients at risk of serious illness due to blood infections. Researchers trained the AI program to study the electronic medical records of about 8,000 patients at Tel Aviv’s Ichilov Hospital who tested positive for bloodstream infections. The results of the study were published in the journal Scientific Reports.
According to Ramot, the university’s technology transfer company, the innovative technology will allow for early identification of at-risk patients and thus help hospitals reduce costs.
Students Yazeed Zoabi and Dan Lahav from Professor Noam Shomron’s lab at Tel Aviv University’s Sackler School of Medicine, in collaboration with Dr. Ahuva Weiss Meilik, head of the I-Medata AI Center at Ichilov Hospital, Professor Amos Adler and Dr. Orli Kehat conducted the study.
The importance of early diagnosis
Bloodstream infections are among the leading causes of morbidity and mortality in the world, so it is very important to identify the risk factors for developing a serious disease at the early stage of infection with bacteria or fungi. Most of the time, the bloodstream is sterile, but bacterial and fungal infection can occur during surgery or as a result of complications from other infections, such as pneumonia or meningitis. The body’s immunological response to the infection can lead to sepsis or shock, dangerous conditions with high mortality rates. Diagnosis of infection is made by taking a blood culture and transferring it to a growth medium for bacteria or fungi.
An 82% accuracy level
For the study, the researchers developed a trained AI program to study the electronic medical records of about 8,000 patients at Tel Aviv’s Ichilov Hospital with bloodstream infections. These records included demographic data, blood test results, medical history and diagnoses. Prof Noam Shomron explains:
“We worked with the medical records of about 8,000 patients at Ichilov Hospital who tested positive for bloodstream infections between the years 2014 and 2020, during their hospitalization and up to 30 days afterwards, regardless of whether the patient died or not. We entered the medical records into artificial intelligence-based software; 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.”
After studying each patient’s data and medical history, the AI achieved 82% accuracy in predicting disease progression, even ignoring obvious factors such as the patients’ age and the number of hospitalizations they have had. Once the researchers entered the patient’s data, the algorithm was able to predict the course of the disease, suggesting that in the future, this model could serve as an early warning system for doctors to classify patients according to their risk of developing severe disease. Prof Shomron relates:
“Using artificial intelligence, the algorithm was able to find patterns that surprised us, parameters in the blood that we hadn’t even thought to consider. We’re now working with medical staff to understand how this information can be used to classify patients according to the severity of the infection. We can use the software to help doctors detect the patients most at risk.”
Since the success of the study, Ramot, the technology transfer company at Tel Aviv University, has been working on filing a worldwide patent for this groundbreaking technology. Keren Primor Cohen, CEO of Ramot, states:
“Ramot believes in the ability of this innovative technology to make a significant change in the early identification of at-risk patients and help hospitals reduce their costs. This is an example of effective cooperation between university researchers and hospitals, which improves the quality of medical care in Israel and around the world.”
Translated from Sauver des vies grâce à l’Intelligence Artificielle
