There is significant interest in using brain imaging data to predict non-brain-imaging phenotypes in individual participants. However, most prediction studies are underpowered, relying on less than a few hundred participants, leading to low reliability and inflated prediction performance. Yet, small sample sizes are unavoidable when studying clinical populations or addressing focused neuroscience questions. Here, we propose a simple framework -"meta-matching" -to translate predictive models from large-scale datasets to new unseen non-brain-imaging phenotypes in boutique studies. The key observation is that many large-scale datasets collect a wide range inter-correlated phenotypic measures.Therefore, a unique phenotype from a boutique study likely correlates with (but is not the same as) some phenotypes in some large-scale datasets. Meta-matching exploits these correlations to boost prediction in the boutique study. We applied meta-matching to the problem of predicting non-brain-imaging phenotypes using resting-state functional connectivity (RSFC). Using the UK Biobank (N = 36,848), we demonstrated that metamatching can boost the prediction of new phenotypes in small independent datasets by 100% to 400% in many scenarios. When considering relative prediction performance, metamatching significantly improved phenotypic prediction even in samples with 10 participants.When considering absolute prediction performance, meta-matching significantly improved phenotypic prediction when there were least 50 participants. With a growing number of largescale population-level datasets collecting an increasing number of phenotypic measures, our results represent a lower bound on the potential of meta-matching to elevate small-scale boutique studies..

No abstract

A primary aim of precision psychiatry is the establishment of predictive models linking individual differences in brain functioning with clinical symptoms. In particular, cognitive impairments are transdiagnostic, treatment resistant, and contribute to poor clinical outcomes. Recent work suggests thousands of participants may be necessary for the accurate and reliable prediction of cognition, calling into question the utility of most patient collection efforts. Here, using a transfer-learning framework, we train a model on functional imaging data from the UK Biobank (n=36,848) to predict cognitive functioning in three transdiagnostic patient samples (n=101-224). The model generalizes across datasets, and brain features driving predictions are consistent between populations, with decreased functional connectivity within transmodal cortex and increased connectivity between unimodal and transmodal regions reflecting a transdiagnostic predictor of cognition. This work establishes that predictive models derived in large population-level datasets can be exploited to boost the prediction of cognitive function across clinical collection efforts.

No abstract

There is significant interest in pooling magnetic resonance image (MRI) data from multiple datasets to enable mega-analysis. Harmonization is typically performed to reduce heterogeneity when pooling MRI data across datasets. Most MRI harmonization algorithms do not explicitly consider downstream application performance during harmonization. However, the choice of downstream application might influence what might be considered as study-specific confounds. Therefore, ignoring downstream applications during harmonization might potentially limit downstream performance. Here we propose a goal-specific harmonization framework that utilizes downstream application performance to regularize the harmonization procedure. Our framework can be integrated with a wide variety of harmonization models based on deep neural networks, such as the recently proposed conditional variational autoencoder (cVAE) harmonization model. Three datasets from three different continents with a total of 2787 participants and 10085 anatomical T1 scans were used for evaluation. We found that cVAE removed more dataset differences than the widely used ComBat model, but at the expense of removing desirable biological information as measured by downstream prediction of mini mental state examination (MMSE) scores and clinical diagnoses. On the other hand, our goal-specific cVAE (gcVAE) was able to remove as much dataset differences as cVAE, while improving downstream cross-sectional prediction of MMSE scores and clinical diagnoses.