Perspective:

When a patient with a device presents for evaluation, and the device manufacturer is unknown, there are three options: call all device manufacturers to check which one the patient is registered with, empirically try to establish communication between the device and all available programmers, or perform a chest x-ray and attempt to identify the device based on the published algorithm. This approach is both time consuming and inefficient, and may delay delivery of emergency care in some critically ill patients. The authors of this study employed machine learning (i.e., artificial intelligence) to develop a computer algorithm, which provides rapid x-ray image analysis, thus speeding up the diagnosis and treatment. The authors have made the tool publicly available online. This will enable users to upload additional images and facilitate continuous machine learning to identify new models of devices and their manufacturers. The study provides an example of how neural networks are increasingly being deployed to process large quantities of medical data, and how future patient care will likely rely increasingly on computer-aided decision making.