Digital Health: QA, RA & CA Forum

Has anyone got a question for the group?

Its not a diagnostic if it only categories the risks......could this be a new category? On Thursday, the FDA granted marketing authorization of Renalytix AI, Inc.’s KidneyIntelX.dkd, an in vitro diagnostic intended to aid in the assessment of risk of progressive kidney function decline in adult patients with Type 2 diabetes and existing chronic kidney disease. KidneyIntelX.dkd works by measuring three analyte components associated with kidney function decline from a patient’s plasma sample. The results of the three measured analytes are combined with three data inputs from the patient’s medical record provided by the ordering physician, and a machine-learning algorithm provides a risk category of low, moderate, or high. KidneyIntelX.dkd is not intended for screening or as a stand-alone diagnostic test. https://www.medicaldevice-network.com/news/renalytix-de-novo-authorisation-kidneyintelx-dkd-test/

No standards for Medical AI or Machine Learning... (other than IEC 62304 of course).... may we present: Good Machine Learning Practice for Medical Device Development: Guiding Principles The U.S. Food and Drug Administration (FDA), Health Canada, and the United Kingdom’s Medicines and Healthcare products Regulatory Agency (MHRA) have jointly identified 10 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 intelligence and machine learning (AI/ML).

Let us know what you think....

Guidance on significant changes regarding the transitional provision under Article 120 of the MDR.

Its simple, but its not.....

Its all about the intended use, especially with SaMD.

Here is a guidance on how to write one (this time from the UK)

Crafting an intended purpose in the context of software as a medical device (SaMD)