How to assess the risks associated with the usage of a medical device based on predictive modeling: the case of an anemia control model certified as medical device. (2nd November 2021)

• Record Type: Journal Article
• Authors: Barbieri, Carlo; Neri, Luca; Chermisi, Milena; Bolzoni, Elena; Cattinelli, Isabella; Decker, Wolfgang; Stuard, Stefano; Martín-Guerrero, José D.; Mari, Flavio
• Is Part Of: Expert review of medical devices. Volume 18:Number 11(2021)
• Page Start: 1117
• Page End: 1121
• Publication Date: 2021-11-02
• Subjects: Anemia control model -- machine learning -- medical device certification -- predictive modeling -- risk assessment; Medical instruments and apparatus -- Periodicals; 610.28
• DOI: 10.1080/17434440.2021.1990037
• Languages: English
• ISSNs: 1743-4440

Abstract

ABSTRACT: Background: The successful application of Machine Learning (ML) to many clinical problems can lead to its implementation as a medical device (MD), which is important to assess the associated risks. Methods: An anemia control model (ACM), certified as MD, may face adverse events as a result of wrong predictions that are translated into suggestions of doses of erythropoietic stimulating agents to dialysis patients. Risks are assessed as the combination of severity and probability of a given hazard. While severities are typically assessed by clinicians, probabilities are tightly related to the performance of the predictive model. Results: A postmarketing data set formed by all adult patients registered in French, Portuguese, and Spanish clinics, belonging to an international network, was considered; 3876 patients and 11, 508 suggestions were eventually included. The achieved results show that there are no statistical differences between the probabilities of adverse events that are estimated in the ACM test set (using only Spanish clinics) and those actually observed in the postmarketing cohort. Conclusions: The risks of an ACM-MD can be accurately and robustly estimated, thus enhancing patients' safety. The proposed methodology is applicable to other clinical decisions based on predictive models since our proposal does not depend on the particular predictive model.