For years, I heard about Artificial Intelligence and Machine Learning (AI/ML) and how they would impact the medical device sector. I understood software, but I’m not a software engineer by training. The closest I got to programing was using CTRL+C and CTRL+V.
I did not want that to stop me from gaining more understanding and insights into this new innovative world. So, I enrolled in a weeklong workshop here in the Silicon Valley area of California. I did not enter the training session as an expert, just the opposite. It was a personal and professional growth experience for me. I felt out of place and intimidated by those cool computer programmers and scientists—my new best friends.
Then, on November 5, 2019, I wrote my first article on AI/MI on LinkedIn: “Hey Artificial Intelligence, Let’s Be Foolish Friends.” That began an adventure for me. I had to hold on tight because this field was moving fast. Here is a critical point, the bottom line, I learned years ago, which has proven true today.
Artificial Intelligence + Human Input Beats Artificial Intelligence or Human Input Alone Every Time.
Artificial intelligence is a technology that mimics human activity, decision-making, and learning.
In the medical device and healthcare industry, artificial intelligence can (i) automate tasks, synthesize data from multiple sources, and pinpoint trends, (ii) predict which patients are at an increased risk for disease, complications, or adverse outcomes based on patient-specific data, and (iii) process and analyze information from wearable sensors and identify disease or the onset of medical conditions, and (iv) support research by evaluating large amounts of data and monitoring treatment effectiveness.
The truth is artificial intelligence has the potential to significantly improve the medical field and medical devices in multiple ways. Medical devices that harness the power of artificial intelligence have the potential to revolutionize the entire health care industry and help medical professionals effectively and accurately diagnose and treat patients while improving care.
Related: Top 5 Cutting Edge Medical Device Advancements That May Be In Your Home Soon
Medical Artificial Intelligence Defined
According to Techopedia, artificial intelligence is a branch of computer science that works to improve software solutions by giving the ability to analyze the surrounding environment and then make decisions based on the analyses done. Artificial medical intelligence is any medical technology used to collect, analyze, and make decisions based on health data.
Are you interested in learning more about how the EU MDR affects medical device manufacturing? If so, learn about this in an upcoming book release from David R. Rutledge. Follow this story of intrigue and redemption within an up-and-coming manufacturer, Mythical Medical™.
How the Continued Development of Artificial Intelligence for Medical Devices Is Benefiting the Healthcare Industry
You may have noticed that large technology companies have accelerated their design and development of intelligent products, particularly smart wearables. Some use artificial intelligence to develop new artificial intelligence applications and create new and innovative patient-friendly functionalities.
Beyond the larger tech companies, artificial intelligence for medical devices is accelerating significantly. Artificial intelligence has begun to present new opportunities in the medical device industry by providing equipment and device manufacturers the ability to:
- Reach new customer segments
- Use the collected data in new ways with no limits in volume or processing speed
- Create new methods of helping patients and developing new and unique products
- Finding hidden correlations in data, with some being discovered in real-time
Artificial intelligence in the medical device industry is fascinating. New and exciting innovations are being produced and released weekly. Some of the ways that medical services are now using AI-powered medical devices include:
- Diagnosing: Healthcare providers can provide a better and more timely medical condition diagnosis.
- Prevention: It’s possible to predict pathologies and let caregivers make informed and timely decisions.
- Care: It’s possible to automate the follow-up process with patients, even if they are being seen remotely.
- Personalization: It’s possible to personalize the treatment of every patient.
Along with the benefits above, artificial intelligence-powered medical devices can also improve medical data quality so that it’s able to be used for predictive analytics purposes. It also helps to improve the operational efficiency of all types and sizes of care institutions.
How Else is Artificial Intelligence Being Used for Medical Devices Today?
As technology continues to advance, medical device manufacturers are creating artificial intelligence devices that can be used for two primary functions:
1. Internet of Things (IoT)
The Internet of Things (IoT) is a system of interrelated, wireless, and connected devices that medical professionals utilize in terms of medical devices. The purpose is to manage data, monitor patients, work more efficiently and effectively, reduce costs, and ensure patients remain informed about what is going on. Most companies are now using IoT for medical devices to help improve patient outcomes.
