The quest is on for machine learning (ML) to turn raw data into useful medical devices that improve outcomes and reduce burden on the healthcare system. Supporting, and someday emulating, human thought processes enables ML devices to improve the decision-making process for patients and clinicians. Software designed to continually learn and improve poses both challenges and opportunities.
For example, in the not-so-distant future, patients may experience medical devices such as an intelligent insulin pump that more effectively manages patient needs in anticipation of a dessert about to be consumed. As ML matures, the possibilities to improve patient care are endless while the challenges are many.
ML Device Development
As device developers seek to harness ML for next generation products, it’s important to address the unique ML challenges in the pre-commercial stage, including:
- The research phase, where selecting the ML algorithm drives subsequent risk mitigation considerations
- The building phase, which addresses verification, validation, and risk management concerns specific to ML
- Regulatory processes and the nuances of working with regulatory bodies and novel technology
ML Algorithms
ML typically uses supervised or unsupervised algorithms to discover a data pattern and generate actions. In supervised learning, the developer guides the teaching process of the algorithm. This requires a known data set with inputs and outputs to train the machine to make predictions. The developer corrects the machine’s predictions in this learning cycle, and the system learns from the corrections.
Natural language processing is an example of this. The developer enters a sentence, asks the machine what it means and over time, the machine learns the pattern and consequently makes smarter outputs.
Unsupervised Learning
The other type is unsupervised learning, where the developer does not provide teaching guidance along the way. Instead, the machine extracts general rules from the data using mathematical optimization and other techniques. An example involves the condition of peritonitis, a swelling of the peritoneal cavity. The machine takes pictures of the patient cavity and determines if infection is suggested based on its analysis of prior data.
Choosing to use either a supervised or unsupervised ML algorithm typically depends on factors. These include the structure and volume of the data, and the use case at hand of the medical device. The developer can introduce errors in the model if the underlying assumptions are untrue. For example, a machine could learn how to visually differentiate between a criminal and civilian if given a set of photographs. However, the resulting algorithm would be incorrect when applied to future photos because appearance doesn’t predict criminal behavior.
ML Validation and Verification
Besides choosing the best algorithm at the onset of new product development, the R&D professional needs to choose the right amount of data to validate the model. Mislabeled data, too little data, and too much data introduces risk into the machine. The risks are based on the type of algorithm in ML.
In supervised learning, the decision tree or statistics are used to teach the machine. It’s validated by using fault tree analysis that pairs with the decision tree to understand if the machine takes the wrong path based on input data. The challenge in validation is mathematically proving the error margin falls within the tolerance originally specified. The math requires an adequate data set where data points can be allocated between the learning the validation samples.
In Vitro Diagnostics
ML can make it difficult to determine appropriate data sizes due to the lack of standards and potential introduction of creative approaches. A developer, for example, might compare previous clinical studies to suggest sample sizes. In-vitro diagnostics (IVD) validation might require some 450,000 patient data sets for algorithm development and validation to ensure the sample size in the fault tree analysis.
Artificial Intelligence
In another example, IBM Watson allows developers to choose various AI algorithms. A developer searching for cancer tumors in a biopsy might choose a neural network, which can be difficult to understand and challenging to develop and validate.
The neural network is trained using sets of data like a list of blood test results that indicate the patient has a certain number of cancer cells. Or, the algorithm can be trained by supplying it with images of healthy cells and those afflicted with cancer. In this example, the algorithm can be validated by comparing the training data set to a reasonable clinical study, which compares blood test results to correct diagnoses, the developer asserts that the algorithm has been adequately trained.
Algorithms, which are developed by using a pre-developed AI model, can be validated by leveraging the recommendation of the original creator on the amount of data needed to test to meet the desired margin of error. Another way to determine sample size involves leveraging domain experts such as clinicians, who understand the frequency of all paths in the decision tree based on their knowledge of each tree node and its associated risks.
