HCTMFS: A multi-modal feature selection framework with higher-order correlated topological manifold for ESRDaMCI

•A multi-modal feature selection framework with higher-order correlated topological manifold (HCTMFS) were proposed to classify ESRDaMCI patients and identify the discriminative brain regions. It constructed brain structural and functional networks with diffuse kurtosis imaging (DKI) and functional magnetic resonance imaging (fMRI) data, and extracted node efficiency and clustering coefficient from the brain networks to construct multi-modal feature matrices.•The topological relationship matrices were constructed to measure the lower-order topological correlation between features. Then the consensus matrices were learned to approximate the topological relationship matrices at different confidence levels and eliminate the noise influence of individual matrices. The higher-order topological correlation between features was explored by the laplacian matrix of the hypergraph, which was calculated through the consensus matrix, allowing for the achievement of multi-modal feature selection.•HCTMFS achieved an accuracy rate of 93.56 % for classifying ESRDaMCI patients and outperformed existing state-of-the-art methods in terms of sensitivity, specificity, and area under the curve. The research results could effectively reflect the functional neural degradation of ESRDaMCI and provide a reference value for the diagnosis of ESRDaMCI by selecting discriminative brain regions. The diagnosis of end-stage renal disease associated with mild cognitive impairment (ESRDaMCI) mainly relies on objective cognitive assessment, clinical observation, and neuro-psychological evaluation, while only adopting clinical tools often limits the diagnosis accuracy. We proposed a multi-modal feature selection framework with higher-order correlated topological manifold (HCTMFS) to classify ESRDaMCI patients and identify the discriminative brain regions. It constructed brain structural and functional networks with diffuse kurtosis imaging (DKI) and functional magnetic resonance imaging (fMRI) data, and extracted node efficiency and clustering coefficient from the brain networks to construct multi-modal feature matrices. The topological relationship matrices were constructed to measure the lower-order topological correlation between features. Then the consensus matrices were learned to approximate the topological relationship matrices at different confidence levels and eliminate the noise influence of individual matrices. The higher-order topological correlation between features was explored