AI Tool Helps Clinicians Prescribe Right Dose of Warfarin to Heart Surgery Patients

The dosage determination depends on the International Normalized Ratio (INR) test, a blood test that gauges the blood's clotting time. Achieving the appropriate warfarin dosage is critical; too low a dose could lead to clot formation, whereas too high a dose increases the risk of internal bleeding or other serious complications. Frequent INR monitoring is essential post-initiation of warfarin therapy to assess the patient's drug response. The warfarin dose is then adjusted based on achieving a therapeutic INR range. This dosage adjustment process continues until the desired INR range is attained. However, finding the correct warfarin dose can be challenging due to the multitude of factors influencing its effectiveness, including genetic makeup, kidney and liver function, and the timing of drug initiation post-surgery. Until now, clinicians had to manually consider all these variables for determining the patient's dose. But now, a new artificial intelligence (AI) tool can automatically account for them and calculate a dose for use as a reference.

The AI tool developed by a group of researchers at St. Michael’s Hospital (Toronto, Canada) can help clinicians prescribe warfarin to heart surgery patients by guiding their use of the blood thinner medication. The tool was developed using data from more than 1,000 heart surgery patients who were administered warfarin that included variables such as patient characteristics, health conditions, individual warfarin doses, and response to the anticoagulant. The tool was then tested using a second set of data and validated for accuracy. The tool incorporates two validated AI models: one for predicting the warfarin dose in patients undergoing mechanical valve replacement, and another for dosing in all other heart surgery patients. This AI tool is currently in use at St. Michael’s Hospital, where it has received positive feedback from clinicians.

“People talk about the art of dosing, and some clinicians have a knack for it. But the nice thing about this tool is that it’s an extra layer of validation for patients for whom we’re struggling to get the right dose,” said Lindsay Dryden, St. Michael’s Hospital clinical pharmacist. “It’s something that clinicians can hang their hat on and that gives them a bit more confidence.”

“It’s a predictive tool that’s based off retrospective data – so if a patient comes in with similar characteristics and variables of past patients, we can predict how they might respond to a similar warfarin dose,” added Jacquelin Song, interim manager of Practice Innovation and Change. “This is an extra tool to help support clinical decision-making, almost like a second opinion.”

Related Links:
St. Michael’s Hospital