Article

Challenges in Multi-Task Learning for fMRI-Based Diagnosis: Benefits for Psychiatric Conditions and CNVs Would Likely Require Thousands of Patients

2023-12-15

Abstract excerpt

<p>There is a growing interest in using machine learning (ML) models to perform automatic diagnosis of psychiatric conditions; however, generalising the prediction of ML models to completely independent data can lead to sharp decrease in performance. Patients with different psychiatric diagnoses have traditionally been studied independently, yet there is a growing recognition of neuroimaging signatures shared acro...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: fbb51112-df88-5644-952a-07790a810769
DOI: 10.31234/osf.io/srmx7

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Challenges in Multi-Task Learning for fMRI-Based Diagnosis: Benefits for Psychiatric Conditions and CNVs Would Likely Require Thousands of PatientsDOI 10.31234/osf.io/srmx7Read

Challenges in Multi-Task Learning for fMRI-Based Diagnosis: Benefits for Psychiatric Conditions and CNVs Would Likely Require Thousands of PatientsSemantic proximity Read

Identifying diagnosis-specific genotype-phenotype associations via joint multitask sparse canonical correlation analysis and classification.Semantic proximity Read

Performance reserves in brain-imaging-based phenotype prediction.Semantic proximity Read

Different scaling of linear models and deep learning in UKBiobank brain images versus machine-learning datasets.Semantic proximity Read

A Multimodal Foundation Model for Discovering Genetic Associations with Brain Imaging PhenotypesSemantic proximity Read

Identifying disease sensitive and quantitative trait-relevant biomarkers from multidimensional heterogeneous imaging genetics data via sparse multimodal multitask learning.Semantic proximity Read

Associating Multi-Modal Brain Imaging Phenotypes and Genetic Risk Factors via a Dirty Multi-Task Learning Method.Semantic proximity Read

Supervised Phenotype Discovery from Multimodal Brain ImagingSemantic proximity Read

Combining heterogeneous data sources for neuroimaging based diagnosis: re-weighting and selecting what is importantSemantic proximity Read

Supervised Phenotype Discovery from Multimodal Brain ImagingSemantic proximity Read

The Brain Imaging and Neurophysiology Database: BINDing multimodal neural data into a large-scale repositorySemantic proximity Read

Comparative Analysis of Machine Learning Algorithms for Multi-Syndrome Classification of Neurodegenerative SyndromesSemantic proximity Read