Cybersecurity
Developers understand the need for security and privacy in healthcare applications. In ML, a new security risk involves the malicious introduction of bad data into the machine, which can lead to invalid and harmful outputs. Use of ethical hackers, however, can help mitigate the risk of bad data in supervised learning. These hackers specialize in simulating malicious acts that lead to limitations or boundaries on system learning, which ultimately protect against bad data.
Mitigation Tactics
The risk of bad data in unsupervised ML can be reduced by buying an established algorithm with embedded mitigation tactics (mathematical, programmatic, etc). However, a thorough review of the algorithm mitigations is necessary by cybersecurity specialists who understand medical devices and unsupervised machine learning algorithms.
Developers have long been wary of privacy issues related to protected health information in cloud applications. Since many ML platforms leverage cloud storage and therefore introduce new risks to the process, it’s important for ML developers to understand how their data is collated with other data sets. This shared data about the patient condition could be combined to violate privacy through a technique called inference by malicious entities.
Inference
Inference is an approach that combines different innocuous and non-sensitive data to gain sensitive information. Consider the aggregated data for an automobile accident patient. It’s possible an attorney might slice the data and discover information about the victim’s diabetes to blame the patient for the mishap due to a potential diabetic coma.
The use of polyinstantiation can mitigate these types of risks by slicing the data into sets for collation, and designing data silos so only the developer knows which piece goes into the algorithm, thereby preventing the disclosure of the entire patient database.
Regulation in ML Technologies
Experienced medical device developers understand the well-established process for working with regulators and developing submissions. The challenge in ML surrounds the lack of precedence.
Regulators are used to working with established frameworks where a consistent set of inputs generates a reliable set of outputs, but in ML, the outputs are continuously evolving. Thus, device developers must help regulatory agencies establish ways to assess the safety and effectiveness of products. Some suggested tactics include:
- Build a regulatory affairs team with experience in ML and multidisciplinary functions.
- Conduct early and frequent meetings with regulatory authorities so both sides can learn from each other.
- Find clinical and regulatory information throughout the world that is supportive of the desired goal. If negative information is uncovered, address it rather than ignore it.
- Do not submit a “black box.” Develop ways to communicate how and why a particular result occurred.
- Seek related credible sources, publications, guidance documents and subject matter experts, reference them, and utilize them.
- Recognize that regulators are used to understanding the device’s Mechanism of Action. In ML and other novel technologies, it is difficult to describe how the device works, so seek alternatives such as Safety Assurance Cases to help effectively communicate risks and risk management activities.
Safety Assurance
- Presents all claims that can be easily linked with supporting evidence to demonstrate the validity of safety claims
- Is a formal method used to demonstrate the validity of a claim. It is presented as a clear, understandable argument supported by scientific evidence
- Contains arguments based on statistical measurements of the system’s reliability and are grounded in risk-based and scientific methods to help discuss and draw conclusions
For regulators, safety assurance cases:
- Help to connect the dots in a structured way
- Helps them to see both claims and supporting evidence
- Helps them understand the “big picture”
For medical device manufacturers, safety assurance cases:
- Align medical device product development with FDA expectations.
- Help gain faster regulatory approvals. Medical device companies that move toward best practices by leveraging safety assurance case principles can clearly demonstrate product safety in a single document, making it easier for the FDA to review.
The three elements of an assurance case are claims, evidence, and arguments.
- The claim is a statement about a property of the system—typically, contained and/or driven by a requirements specification
- The evidence should provide information demonstrating the validity of the claim. This evidence may include verification and/or validation results including, but not limited to, test data, experiment results, and analysis. The evidence should also address the relevance to the claim, whether the evidence directly supports the claim, and whether it is providing sufficient coverage of the claim
- Arguments should link evidence to the claim and provide a detailed description of what is being proven. The arguments also should identify specific evidence that supports the claim
Risk Management
About the Article
About RCA’s Medical Device Consulting Services
The regulatory compliance process surrounding the medical device industry involves a strict adherence to pre/post market information throughout a device’s life-cycle. Even a single compliance issue you have can turn into a significant effect on your business. Regulatory Compliance Associates medical device consultants can help guide you through any stage of this strategic process, with capabilities during product development through the regulatory clearance/approval of your product.
