Antibiotics Resistance: Scientists Develop Algorithm-Based Technique To Personalize Antibiotic Treatments

Scientists have developed a new technique to personalize, or custom-tailor, antibiotics according to the individual needs of the patients. It will reduce the problems associated with a treatment compromised from an ineffective strain, and developing antibiotic-resistant strains of bacteria.

The new technology was developed by Varda Shalev, who is the head of the Kahn-Sagol-Maccabi Research and Innovation Institute, in collaboration with researchers Roy Kishony and Idan Yelin at the Technion - Israel Institute of Technology.

One of the biggest challenges faced by the modern medicine is coping with the antibiotics resistant bacteria. The World Health Organization (WHO) has described it as a major threat to global health. It can affect people belonging to any gender, age group and region.

The International health body also stated that antibiotic resistance can lead to increased mortality, higher medical costs and longer hospital stays.

It is estimated that annually more than two million people in the United States develop an antibiotic resistant infection, according to the Centers for Disease Control and Prevention. The agency also reported that nearly 23,000 individuals die due to this type of infection.

There are several reasons for bacteria to develop antibiotics resistance. One of them is overuse of antibiotics, which can eventually lead to loss of their effectiveness. It is also worth noting that some resistant bacteria develop because of the infections caused by the overuse of antibiotics. This type of bacteria is likely to become “treatment-resistant and deadly,” the researchers said.

The development of resistant bacteria can be prevented through the reduced repetitive use of antibiotics in medical treatments. Depending on patients’ needs scientists could be able to develop specific antibiotics with the help of artificial intelligence and patient data.

“It is now possible to computationally predict the level of bacterial resistance for infection-causing bacteria. This is done by weighing of demographic data, including age, gender, pregnancy … together with levels of resistance [which are] measured in the patient’s previous urine cultures as well as their drug purchase history,” Israel Hayom quoted Yelin.

For the research, the scientists analyzed over 700,000 urine cultures. Then they focussed on urine tract infections that involve various types of bacteria, including E. coli, Klebsiella pneumonia and Proteus mirabilis.

The researchers then developed an algorithm, which was based on antibiotic purchases made in the past 10 years for over five million cases. The algorithm provided treatment recommendations based on the infection’s antibiotics resistance.

The study titled "Personal clinical history predicts antibiotic resistance of urinary tract infections" was published in the journal Nature Medicine last week.