Work

Beyond Accuracy: A Metrological Framework for the Reliability of Artificial Intelligence-Based Biomedical Measurement Systems

Year: 2026

Type: article

Abstract: This review proposes the Biomedical AI Metrological Reliability Framework (BAMRF), a 12-domain framework for evaluating the reliability of artificial intelligence-enabled biomedical measurement systems. The paper integrates concepts from medical metrology, measurement uncertainty, traceability, clinical validation, AI reporting guidelines, regulatory science, and risk management. It argues that algorithmic accuracy alone is insufficient to establish reliable clinical measurement and proposes a comprehensive framework covering the complete measurement chain, from sensor calibration to lifecycle surveillance. The review aims to support researchers, regulators, manufacturers, conformity assessment bodies, and healthcare professionals involved in trustworthy biomedical AI systems.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.21612594

Author: Durmuş, Hüseyin Okan

Institutions: Gebze Technical University, Middle East Technical University, Tübitak National Metrology Institute

Language: English

Topic: Artificial Intelligence in Healthcare and Education

Subfield: Health Informatics

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: green

OpenAlex ID: W7171291997

FWCI:

Cites:

Cited by:

Related to: