Clinical evaluation process of software as a medical device (SaMD)

The clinical evaluation process of software as a medical device (SaMD) is a critical step to ensure its safety, efficacy, and performance in a real-world clinical settings. This process is guided by international standards, regulatory frameworks and guidelines, such as the ones derived from the International Medical Device Regulators Forum (IMDRF).

Basically speaking, a SaMD uses an algorithm (e.g., logic, set of rules, or
model) that operates on data input (i.e., digitized content) to produce an output that is intended for medical purposes. As such, the risks and benefits posed by SaMD outputs are largely related to the risk of inaccurate or incorrect output of the SaMD, which may impact the clinical management of a patient.

Prior to product launch (pre-market), the manufacturer has already complied with verification and validation activities using common specifications and ISO standards as a structured framework to generate evidence of the SaMD's accuracy, specificity, sensitivity, reliability, limitations, and scope of use in the intended use environment with an intended user in mind.

As such, in the initial step of a clinical evaluation of the SaMD, we clearly define the user, the target patient population, the clinical condition, and the specific healthcare setting in which the software will be used, based on pre-market information provided by the manufacturer.

The risk assessment done as part of the SaMD’s lifecycle activities and processes is fundamental when conducting a clinical evaluation, because it identifies potential risks and pre-determines the clinical data needed to address these risks assuring patient safety.

As such, with the risks in mind, we then need to determine the types of clinical data that is needed to limit those risks and demonstrate the safety, clinical performance, and effectiveness of the SaMD. This includes clinical investigations, real-world evidence, published scientific literature, and post-market surveillance data from the device itself and similar (or equivalent) devices currently on the market.

In the end, by balancing the risks against the clinical benefits, we conduct an independent assessment that the SaMD is clinically meaningful to its
users/patients and provides a positive output that can impact clinical outcomes/patient care.

The recommendation for independent review from the IMDRF highlights where the evidence generated from the clinical evaluation of the SaMD should be reviewed by someone who has not been significantly involved in the development of the SaMD, and who does not have anything to gain from the SaMD, and who can objectively assess the SaMD’s intended purpose and the conformity with the overall clinical evaluation evidence. The level of clinical evaluation and importance of an independent review should be commensurate with the risk posed by the SaMD.