AdobeStock_174784528

Emerging AI Applications in Medical Devices

In April, the U.S. FDA issued its first marketing permit for a medical device using artificial intelligence to detect greater than mild diabetic retinopathy. While it was the first such AI approval, it promises to be just the beginning of AI medical devices.

Technology is driving immense changes in healthcare delivery from 3D printing to robotic service delivery. Among the hottest topics in healthcare technology is artificial intelligence judging from the presentations at recent meetings of radiologists and health IT executive.

The FDA approved device called IDx-DR is a software program that uses AI to analyze images of the eye taken with a retinal camera. The doctor uploads the digital images of the patient’s retinas to a cloud server. The software analyzes the images and tells the doctor either there is more than mild diabetic retinopathy detected, or they are negative for more than mild diabetic retinopathy.

IDx-DR is the first FDA authorized device that provides a screening decision without the need for a clinician to also interpret the image, which makes it possible for health care providers not normally involved in eye care to make treatment decisions.

Other emerging AI technologies are focusing on chronic disease management, medical imaging and treatment compliance according to a report in techemergence, an online trade publication.

An example of chronic disease management is Medtronic’s efforts to use AI to help diabetic patients manage their conditions through a mobile app called Sugar.IQ that it is developing in cooperation with IBM’s Watson Health. The app features the ability to monitor glucose patterns and deliver personalized messages to the patient regarding specific actions or habits that are affecting their glucose levels.

Patients can tailor the app to help them quickly and easily track their specific food or therapy-related actions that they take and learn how those impact their personal glucose levels. Based on the technology the company has already launched an advanced model insulin pump that automates delivery of insulin every 5 minutes to stabilize blood glucose 24-hours a day.

In medical imaging GE Healthcare and NVIDIA have teamed up to integrate NVIDIA’s AI platform with GE’s imaging devices. The collaborators cite successes in using AI to improve the speed and accuracy of CT scans. The increased speed results in lower radiation exposures for patients.

With a predicted $25 billion slice of the healthcare market by 2019, a number of companies are looking at pairing wearable healthcare devices with AI to improve patient monitoring and treatment compliance.

Philips Healthcare’s IntelliVue Guardian Solution is one such device that uses AI to predict life-threatening events in a patient to allow earlier intervention. The device combines software, clinical decision support algorithms and mobile connectivity to watch for significant changes in vital signs. Based on algorithms trained on large datasets patient data can be transmitted to IntelliVue monitors or mobile devices to notify the patient’s providers.

In a clinical study of the system, involving 178 patients, nearly 70 percent of their clinicians who used the system felt confident they could easily identify patients who needed immediate medical assistance.

Other lesser-known examples highlighted a report in Asian Healthcare & Hospital Management, include ATL Ultrasound, Inc. a Seattle-based firm that has developed a range of diagnostic ultrasound systems for imaging and monitoring cardiac tissue structures and activity.

The system uses an adaptive intelligence algorithm to optimize examination of tissues against millions of parameters during a patient examination, thereby eliminating irrelevant frequencies in returned signals.

Neuromedical Systems, Inc. of New Jersey uses an application of neural networks to scan Pap smears to identify cells for review during cancer screening, and Agilent Technologies (Andover, Massachusetts) has developed a smart ECG device that estimates the probability of acute cardiac ischemia (ACI). This ACI time-insensitive predictive instrument aims to increase the accuracy of diagnosing ACI.

While the examples cited here are few, it appears that the AI applications for medical device development are poised for rapid emergence from academia to development and commercialization.

Kapstone Medical is a full-service product realization firm that partners with inventors and manufacturers of all sizes to help them rapidly develop and commercialize new medical devices or processes, including AI applications for medical devices. Visit our website or Call Us Today to learn more! Phone: (704) 843-7852 – email: info@kapstonemedical.com

Contact Us Today!

Sources: FDA press release, techemergence.com, and Asian Healthcare & Hospital Management