By pinning down higher-risk situations, doctors can change their treatment programs after surgery, which could mean more frequent appointments, or changing their medication.
Kidney transplants can significantly prolong the life expectancy of patients, but over time, some recipients may experience complications, putting them back on dialysis when their kidneys begin to fail.
In an effort to predict when that would happen, Halifax kidney specialist Dr. Karthik Tennankore partnered with a team of computer scientists specializing in artificial intelligence. According to Tennankore, using AI for this task would enable doctors to estimate how long a kidney transplant would last, and potentially help patients receive better care after surgery.
“If we can find these groups that are more vulnerable or higher risk, we can better their care,” said Tennankore, who recently used machine learning to analyze a database of 50,000 kidney transplants in the US. He now plans to apply the same technique to analyze kidney transplants in Nova Scotia.
As part of the analysis, the nephrologist compared the characteristics of donors with those of recipients to identify connections and make predictions on how long a new organ will last. Such factors include weight, age, and other health conditions that may determine the success of the transplant.
“There may be 30, 40, maybe even as high as 50 variables that we combine together and use this machine learning approach to see how they connect all together,” he said. Once the data analysis is finished, the machine then categorizes the potential life of the transplant in years.
The idea is that by pinning down higher-risk situations, doctors can change their treatment programs after surgery, which could mean more frequent appointments, or changing their medication. So far, the novel technique has proved to be 80 percent accurate.
To ensure the process is used in an ethical manner, Tennankore’s team plans to consult with the patient network through the Canadian Donation and Transplantation Research Program. This would prevent the work from being used in determining who gets a transplant and who doesn’t.
“We don’t want to deny that patient the opportunity or the chance to get that kidney,” he said. “So they get the transplant, but we know that things may not go well in the future, so it’s important to us to monitor that patient a bit more closely.”