Artificial intelligence (AI) – the simulation of human intelligence processes by machines, especially computer systems that can be applied for many uses – has been used at Tel Aviv University (TAU) to identify patients at risk of serious illness as a result of blood infections. 

The researchers trained the AI program to study the electronic medical records of some 8,000 patients at Tel Aviv Sourasky Medical Center who were found to be positive for blood infections. These records included demographic data, blood test results, medical history and diagnoses. After studying each patient’s data and medical history, the program was able to identify automatically the medical files’ risk factors with an impressive accuracy of 82%. According to the researchers, in the future this model could even serve as an early warning system for doctors by enabling them to rank patients based on their risk of serious disease.

Behind this groundbreaking research with the potential to save many lives are students Yazeed Zoabi and Dan Lahav from the laboratory of Prof. Noam Shomron of TAU’s Sackler Faculty of Medicine, in collaboration with Dr. Ahuva Weiss Meilik, head of the I-Medata AI Center at Sourasky, Prof. Amos Adler, and Dr. Orli Kehat. The results of the study were published in the journal Scientific Reports under the title “Predicting bloodstream infection outcome using machine learning.” 

The researchers explained that since blood infections are one of the leading causes of disease and death in the world, it is very important to identify the risk factors for developing serious illness at the early stage of infection with a bacterium or fungus. Most of the time, the blood system is a sterile one, but infection with a bacterium or fungus can occur during surgery, or as the result of complications from other infections, such as pneumonia or meningitis. 

Bloodstream infections can lead to prolonged hospital stays and life-threatening and aggressive complications, they wrote, in addition to high costs to health care systems. Increasing rates of antimicrobial-resistant pathogens, particularly gram-negative bacteria, limit treatment options; this often prompts empirical use of broad-range antibiotics. Therefore, timely and critical assessment of available microbiology results are necessary to ensure that individuals with bloodstream infections receive prompt, effective and targeted treatment for optimal clinical outcomes. However, the current standard-of-care, which mostly depends on blood culture-based diagnosis, is often extremely slow. 

The diagnosis of infection is made by taking a blood culture and transferring it to a growth medium for bacteria and fungi. The body’s immunological response to the infection can cause sepsis (the body’s extreme response to an infection – a life-threatening medical emergency when an infection you already have triggers a chain reaction throughout your body) or shock (a critical condition brought on by the sudden drop in blood flow through the body that can result from trauma, heatstroke, blood loss, an allergic reaction, severe infection, poisoning, severe burns or other causes).

“We worked with the medical files of about 8,000 of the hospital’s patients who were found to be positive for blood infections between 2014 and 2020, during their hospitalization and up to 30 days after, whether the patient died or not,” recalled Shomron. “We entered the medical files into software based on artificial intelligence; 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.”

The researchers were happy to see that following their training, the AI reached an accuracy level of 82% in predicting the course of the disease, even when ignoring obvious factors such as the age of the patients and the number of hospitalizations they had endured. After they entered each patient’s data, the algorithm knew how to predict the course of the disease, which suggests that in the future it will be possible to rank patients in terms of the danger posed to their health – ahead of time.

“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 Shomron. “We are now working with medical staff to understand how this information can be used to rank patients in terms of the severity of the infection. We can use the software to help doctors detect the patients who are at maximum risk.”

Since the study’s success, Ramot – TAU’s technology transfer company – is working to register a global patent for the groundbreaking technology. Ramot CEO Keren Primor Cohen said that her institution “believes in this innovative technology’s ability to bring about a significant change in the early identification of patients at risk and help hospitals reduce costs. This is an example of effective cooperation between the university’s researchers and hospitals, which improves the quality of medical care in Israel and around the world.”