Our team of over 500 medical device consulting Experts — including former FDA officials and regulatory compliance leaders in the field of medical device regulation — will work with your company to create a quality assurance and regulatory compliance approach tailored to your products and regulatory needs. Regulatory Compliance Associates works with international Fortune 100 companies, venture capital start ups, and companies of all sizes and shapes. our compliance enforcement solutions for law firms include remediation for warning letters, FDA 483’s, import bans or consent decrees. Very few regulatory compliance services have the same regulatory compliance expertise in a variety of medical fields.
Cybersecurity
For medical device manufacturers, technology can be a double-edged sword. The innovative technologies that elevate the quality of life for patients can also be used to potentially undermine the organization using the device. The consequences can affect the device itself if Regulatory Compliance Associates medtech consultants do not implement good IoT cybersecurity and FDA cybersecurity protocols.
At Regulatory Compliance Associates, we offer a wide variety of services for medical devices security to help ensure that your product is protected from cyber-attacks. With a well-planned design, along with full visibility of product development and the supply chain, Regulatory Compliance Associates medical device consultant Experts can help strengthen your device’s cybersecurity. We partner with medical device companies in each phase of the design cycle, including protecting inputs from threat exposure and hardening outputs for regulatory compliance & FDA submission approval of your medical technology.
Regulatory Affairs
Regulatory affairs is Regulatory Compliance Associates® backbone, and we handle more submissions in a month than many manufacturers do in a lifetime. Our regulatory compliance consulting Experts have experience working with the FDA, global regulatory bodies and / or agencies, and notified bodies worldwide. Therefore, you can count on us for in-depth and up-to-date insights which increase speed-to-market.
As a trusted regulatory affairs consultant, our FDA veterans and industry experts represent Regulatory Compliance Associates® as one of the top medical device consulting firms. We’re here to help you navigate the difficulties associated with new product submissions. Regulatory Compliance Associates® medical device consulting company has expertise in both the approval process and post-approval support.
- New Product Approval
- Post-Approval Support
- Outsourced Staffing
- EU MDR
- Combination Products
Compliance Assurance
Increasingly, life science companies are feeling the pressure of greater scrutiny by regulators, and responding by developing sustainable compliance strategies. Whether it’s preparing for an audit, developing a response to an FDA finding, or remediation to an adverse event, Regulatory Compliance Associates® can help.
Our network of over 500 medical device consultant & FDA, MHRA & EMA veterans are industry professionals offers a unique blend of expertise. This allows Regulatory Compliance Associates® to handle both simple and complex regulatory compliance challenges within medical device consulting companies.
- Gap Assessments
- Internal Audits
- Employee Training
- Notified Body Response
- Data Integrity
Quality Assurance
Regulatory Compliance Associates® Quality Assurance consulting includes quality system assessments, strategy, implementations, and identification of quality metrics to ensure continuous improvement, aligning with your business needs and goals. Each Regulatory Compliance Associates® medical device consultant is a quality expert with experience spanning major corporations and start-ups. We know firsthand how to achieve, maintain, and improve quality, and we excel in transferring this knowledge to your organization.
In the medical devices field, quality assurance (QA) is more than merely ensuring the quality of a finished product. You need the tools to monitor and regulate every process from the design of a new product to continued quality compliance as the device is sent to market. At Regulatory Compliance Associates®, we offer you the quality assurance services you need to monitor these processes and ensure quality compliance every step of the way.
With more than 20 years experience working with medical device consulting companies, Regulatory Compliance Associates® trusted medical device quality assurance consultant team is fully equipped to handle your unique QA needs.
