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.
Anemia control model
machine learning
medical device certification
predictive modeling
risk assessment
Journal
Expert review of medical devices
ISSN: 1745-2422
Titre abrégé: Expert Rev Med Devices
Pays: England
ID NLM: 101230445
Informations de publication
Date de publication:
Nov 2021
Nov 2021
Historique:
pubmed:
7
10
2021
medline:
26
11
2021
entrez:
6
10
2021
Statut:
ppublish
Résumé
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. 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. 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. 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.
Sections du résumé
BACKGROUND
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
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
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
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.
Identifiants
pubmed: 34612120
doi: 10.1080/17434440.2021.1990037
doi:
Substances chimiques
Hematinics
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM