By Jeffrey Hoffmeister
Artificial intelligence (AI) has become the latest technology to upend the status quo. However, unlike other industries, healthcare’s adoption and implementation of AI is still in its infancy, in part, due to many providers still updating their systems and processes for the new technology. Nonetheless, the momentum is building and AI and the Internet of Medical Things (IoMT) is poised to revolutionize the healthcare industry.
A recent analysis from Accenture shows growth in the AI health market is expected to reach $6.6 billion by 2021 and key clinical health AI applications can potentially create $150 billion in annual savings for the US healthcare economy by 2026. Additionally, Harvard Business Review found the application of AI to administrative processes could add a potential annual value of $18 billion by 2026.
Based on what we know so far, it’s clear AI can provide the healthcare industry with a unique opportunity to not only offer tools and insights that can vastly improve patient care, but that also improve their bottom line. AI has the power to see patterns in research studies, detect ailments faster and provide more in-depth education.
However, despite all the benefits and advantages of AI, some providers remain skeptical and hesitant to implement solutions, and are concerned about the challenges of AI in the healthcare industry.
First rule of AI in medicine: Do no harm
Since AI relies mainly on data collection, if the data isn’t accurate, the AI solution is blamed. In healthcare, AI solutions that rely on deep learning capabilities can lead to incorrect patterns being identified and thus incorrect diagnoses – such as false positive results. Despite these trepidations, providers who are pro-AI argue that this technology is actually much faster and more accurate than humans and only provides us with even more opportunities to succeed and streamline tasks.
Other AI fears relate to job loss – much like the argument made across all industries against AI. Automation of processes will certainly make some roles obsolete, but for many positions within healthcare and caregiving, machines and computers will be responsible for one role, not the many hats worn by healthcare providers. Take radiologists for example. Deep learning solutions can help them identify areas of interest within a scan, but that’s not all radiologists do. AI solutions are simply a supplement to their duties and can allow them to spend more time focused on patients and providing value-based care.
AI equals real results
Depending on the industry, AI delivers different types of results. In the healthcare industry, AI solutions can assist in improving health outcomes, especially when it comes to breast imaging.
According to Breastcancer.org, nearly one in eight U.S. women will develop invasive breast cancer during her lifetime. However, two-thirds have the potential to be saved through early detection and progressive treatments. In response, many medical facilities worldwide are turning to Digital Breast Tomosynthesis (DBT) technology solutions as their preferred method for screening and diagnostic mammography in order to do just that – detect and diagnose women with early-stage breast cancer.
But just like all technology, there are also some challenges radiologists face when utilizing DBT. For example, detection of breast cancer using DBT involves interpretation of massive data sets, which can be extremely time consuming for radiologists. A 3D mammogram, or DBT, produces hundreds of images, while 2D digital mammography exams produce only four images. While DBT ultimately provides greater clarity and detail, it also requires radiologists to spend significantly more time reviewing and interpreting breast exams.
However, this is where technology comes into play. Radiologists can leverage innovative AI and deep learning solutions to help reduce their DBT interpretation time and improve reading workflow. This is due to the capabilities of particular AI solutions, as some tools can automatically highlight areas for radiologists that might appear concerning, calling attention to spots that might need to be reviewed more cautiously. These capabilities are especially imperative for radiologists today, as many report feeling burnout.
Although more research needs to be done on AI, in the medical imaging industry its clear these solutions are fundamentally changing the way radiologists and other healthcare providers do their jobs. In order for providers to overcome their concerns associated with AI, they must first carefully research and consider the right AI solution for their individual needs. As the healthcare industry as a whole continues to transform, it’s easy to believe that providers who utilize and understand the unique capabilities of AI solutions will perform above the rest.
About Jeffrey Hoffmeister: As VP, medical director at iCAD, Jeffrey has participated in developing mammographic AI solutions for 25 years. He has provided clinical insight to engineering and marketing teams and managed the design and implementation of clinical studies for FDA approval of mammographic AI products, from iCAD’s first mammography CAD product, SecondLook, in 2002 to iCAD’s most recent digital breast tomosynthesis AI solution, PowerLook Tomo Detection. iCAD, a global leader in medical technology providing innovative cancer detection and therapy solutions, is the manufacturer of the first and only FDA-approved concurrent-read cancer detection solution for breast tomosynthesis, iCAD’s PowerLook Tomo Detection. Utilizing a trained algorithm developed through deep learning, the system automatically analyzes each tomosynthesis plane and identifies suspicious areas. These images are then blended into a 2D synthetic image, providing radiologists with a single, highly sensitive, enhanced image from which they can easily navigate the tomosynthesis data sets.