Fairness and generalizability of OCT normative databases: a comparative analysis
Name
40942_2023_Article_459.pdf
Size
980.32 KB
Format
Adobe PDF
Checksum (MD5)
c49a3523069e9b5f9289e9a28fd74f8a
Author(s)
Nakayama, Luis F.
Zago Ribeiro, Lucas
de Oliveira, Juliana A. E.
de Matos, João C. R. G.
Mitchell, William G.
Malerbi, Fernando K.
Celi, Leo A.
Regatieri, Caio V. S.
Date Issued
August 21, 2023
Publisher
BioMed Central
Citation
International Journal of Retina and Vitreous. 2023 Aug 21;9(1):48
Version
Final published version
Abstract
Abstract
Purpose
In supervised Machine Learning algorithms, labels and reports are important in model development. To provide a normality assessment, the OCT has an in-built normative database that provides a color base scale from the measurement database comparison. This article aims to evaluate and compare normative databases of different OCT machines, analyzing patient demographic, contrast inclusion and exclusion criteria, diversity index, and statistical approach to assess their fairness and generalizability.
Methods
Data were retrieved from Cirrus, Avanti, Spectralis, and Triton’s FDA-approval and equipment manual. The following variables were compared: number of eyes and patients, inclusion and exclusion criteria, statistical approach, sex, race and ethnicity, age, participant country, and diversity index.
Results
Avanti OCT has the largest normative database (640 eyes). In every database, the inclusion and exclusion criteria were similar, including adult patients and excluding pathological eyes. Spectralis has the largest White (79.7%) proportionately representation, Cirrus has the largest Asian (24%), and Triton has the largest Black (22%) patient representation. In all databases, the statistical analysis applied was Regression models. The sex diversity index is similar in all datasets, and comparable to the ten most populous contries. Avanti dataset has the highest diversity index in terms of race, followed by Cirrus, Triton, and Spectralis.
Conclusion
In all analyzed databases, the data framework is static, with limited upgrade options and lacking normative databases for new modules. As a result, caution in OCT normality interpretation is warranted. To address these limitations, there is a need for more diverse, representative, and open-access datasets that take into account patient demographics, especially considering the development of supervised Machine Learning algorithms in healthcare.
MIT Department
Harvard--MIT Program in Health Sciences and Technology. Laboratory for Computational Physiology
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1186/s40942-023-00459-8