2. Medical Imaging
Medical devices are also being developed with artificial intelligence to help with medical imaging. These devices produce higher-quality images with increased clarity to improve diagnosis, treatments, or monitoring. The outcomes are better than just relying on your eyes alone. It also picks up patterns your eyes may not see. Another benefit of artificial intelligence-powered imaging devices is reducing radiation exposure.
FDA Guidance for Artificial Intelligence-Powered Medical Devices
While the benefits of artificial intelligence for medical devices are evident, it’s also worth noting the challenges it faces. One example would be the need for regulation to ensure technology advancements don’t surpass oversight and testing. Like with any other technology, there is the possibility that artificial intelligence is flawed. This increases the risk that artificial intelligence medical devices may misdiagnose patients or administer improper treatment. Also, since medical devices impact a person’s health and life, they deserve to be highly regulated.
Creating regulations and the process that devices must undergo for approval takes time. The U.S. Food and Drug Administration (FDA) issued the “Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD) Action Plan” from the Center for Devices and Radiological Health’s Digital Health Center of Excellence. As part of this Action Plan, the agency is highlighting the following intended actions and goals:
- Develop an update to the proposed regulatory framework presented in the Artificial Intelligence/Machine Learning (AI/ML)-based Software as a Medical Device (SaMD) discussion paper, including the issuance of a Draft Guidance on the Predetermined Change Control Plan.
- Strengthen FDA’s encouragement of the harmonized development of Good Machine Learning Practice (GMLP) through additional FDA participation in collaborative communities and consensus standards development efforts.
- Support a patient-centered approach by continuing to host discussions on the role of transparency to users of AI/ML-based devices. Building upon the October 2020 Patient Engagement Advisory Committee (PEAC) Meeting focused on patient trust in AI/ML technologies, hold a public workshop on medical device labeling to support transparency to users of AI/ML-based devices.
- Support regulatory science efforts on the development of methodology for the evaluation and improvement of machine learning algorithms, including for the identification and elimination of bias, and on the robustness and resilience of these algorithms to withstand changing clinical inputs and conditions.
- Advance real-world performance pilots in coordination with stakeholders and other FDA programs to provide additional clarity on what a real-world evidence generation program could look like for AI/ML-based SaMD.
Related: Top 5 Cutting Edge Medical Device Advancements That May Be In Your Home Soon
Until then, FDA has made progress by granting 510(k) clearance for several artificial intelligence-based systems, such as (i) QuantX, an artificial intelligence diagnostic tool aiming to improve breast cancer diagnosis; (ii) the Apple watch ECG, which uses electrodes to capture heart rhythm irregularities and cleared as an over-the-counter ECG monitoring device; (iii) AIDOC, an artificial intelligence-based system that allows radiologists to identify acute intracranial hemorrhages in head CT scans specifically for the detection of large-vessel occlusions; and (iv) Zebra Medical Vision, which secured five FDA clearances for their artificial intelligence imaging products. These examples represent a model of collaboration between innovators and regulators.
It is expected that eventually, the FDA will have a standard medical device testing process in place to help speed up the time to market for these items.
In October 2021, three competent authorities agreed to philosophies that would push the area of AI/ML into greatness. The FDA, Health Canada, and the United Kingdom’s Medicines and Healthcare products Regulatory Agency (MHRA) have jointly identified ten guiding principles that can inform the development of Good Machine Learning Practice (GMLP). These guiding principles will help promote safe, effective, and high-quality medical devices that use artificial AI/ML.
Strong international public health partners will be crucial to empowering entrepreneurs, manufacturers, and other stakeholders to advance responsible innovations in this area.
Book an appointment today if you are ready to learn more about global medical device approvals and how Global Strategic Solutions, LLC here in the Silicon Valley area of California might help.
Conclusion
Artificial intelligence has helped present an entirely new spectrum of diagnostic and therapeutic possibilities for patients in the past ten years. Now it has begun to power an all-new generation of systems that help doctors and other healthcare professionals deliver higher levels of care. Because of this, it is believed that artificial intelligence will lead the way when it comes to introducing a new era of startling breakthroughs related to patient care.
It’s a fun, intellectually stimulating journey. Join me—no computer programming is required!
Related: What Is the Difference Between Quality Control and Quality Assurance?