• Home
  • Search
  • Multilayer meta-matching: translating phenotypic prediction models from multiple datasets to small data
  • Open Access IconOpen Access
  • Cite Icon3
  • https://doi.org/10.1101/2023.12.05.569848Copy DOI Icon

Multilayer meta-matching: translating phenotypic prediction models from multiple datasets to small data

  • Dec 7, 2023
  • bioRxiv
  • Pansheng Chen +13 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Resting-state functional connectivity (RSFC) is widely used to predict phenotypic traits in individuals. Large sample sizes can significantly improve prediction accuracies. However, for studies of certain clinical populations or focused neuroscience inquiries, small-scale datasets often remain a necessity. We have previously proposed a “meta-matching” approach to translate prediction models from large datasets to predict new phenotypes in small datasets. We demonstrated large improvement of meta-matching over classical kernel ridge regression (KRR) when translating models from a single source dataset (UK Biobank) to the Human Connectome Project Young Adults (HCP-YA) dataset. In the current study, we propose two meta-matching variants (“meta-matching with dataset stacking” and “multilayer meta-matching”) to translate models from multiple source datasets across disparate sample sizes to predict new phenotypes in small target datasets. We evaluate both approaches by translating models trained from five source datasets (with sample sizes ranging from 862 participants to 36,834 participants) to predict phenotypes in the HCP-YA and HCP-Aging datasets. We find that multilayer meta-matching modestly outperforms meta-matching with dataset stacking. Both meta-matching variants perform better than the original “meta-matching with stacking” approach trained only on the UK Biobank. All meta-matching variants outperform classical KRR and transfer learning by a large margin. In fact, KRR is better than classical transfer learning when less than 50 participants are available for finetuning, suggesting the difficulty of classical transfer learning in the very small sample regime. The multilayer meta-matching model is publicly available at GITHUB_LINK.

Similar Papers
  • Discussion
  • Citations3

Prediction models: stepwise development and simultaneous validation is a step back

  • Aug 01, 2021
  • Journal of Clinical Epidemiology
  • Georg Heinze +4
  • PDF
  • Research Article
  • Citations5

Spectrally-truncated kernel ridge regression and its free lunch

  • Jan 01, 2021
  • Electronic Journal of Statistics
  • Arash A. Amini
  • Research Article
  • Citations46

Generalization error of random feature and kernel methods: Hypercontractivity and kernel matrix concentration

  • Jul 01, 2022
  • Applied and Computational Harmonic Analysis
  • Song Mei +2
  • Research Article
  • Citations9

Comparative analysis of deep convolution neural network models on small scale datasets

  • Nov 13, 2022
  • Optik
  • C.R Edwin Selva Rex +2
  • Front Matter
  • Citations5

Some Thoughts About Data Type, Distribution, and Statistical Significance

  • Nov 01, 2006
  • The Journal of Foot and Ankle Surgery
  • D Scot Malay
  • Preprint Article

Determination of statistical steady states of thermal convection aided by machine learning predictions

  • Jul 03, 2024
  • Siddhant Agarwal +4
  • Conference Article
  • Citations18

Similarity of Speech Emotion in Different Languages Revealed by a Neural Network with Attention

  • Feb 01, 2020
  • Changzeng Fu +4
  • Research Article
  • Citations7

Augmenting small biomedical datasets using generative AI methods based on self-organizing neural networks

  • Nov 22, 2024
  • Briefings in Bioinformatics
  • Alfred Ultsch +1
  • PDF
  • Conference Article
  • Citations147

MAVEN: A Massive General Domain Event Detection Dataset

  • Jan 01, 2020
  • Xiaozhi Wang +9
  • Research Article
  • Citations10

Outlier detection in multimodal MRI identifies rare individual phenotypes among more than 15,000 brains.

  • Dec 26, 2021
  • Human brain mapping
  • Zhiwei Ma +4
  • Research Article
  • Citations20

Altered brain entropy and functional connectivity patterns in generalized anxiety disorder patients

  • Mar 26, 2023
  • Journal of Affective Disorders
  • Siyu Fan +8
  • Conference Article

Classification Using Transfer Learning and SWIN-MAE Model on Small-Scale Datasets

  • Apr 25, 2025
  • Honglin Hui +1
  • PDF
  • Research Article
  • Citations6

Deep learning image analysis for filamentous fungi taxonomic classification: Dealing with small datasets with class imbalance and hierarchical grouping

  • Jan 11, 2024
  • Biology Methods & Protocols
  • Stefan Stiller +4
  • PDF
  • Research Article
  • Citations5

Multi-EPL: Accurate multi-source domain adaptation

  • Aug 05, 2021
  • PLoS ONE
  • Seongmin Lee +2
  • PDF
  • Research Article
  • Citations1589

Machine learning algorithm validation with a limited sample size.

  • Nov 07, 2019
  • PLOS ONE
  • Andrius Vabalas +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.