In their most simple form, AI applications in healthcare consist of a collection of technologies that will enable machines to sense, comprehend, predict, act, and learn. The first application for AI-based machines, as discussed at the World Medical Innovation Forum (held in April 2018), is to execute healthcare administrator and clinical healthcare functions. Current technologies are limited because they are algorithm based. The future of AI will make the leap past algorithm-only tools to become indispensable instruments for patients, providers, physicians, and payers. AI has the potential to truly augment human activity.
Why This Is Important
The potential to drive improvements in quality, cost, and access has made AI a notable buzzword in healthcare. The AI health market is growing rapidly and is forecasted to reach $6.6 billion by 20211
AI Applications in Orthopedics
AI has demonstrated high utility in classifying non-medical images. A study2 looked at the feasibility of using AI for skeletal radiographs. The study authors compared an AI program against the radiography gold standard for fractures. They also compared the performance of the AI program with two orthopedic surgeons who reviewed the same images. They found the AI program had an accuracy of at least 90 percent when identifying laterality, body part, and exam view. AI also performed comparably to the senior orthopedic surgeons’ image reviews. The study outcomes support the use of AI in orthopedic radiographs. While the current AI technology does not provide important features surgeons need, such as advanced measurements, classifications, and the ability to combine multiple exam views, these are technical details that can be worked out in future iterations for the orthopedic surgeon community.
AI in Computer-Assisted Navigation3
Orthopedic surgeons have had access to robotic technology to help them position screws, prostheses, or tunnels for some time, but AI enhanced applications are in development (Table 2). For example, one device utilizes infrared light to locate bones intraoperatively. Another technology uses a form of AI to mill the canal for a prosthesis based on CT scans. In total hip surgery, computer assistance in placing the cup of the prosthesis is reported to have the same accuracy as with traditional methods. In the realm of knee replacement surgery, AI-supplemented robotics technology assists to align prostheses. In spine surgery, AI-enhanced computer-assisted navigation helps surgeons avoid neurovascular structures, and place thoracic and lumbar pedicle screws accurately. It is reported that the incidence of poorly placed screws has reached 42 percent with conventional surgical techniques, according to some studies, but is as low as 10 percent with AI-based computer assistance.
By Maria Shepherd | Orthopedic Design & Technology
Image Credit: Maria Shepherd / Orthopedic Design & Technology