Agency Takes Steps to Promote Scientifically Sound Development of AI-Based Medical Devices
The FDA is stepping up its efforts to regulate the development of medical devices that use artificial intelligence and machine learning (AI/ML) technologies. Here’s a briefing on a pair of significant initiatives that the agency unveiled in the past six weeks. The AI/ML Action Plan On Sept. 22, the agency published an Action Plan setting forth five actions it intends to take to advance sound, safe and effective development of AI/ML-based medical devices: Issue draft guidance for modification of algorithms in AI/ML software as a medical device (SaMD) over time; Promote Good Machine Learning Practice (GMLP), i.e., AI/ML best practices for data management, feature extraction, training, interpretability and evaluation that are akin to good software engineering practices; Hold a public workshop on how device labeling supports transparency to users and enhances trust in AI/ML-based devices; Support regulatory science efforts to develop methodology for evaluating and improving machine learning algorithms, including via identification and elimination of bias; and Support the piloting of real-world performance (RWP) monitoring for SaMD. The AI/ML Best Practices Guidelines On Oct. 27, the FDA and its counterpart agencies in Canada and the United Kingdom issued joint guidelines for companies developing The FDA, Health Canada and U.K. Medicines […]
The FDA is stepping up its efforts to regulate the development of medical devices that use artificial intelligence and machine learning (AI/ML) technologies. Here’s a briefing on a pair of significant initiatives that the agency unveiled in the past six weeks.
The AI/ML Action Plan
On Sept. 22, the agency published an Action Plan setting forth five actions it intends to take to advance sound, safe and effective development of AI/ML-based medical devices:
- Issue draft guidance for modification of algorithms in AI/ML software as a medical device (SaMD) over time;
- Promote Good Machine Learning Practice (GMLP), i.e., AI/ML best practices for data management, feature extraction, training, interpretability and evaluation that are akin to good software engineering practices;
- Hold a public workshop on how device labeling supports transparency to users and enhances trust in AI/ML-based devices;
- Support regulatory science efforts to develop methodology for evaluating and improving machine learning algorithms, including via identification and elimination of bias; and
- Support the piloting of real-world performance (RWP) monitoring for SaMD.
The AI/ML Best Practices Guidelines
On Oct. 27, the FDA and its counterpart agencies in Canada and the United Kingdom issued joint guidelines for companies developing The FDA, Health Canada and U.K. Medicines and Healthcare Products Regulatory Agency outline 10 “guiding principles” for companies that develop AI/ML-based medical devices:
- Leverage multi-disciplinary expertise throughout the total product life cycle;
- Implement Good Software Engineering and Security Practices;
- Ensure that relevant characteristics of the intended patient population (e.g., regarding age, gender, sex, race, and ethnicity), use and measurement inputs are sufficiently represented in a sample of adequate size in the clinical study and training and test datasets, so that results can be reasonably generalized to the population of interest;
- Ensure that training and test datasets are appropriately independent of one another;
- Select referenced datasets upon best available methods;
- Tailor model design to the available data and ensure that it reflects the device’s intended use;
- Account for human factors in evaluating performance of models that include a “human in the loop”;
- Ensure that testing of device performance is carried out in clinically relevant conditions;
- Provide device users clear, essential information; and
- Monitor models that are deployed in real world condition with a focus on maintaining or improving safety and performance.
As the AI/ML medical device field evolves, so too must [Good Machine Learning Practice] best practice and consensus standards, the new guidance notes.
Here are some of the key new FDA EUAs and clearances announced in October 2021:
New FDA Emergency Use Authorizations (EUAs) & Approvals
Manufacturer(s) | Product |
---|---|
InBios International | EUA for SCoV-2 Detect Neutralizing Ab ELISA immunoassay |
Celltrion | EUA for over-the-counter, at-home SARS-CoV-2 antigen test |
Biological Dynamics | Breakthrough device designation for Exo-PDAC liquid biopsy assay |
Cognetivity Neurosciences Ltd | Clearance for CognICA, 5-minute, computerized cognitive assessment for detecting dementia done on an iPad |
Thermo Fisher Scientific | EUA for using saliva samples collected with Spectrum Solutions SpectrumDNA SDNA-1000 collection device for COVID-19 tests run on Amplitude Solution |
Lighthouse Lab Services | EUA for RT-PCR-based CovidNow SARS-CoV-2 Assay |
Xtrava Health | EUA for SPERA COVID-19 Ag Test lateral flow immunoassay |
Agilent Technologies | Clearance for Ki-67 IHC MIB-1 pharmDx (Dako Omnis) assay to identify early breast cancer patients who can be treated with Eli Lilly’s abemaciclib (Verzenio) in combination with endocrine therapy |
Cleveland Clinic | EUA for SelfCheck Cobas SARS-CoV-2 Assay |
Quanterix | Breakthrough device designation for Alzheimer’s blood test run on the Quanterix HD-X immunoassay system |
Nonagen Bioscience | Breakthrough device designation for Oncuria non-invasive bladder cancer test |
Quest Diagnostics | EUA for at-home Collection Kit for COVID-19 |
PerkinElmer | EUA for PKamp Respiratory SARS-CoV-2 RT-PCR Panel 1 assay to detect SARS-CoV-2 and the flu |
Euroimmun | EUA for Anti-SARS-CoV-2 S1 Curve ELISA test |
Acon Laboratories | EUA for Flowflex COVID-19 Home Test over-the-counter antigen test |
OpGen | 510(k) clearance for Acuitas AMR Gene Panel |
LabCorp | EUA for combined home collection kit for molecular testing for COVID-19 and influenza A/B. |
New CE Marks & Global Certifications
Notable European CE certifications announced during the period:
NEW CE MARKINGS IN EUROPE
Manufacturer(s) | Product(s) |
---|---|
Intelligent Fingerprinting | VSS-GP COVID-19 Saliva Test |
GenomSys | GenomSys Variant Analyzer |
BioMérieux + Baxter | Nephroclear CCL14 Test for detecting acute kidney injury |
Agilent Technologies | PD-L1 IHC 28-8 pharmDx as companion diagnostic test to guide treatment of adult patients with HER2-negative advanced or metastatic gastric, gastroesophageal junction or esophageal cancers |
Sorrento Therapeutics | Covistix SARS-CoV-2 rapid antigen test |
Qiagen | QiaReach QuantiFeron-TB test for tuberculosis infection |
Biopix-T | COV19 qcLAMP kit + point-of-care Pebble qcLAMP Platform it runs on |
Cepheid | Xpert Xpress CoV-2/Flu/RSV plus rapid molecular diagnostic test for SARS-CoV-2, influenza A and B, and respiratory syncytial virus |
Genematrix | NeoPlex HPV29 Detection kit for human papillomavirus |
Takara Bio Europe | Takara SARS-CoV-2 Direct PCR detection kit |
Genedrive | Next generation of Genedrive System gene amplification platform |
Other international clearances announced during the period:
Manufacturer(s) | Country(ies) | Product(s) |
---|---|---|
LumiraDx | India | SARS-CoV-2 Antigen test |
Subscribe to view Essential
Start a Free Trial for immediate access to this article