- ISO13485
- 21 CFR 210
- 21 CFR 211
- Outsourced Staffing
- MDSAP
- Facility Validation
- Equipment Validation
- Quality Metrics
Remediation Support
Regulatory Compliance Associates® is widely recognized within medical device consulting companies & the life science industry for remediation support. Regulatory Compliance Associates® ability to help companies successfully resolve complex regulatory challenges have a proven track record of success. Our medical device consulting services include significant experience with the development of responses to 483 Observations, Warning Letters, Untitled Letters and Consent Decrees.
- Regulatory Action
- Regulatory Compliance
- Regulatory Enforcement
- Warning Letter
- 483 Observation
- Oversight Services
Our value goes beyond the initial response by helping companies successfully execute their action plans, develop an improved compliance culture tailored to the needs of their business, and ultimately move beyond the regulatory action to emerge as a stronger business. We negotiate difficult demands of remediation with insight and the clear advantage of our medical device consultant expertise and experience that makes partnering with Regulatory Compliance Associates® a competitive differentiator in the remediation space.
- Quality System
- Technical File
- Design History File
- Data Integrity
- cGMP
Strategic Consulting
Whether it’s a strategy, a technical plan, or project, Regulatory Compliance Associates® medical device consultancy can help ensure a successful project. Regulatory Compliance Associates® medical device strategy consulting can deliver your project on time, on budget, and you’re never embroiled in a costly mistake.
Our medical device consultant Experts are industry Experts are here to provide the unique insight you need before an M&A deal, through a staffing crisis and in every area of your product’s development and life cycle. As the trusted medical device manufacturing consultants of thousands of companies around the world, we have the knowledge and expertise needed to deliver exceptional results to your business — no matter your size or unique needs.
- Manufacturing Optimization
- Product Lifecycle Management
- Mergers & Acquisitions (M&A)
- Due Diligence
- Device Vigilance
- Risk Management Plan
- Product Complaints
- Medical Information
About Regulatory Compliance Associates
Regulatory Compliance Associates® (RCA) provides medical device consulting to the following industries for resolution of life science challenges:
- Life Sciences
- Pharmaceutical
- Biologic & Biotechnology
- Sterile compounding
- Medical device
- Lab Testing
We understand the complexities of running a life science business and possess areas of expertise that include every facet of R&D, operations, regulatory affairs, quality, and manufacturing. We are used to working on the front lines and thriving in the scrutiny of FDA, Health Canada, MHRA and globally-regulated companies.
As your partners, we can negotiate the potential minefield of regulatory compliance and regulatory due diligence with insight, hindsight, and the clear advantage of our unique expertise and experience.
- Founded in 2000
- Headquartered in Wisconsin (USA)
- Expertise backed by over 500 industry subject matter experts
- Acquired by Sotera Health in 2021
About Sotera Health
The name Sotera Health was inspired by Soteria, the Greek goddess of safety, and reflects the Company’s unwavering commitment to its mission, Safeguarding Global Health®.
Sotera Health Company, along with its three best-in-class businesses – Sterigenics®, Nordion® and Nelson Labs®, is a leading global provider of mission-critical end-to-end sterilization solutions and lab testing and advisory services for the healthcare industry. With a combined tenure across our businesses of nearly 200 years and our industry-recognized scientific and technological expertise, we help to ensure the safety of over 190 million patients and healthcare practitioners around the world every year.
We are a trusted partner to more than 5,800 customers in over 50 countries, including 40 of the top 50 medical device companies and 8 of the top 10 pharmaceutical companies.
Commitment to Quality
Our Certificate of Registration demonstrates that our Quality Management System meets the requirements of ISO 9001:2015, an internationally recognized standard of quality.
To begin the Regulatory Compliance Associates® scoping process today, please enter your information in the blue form below and click the submit button at the bottom of the webpage.