% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Chen:1019822,
      author       = {Chen, Pansheng and An, Lijun and Wulan, Naren and Zhang,
                      Chen and Zhang, Shaoshi and Ooi, Leon Qi Rong and Kong, Ru
                      and Chen, Jianzhong and Wu, Jianxiao and Chopra, Sidhant and
                      Bzdok, Danilo and Eickhoff, Simon B and Holmes, Avram J and
                      Yeo, B. T. Thomas},
      title        = {{M}ultilayer meta-matching: translating phenotypic
                      prediction models from multiple datasets to small data},
      reportid     = {FZJ-2023-05653},
      year         = {2024},
      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 $GITHUB_LINK.$},
      cin          = {INM-7},
      cid          = {I:(DE-Juel1)INM-7-20090406},
      pnm          = {5251 - Multilevel Brain Organization and Variability
                      (POF4-525)},
      pid          = {G:(DE-HGF)POF4-5251},
      typ          = {PUB:(DE-HGF)25},
      doi          = {10.1101/2023.12.05.569848},
      url          = {https://juser.fz-juelich.de/record/1019822},
}