Opaque ontology: neuroimaging classification of ICD-10 diagnostic groups in the UK Biobank
GigaScience · 2025
DOI: 10.1093/gigascience/giae119 ↗Kurz gefasst
Fachartikel in der Zeitschrift GigaScience, 2025. Verfasst von Ty Easley und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Washington University School of Medicine, Saint Louis, Missouri 63110, USA. Hauptthemen laut MEDLINE: International Classification of Diseases, Neuroimaging, Biological Specimen Banks. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Washington University Research Computing and Informatics Facility, NIMH NIH HHS, NIH HHS.
Abstract (Originalsprache)
Background
The use of machine learning to classify diagnostic cases versus controls defined based on diagnostic ontologies such as the International Classification of Diseases, Tenth Revision (ICD-10) from neuroimaging features is now commonplace across a wide range of diagnostic fields. However, transdiagnostic comparisons of such classifications are lacking. Such transdiagnostic comparisons are important to establish the specificity of classification models, set benchmarks, and assess the value of diagnostic ontologies.
Results
We investigated case-control classification accuracy in 17 different ICD-10 diagnostic groups from Chapter V (mental and behavioral disorders) and Chapter VI (diseases of the nervous system) using data from the UK Biobank. Classification models were trained using either neuroimaging (structural or functional brain magnetic resonance imaging feature sets) or sociodemographic features. Random forest classification models were adopted using rigorous shuffle-splits to estimate stability as well as accuracy of case-control classifications. Diagnostic classification accuracies were benchmarked against age classification (oldest vs. youngest) from the same feature sets and against additional classifier types (k-nearest neighbors and linear support vector machine). In contrast to age classification accuracy, which was high for all feature sets, few ICD-10 diagnostic groups were classified significantly above chance (namely, demyelinating diseases based on structural neuroimaging features and depression based on sociodemographic and functional neuroimaging features).
Conclusion
These findings highlight challenges with the current disease classification system, leading us to recommend caution with the use of ICD-10 diagnostic groups as target labels in brain-based disease prediction studies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Washington University School of Medicine, Saint Louis, Missouri 63110, USA.
ORCID-Profile: Ty Easley, Xiaoke Luo, Kayla Hannon, Petra Lenzini, Janine Bijsterbosch
Förderung
- Washington University Research Computing and Informatics Facility
- NIMH NIH HHS
- NIH HHS
- NIH S10
- National Science Foundation
- National Institutes of Health
Zitieren
APA
Easley, T., Luo, X., Hannon, K., Lenzini, P., & Bijsterbosch, J. (2025). Opaque ontology: neuroimaging classification of ICD-10 diagnostic groups in the UK Biobank. GigaScience. https://doi.org/10.1093/gigascience/giae119
Vancouver
Easley T, Luo X, Hannon K, Lenzini P, Bijsterbosch J. Opaque ontology: neuroimaging classification of ICD-10 diagnostic groups in the UK Biobank. GigaScience. 2025. doi:10.1093/gigascience/giae119
BibTeX
@article{Easley2025,
author = {Easley, Ty and Luo, Xiaoke and Hannon, Kayla and Lenzini, Petra and Bijsterbosch, Janine},
title = {Opaque ontology: neuroimaging classification of ICD-10 diagnostic groups in the UK Biobank},
journal = {GigaScience},
year = {2025},
doi = {10.1093/gigascience/giae119}
}
EUVIMED