There are specific standards that can be applied to the design, development, and validation of medical device algorithms. The most commonly used standard is IEC 62304:2006, which provides guidance on software life cycle processes for medical device software. In addition to IEC 62304, there are other standards and guidelines that can be applied to the development of medical device algorithms, depending on their intended use. For example, ISO 14971 provides guidance on risk management for medical devices, including software and algorithms, and the FDA has issued guidance documents on the development and use of artificial intelligence and machine learning algorithms in medical devices.
------------------------------
Raje Devanathan
Amerisource Bergen
TPIreg, Innomar Strategies
Senior Manager - Regulatory Affairs, Medical Devices
rdevanathan@tpireg.com3470 Superior Court
Oakville ON L6L0C4
Canada
------------------------------
Original Message:
Sent: 09-May-2023 11:51
From: Anonymous Member
Subject: Medical Device Algorithm
This message was posted by a user wishing to remain anonymous
62304 is appropriate for implementing an algorithm in software.
For developing the algorithm in the first place, there may be a disease-specific standard to consider as input, but usually it's plain research and development, science and mathematics.
Unless you're using tools like neural net training, in which case there are some standards for that.
Original Message:
Sent: 09-May-2023 09:03
From: Anonymous Member
Subject: Medical Device Algorithm
This message was posted by a user wishing to remain anonymous
What standard is applicable for medical device algorithms? Do manufacturers use IEC 62304, software lifecycle, to develop them or is there another standard or regulation?