Product Creation Studio is pleased to bring you exclusive, on-going content by Heather Thompson, a senior editor for Medical Design & Outsourcing and former editor-in-chief of MD+DI magazine.  With 15 years of experience covering medical technologies and FDA regulations, Heather specializes in delivering the latest trends and news in the medical device industry. 

Deep learning algorithms (aka artificial learning or AI) have the power to transform healthcare in various ways. Adoption of AI into healthcare is no longer a “what if” question. It is no longer a “when” question. At this point, we are only asking “how,” as in “how can we use it to get the best out of the technology.”

Artificial Intelligence in healthcare will be able to solve a variety of problems for patients, hospitals, and the healthcare industry overall. Here are some ways we believe AI is already improving healthcare and how it might in the near future.

Deep learning diagnostics

One of the most anticipated advances for deep learning is in the diagnostics space. Juggernauts like IBM Watson have all but promised the most advanced methods of patient diagnosis. If you’ve ever imagined a hand-held device that would scan a patient and automatically diagnose any injury or illness, that’s AI. And it already exists.

The Qualcomm X-prize recipient was chosen this year. You might remember that Qualcomm held a competition for inventors to create a tricorder inspired by the diagnostic machine seen in the Star Trek franchise. The winner of the X-prize created DxtER (pronounced “Dexter”), an artificial intelligence-based engine that learns to diagnose medical conditions by integrating learnings from clinical emergency medicine with data analysis from actual patients. DxtER includes a group of non-invasive sensors that are designed to collect data about vital signs, body chemistry and biological functions. This information is then synthesized in the device’s diagnostic engine to make a quick and accurate assessment.

Consumer-facing diagnostics are also possible, such as that provided by Buoy Health. Buoy Health is a digital technology that aims to be a single-source of personalized and more accurate analysis of symptoms. Buoy's algorithm analyzes thousands of real world data points drawn from the same medical literature physicians study, in order to resemble the dynamic and nuanced experience of chatting with a doctor.

Smarter surgical robots

Surgical robotics companies are already applying AI to predict surgeon behaviors.

Such software upgrades improve how the robots adapt and respond to the surgeon at the controls. Sensors that provide force feedback and haptics are being included in the latest generation of surgical robots. The next step is to include predictive models into the robots.

It is important to understand that the electronics of a robot arm are usually located somewhere up the armature, behind the sterile drape. The distance between the electronics and the sensors at the distil end creates some lag time and stiffness in movement. Predictive technologies can counter those limitations without requiring complex electronics to move into the sterile field. This greater level of accuracy and control minimizes trauma and damage to the patient. 

Helping overworked physicians

Predictive modeling can provide detailed and patient-specific information used in deciding a course of action to take and in discussing risks to patients. Machine learning is a natural fit for this type of decision-making.

Predictive modeling has already been used in spine surgeries. For example, the Medicrea Group received 510(k) clearance from the U.S. Food & Drug Administration in June for its UNiD HUB product, a data-driven digital portal for the company’s Adaptive Spine Intelligence technology. The UNiD HUB supports the surgeon workflow, identifies tendencies and correlations, and builds predictive modeling to develop surgical strategies and create personalized implants.

AI technology will also make CT scanned images more valuable and less burdensome to technicians and physicians. Companies like Arterys are applying deep learning to cut down on the hours technicians might spend finding, tracking, contouring, and measuring objects in a scanned image. These tedious processes distract the physician from their patients and do not make good use of clinical skills.

In addition, new products are being designed to make surgeons’ workflow more smooth and intuitive. ExplORer Surgical, for example, organizes all surgical cards, safety checks, surgical inventory, and instruction manuals into a single digitized platform that can be brought into the sterile field. It allows busy operating rooms to have a single resource that can eliminate wasted intraoperative time delays.

Wellness maintenance and patient compliance

This one is easily the most visible and pervasive technology that will be seen. Its already here.

Fitness trackers and apps are already popular and used outside the healthcare field. Adopting these consumer tools will mean harnessing them to capture clinically-meaningful data as well as tapping into their psychological power to motivate people to stay healthy or improve health.

More specialized wearable technologies are making their way into various arenas. The motusBASEBALL product is used to predict injury based on a baseball player’s technique. It tracks arm injuries caused by over-usage by measuring every throw, calculating arm stress and throwing workload.

A focus on value and outcome continues to dominate how hospitals and insurance providers evaluate medical technology. Products that go beyond basic functionality and demonstrate those essential contributions to value will see greater success on the market. But more than that, products that successfully incorporate AI into their technology are going to be an intrinsic part of the shift in healthcare. 

Product Creation Studio is excited to be involved as the Platinum Sponsor of Xconomy’s AI + Healthcare Northwest event coming up in Seattle on November 9. Please join us as we hear from industry leaders on this hot topic!