The FDA is the oldest consumer protection agency, and is a part of the U.S. Department of Health and Human Services. Its charter is to protect public health by regulating a broad spectrum of products, such as vaccines, prescription medication, over-the-counter drugs, dietary supplements, bottled water, food additives, infant formulas, blood products, cellular and gene therapy products, tissue products, medical devices, dental devices, implants, prosthetics, electronics that radiate (e.g., microwave ovens, X-ray equipment, laser products, ultrasonic devices, mercury vapor lamps, sunlamps), cosmetics, livestock feeds, pet foods, veterinary drugs and devices, cigarettes, tobacco, and more products. 

In April 2019, the FDA released a discussion paper and request for feedback to its proposed regulatory framework for modifications to AI machine learning-based software as a medical device. Examples of SaMD include AI-assisted retinal scanners, smartwatch ECG to measure heart rhythm, CT diagnostic scans for hemorrhages, ECG-gated CT scan diagnostics for arterial defects, computer-aided detection (CAD) for post-imaging cancer diagnostics, echocardiogram diagnostics for calculating left ventricular ejection fraction (EF), and using smartphones to view diagnostic magnetic resonance imaging (MRI). 

The newly released plan is a response to the comments received from stakeholder regarding the April 2019 discussion paper. The plan covers five areas: 1) custom regulatory framework for AI machine learning-based SaMD, 2) good machine learning practices (GMLP), 3) patient-centered approach incorporating transparency to users, 4) regulatory science methods related to algorithm bias and robustness, and 5) real-world performance. 

This year the FDA plans to update the framework for AI machine learning-based SaMD via publishing a draft guidance on the “predetermined change control plan.” The FDA has cleared and approved AI machine learning-based software as a medical device. Usually these approvals were for “algorithms that are ‘locked’ prior to marketing, where algorithm changes likely require FDA premarket review for changes beyond the original market authorization.”

How to regulate evolving machine learning algorithms that change over time? These types of evolutionary algorithms are not uncommon in machine learning. Real-world data is often used to improve algorithms that were trained using existing data sets, or in some cases, computer-simulated training data. The incorporation of real-world data to fine-tune algorithms may produce different output. The goal of such evolving learning algorithms is to improve predictions, pattern-recognition, and decisions based on actual data over time. Nonetheless, even if these types of algorithms do result in better performance over time, it is still important to communicate to the medical device user what exactly to expect for transparency and clarity sake.

In the area of establishing and defining good machine learning practices (GMLP), the FDA is “committing to deepening its work in these communities in order to encourage consensus outcomes that will be most useful for the development and oversight of AI/ML based technologies,” and aims to provide “a robust approach to cybersecurity for medical devices.” 

In 2021, the FDA plans to hold a public workshop on “how device labeling supports transparency to users and enhances trust in AI/ML-based devices” in efforts to promote transparency, an important part of a patient-centered approach.

To address algorithm bias and robustness, the FDA plans to support regulatory science efforts to develop methods to identify and eliminate bias. “The Agency recognizes the crucial importance for medical devices to be well suited for a racially and ethnically diverse intended patient population and the need for improved methodologies for the identification and improvement of machine learning algorithms,” wrote the FDA.

The FDA is supporting collaborative regulatory science research at various institutions to develop methods to evaluate AI machine learning-based medical software. These research partners include the FDA Centers for Excellence in Regulatory Science and Innovation (CERSIs) at the University of California San Francisco (UCSF), Stanford University, and Johns Hopkins University. 

The final part of the plan aims to provide clarity on real-world performance monitoring for AI machine learning-based software as a medical device. The FDA plans to “support the piloting of real-world performance monitoring by working with stakeholders on a voluntary basis” and engaging with the public in order to assist in creating a framework for collecting and validating real-world performance metrics and parameters.

“The FDA welcomes continued feedback in this area and looks forward to engaging with stakeholders on these efforts,” wrote the FDA.

Artificial intelligence machine learning is gaining traction across many industries, including the areas of health care, life sciences, biotech, and pharmaceutical sectors. With this newly released plan, the FDA has advanced its ongoing discussion with its stakeholders in efforts to provide regulations that ensure the safety and security of AI machine learning-based software as a medical device in order to protect public health.

The post FDA HAS NEW REGULATORY PLANS FOR AI MACHINE LEARNING appeared first on Artificial Intelligence.

An expert in machine learning and natural language processing discusses how these technologies are enhancing care and enabling the use of SDOH data and personalized analytics.

Some healthcare provider organizations are using machine learning and other forms of artificial intelligence to provide clinicians with the best evidence-based care pathways.

A group’s aim could be to improve a patient’s care plan based on personalized analytics. Another goal could be the further merging of evidence-based care paths with historical utilization and outcomes in order to offer optimal patient care. Provider organizations might be using social determinants of health combined with machine learning to offer clinically meaningful services.

Healthcare IT News talked over these ideas with Niall O’Connor, chief technology officer at Cohere Health, a vendor of artificial intelligence technology and services designed to improve the provider, patient and payer experiences.

Q: How is machine learning being used to comprehensively enhance a patient’s entire care plan based on personalized analytics? And how is machine learning being used to combine evidence-based care paths – with real-world historical utilization, outcomes and the latest literature – to provide first-rate patient care?

A: Evidence-based guidelines are an important component of an intelligent care path solution. In fact, they are the starting point for our models. We would never want to relearn the complexity that has been elucidated in clinical guidelines.

At the same time, guidelines were written for the average patient and can’t possibly accommodate all the comorbidity permutations that exist for patients of high acuity. This is where machine learning can help. For patients that don’t perfectly fit existing evidence-based care paths, we can employ machine learning models to infer what has been the most efficacious path for diagnostically identical patients from real world historical data.

Q: How is machine learning being used to use social determinants of health and patient lifestyle to provide precise and clinically meaningful care?

A: Data regarding social determinants of health (SDOH) and patient lifestyle are not typically captured in standard electronic health records, but diligent physicians typically refer to this type of data in their clinical notes.

We can also supplement models with SDOH data – such as the U.S. Census – that can point to access or other patient challenges and incorporate patient-reported data, whether on lifestyle or health state.

This presents a challenge for typical analysis, so we employ natural language processing to help isolate and interpret references to things like lifestyle impacts or resumption of employment following surgery. Although detection of these phrases isn’t comprehensive, when present they can help provide valuable outcome endpoints for us.

Q: How did machine learning first come to be seen as useful in these areas?

A: Clinical data analysis isn’t a big data problem; it’s a messy data problem and is plagued by the fact that much of the valuable information isn’t readily available in structured form.

Volume also plays a big part in why we use machine learning; when we end up with thousands of attributes, we need machine learning to identify the variables that are driving the model. For SDOH in particular, machine learning will be crucial for variable selection and essential to refining some signal from the noise of operational clinical data.

The post How machine learning can improve patients’ care plans appeared first on Artificial Intelligence.