by SingHealth
Credit: Unsplash/CC0 Public Domain
Doctors may soon use an AI-driven solution to swiftly prescribe a personalized antibiotic regimen for patients with just a few mouse clicks instead of giving general treatment. The antibiotic regimen can then be adjusted, if necessary, when bacterial culture and other investigation test results become available.
Known as the Augmented Intelligence in Infectious Diseases (AI2D), the solution is developed by Singapore General Hospital (SGH) in collaboration with DXC Technology and Synapxe. It targets two common infections treated in hospitals—pneumonia and urinary tract infection.
The team, led by SGH’s Division of Pharmacy, has developed the model for pneumonia which showed 90% accuracy in a pilot validation study to first determine if antibiotics were necessary. They are now looking to measure its effectiveness in safely reducing antibiotic use in a comparative study involving 200 inpatients. These patients will be randomly assigned to have either doctors or doctors with AI2D determine whether antibiotics should be given.
“Well-intended doctors are constantly balancing the risks and benefits of antibiotic use. It is often hard to tell definitively that patients will benefit from it based on clinical assessment, patient-specific factors, or condition severity alone,” said Dr. Piotr Chlebicki, Senior Consultant, Department of Infectious Diseases, SGH and project member.
“If not prescribed promptly for those who genuinely need them, it may lead to dire complications. Yet, misusing antibiotics contributes to antibiotic resistance, posing challenges for future infection treatment. So, a tool like AI2D will be very helpful to guide a doctor’s decision before lab results are available.”
The pneumonia model was built using retrospective deidentified clinical data like X-rays, clinical symptoms, periodic vital signs, and trends of common body responses to infection, of about 8,000 SGH patients between 2019 and 2020. It was then validated against another 2,000 cases in 2023 using a design that would simulate real-life usage when deployed.
Besides showing a high level of accuracy, the pilot validation study also revealed that almost 40% of antibiotics prescribed in those cases to treat pneumonia at the onset may not have been necessary. This situation is not unique to Singapore.
The Centers for Disease Control and Prevention (CDC) in the U.S. estimates that up to 50% of all antibiotics prescribed in the U.S. are unnecessary or inappropriate, with many of them prescribed in inpatient settings.
The team will then work on determining which type of antibiotic is most effective against pneumonia and the urinary tract infection model after the comparative study.
“AI2D can help inform doctors if antibiotics are needed, and if so, to recommend what is needed and the dosing regimen based on the patient’s relevant clinical data. This may potentially cut antibiotic use, which in turn lowers the risk of antibiotic resistance, keeping antibiotics effective for treating infections now and in the future with the help of AI,” said Associate Professor Andrea Kwa, Deputy Director, Pharmacy (Research and Innovation), SGH, and project lead.
Explore further
Shortened antibiotic treatment for ventilator-associated pneumonia in ICU patients just as effective as standard course
Leave a Reply