Stanford Uses AI to Identify Safety of Implantable Medical Devices

Researchers at Stanford Medicine developed an algorithm to determined the safety of various, implanted medical devices like hip replacements and pacemakers. The new system uses artificial intelligence (AI) to go through electronic health records (EHR) data of these devices.

Stanford’s new AI monitoring algorithm can access former patients’ medical records, linking them to medical information like infection rates, pain level of patients, specific device, and how long implants last before it is replaced. In testing the algorithm, researchers looked at the EHR data of former hip replacement patients and identified any instances of complications with each patient's implant. Pain was a key determinant in these complications and flag some of the safe devices, according to a recent blog post by the medical school on the research.

Become a Subscriber

Please purchase a subscription to continue reading this article.

Subscribe Now

“Previous studies have likewise shown that pain is a useful predictor for more serious complications later on, said Nigam Shah, PhD, associate professor medicine and biomedical data science, Stanford, in the post. “By tracking patient pain levels over time, the model helped reveal a patients’ quality of life with that specific implant…the algorithm also provided a broader picture of complications and pain levels associated with each device.

She added that the safety standards required by the FDA are for initial approval of the device’s use since these medical instruments must meet specific safety standards before hitting the market. Yet, how effectively these devices perform after years of use in the body is the real challenge.

Although there are currently methods of reporting medical device safety to the Food and Drug Administration (FDA), these processes may often be drawn out, include some bias in data analysis and are oftentimes never reported. There enormous amount of patient data stretched across various databases also makes it challenging to detect a device’s safety.

One way the algorithm may tap into the long-term side of the research is by compiling more data on individuals with hip implants at a younger age, who will ultimately have them for a longer period of time. This could help break down the data to determine which devices are better suited for people of varying age groups, and more.