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

Area of Science:

• Neuroscience
• Computational Biology
• Data Science

Background:

• Resting-state functional connectivity (RSFC) is crucial for predicting individual phenotypic traits.
• Large datasets enhance prediction accuracy, but small datasets are often necessary for clinical or specific research.
• Previous meta-matching approaches showed promise in translating models from large to small datasets.

Conclusions:

• The proposed multilayer meta-matching approach effectively translates prediction models across datasets of varying sizes, particularly benefiting small target datasets.
• These advanced meta-matching techniques offer substantial improvements over traditional methods for phenotype prediction using RSFC.
• The multilayer meta-matching model is publicly available, facilitating further research in the field.