EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Statistically valid explainable black-box machine learning: applications in sex classification across species using brain imaging

Tingshan Liu iD, Jayanta Dey iD, Beiya Xu iD, Eric W Bridgeford, Samuel Alldritt, Karl-Heinz Nenning, Kyoungseob Byeon, Ting Xu, Joshua T Vogelstein

PLOS One · 16.04.2026 · 21 (4) · e0346575

DOI: 10.1371/journal.pone.0346575 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 16.04.2026. Verfasst von Tingshan Liu und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, United States of America. Hauptthemen laut MEDLINE: Machine Learning, Brain, Neuroimaging. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institutes of Health, National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sex classification using neuroimaging data has the potential to revolutionize personalized diagnostics by revealing subtle structural brain differences that underlie sex-specific disease risks. Despite the promise of machine learning, traditional methods often fall short in providing both high classification accuracy and interpretable, statistically validated feature importance scores for high-dimensional imaging data. This gap is particularly evident when conventional techniques such as random forests, LIME, and SHAP are applied, as they struggle with complex feature interactions and managing noise in large datasets. We address this challenge by developing an integrated framework that combines Oblique Random Forests (ORFs) with a novel, permutation-based feature importance testing algorithm. ORFs extend traditional random forests by employing oblique decision boundaries through linear combinations of features, thereby capturing intricate interactions inherent in neuroimaging data. Our feature importance testing method, NEOFIT, rigorously quantifies the significance of each feature by generating null distributions and corrected p -values. We first validate our approach using simulated datasets, establishing its robustness and scalability under controlled conditions. We then apply our method to classify sex from both voxel-wise structural MRI and cortical thickness data in humans and macaques, facilitating direct cross-species comparisons. ORFs achieves AUC > 0.80 on human data, and >0.70 on macaque data, while NEOFIT identifies statistically significant features aligned with sex-dimorphic neuroanatomy. Our results demonstrate that the proposed framework not only enhances classification performance but also provides clear, interpretable insights into the neuroanatomical features that distinguish sexes. These methodological advancements pave the way for improved diagnostic tools and contribute to a deeper understanding of the evolutionary basis of sex differences in brain structure.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningBrainNeuroimagingAnimalsFemaleHumansMaleMagnetic Resonance ImagingRandom ForestClassification AlgorithmsAlgorithmsSex CharacteristicsMacaca

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, United States of America.
  • Department of Psychology, Stanford University, Stanford, California, United States of America.
  • Center for the Developing Brain, Child Mind Institute, New York, New York, United States of America.
  • Nathan S. Kline Institute for Psychiatric Research, Orangeburg, New York, United States of America.
  • Department of Biomedical Engineering, Institute for Computational Medicine, Kavli Neuroscience Discovery Institute, Johns Hopkins University, Baltimore, Maryland, United States of America.

ORCID-Profile: Tingshan Liu, Jayanta Dey, Beiya Xu

Förderung

  • National Institutes of Health
  • National Science Foundation

Zitieren

APA

Liu, T., Dey, J., Xu, B., Bridgeford, E. W., Alldritt, S., Nenning, K. H., Byeon, K., Xu, T., & Vogelstein, J. T. (2026). Statistically valid explainable black-box machine learning: applications in sex classification across species using brain imaging. PLOS One, 21(4), e0346575. https://doi.org/10.1371/journal.pone.0346575

Vancouver

Liu T, Dey J, Xu B, Bridgeford EW, Alldritt S, Nenning KH, et al. Statistically valid explainable black-box machine learning: applications in sex classification across species using brain imaging. PLOS One. 2026;21(4):e0346575. doi:10.1371/journal.pone.0346575

BibTeX
@article{Liu2026,
  author = {Liu, Tingshan and Dey, Jayanta and Xu, Beiya and Bridgeford, Eric W and Alldritt, Samuel and Nenning, Karl-Heinz and Byeon, Kyoungseob and Xu, Ting and Vogelstein, Joshua T},
  title = {Statistically valid explainable black-box machine learning: applications in sex classification across species using brain imaging},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {4},
  pages = {e0346575},
  doi = {10.1371/journal.pone.0346575}
}
Kostenlos starten →