Introduction: Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia.Methods: We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases.Results: A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort.Discussion: The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice.Highlights: There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias
Resting-state functional magnetic resonance imaging (rs-fMRI) has been successfully employed to understand the organisation of the human brain. Typically, the brain is parcellated into regions of interest (ROIs) and modelled as a graph where each ROI represents a node and association measures between ROI-specific blood-oxygen-level-dependent (BOLD) time series are edges. Recently, graph neural networks (GNNs) have seen a surge in popularity due to their success in modelling unstructured relational data. The latest developments with GNNs, however, have not yet been fully exploited for the analysis of rs-fMRI data, particularly with regards to its spatio-temporal dynamics. In this paper, we present a novel deep neural network architecture which combines both GNNs and temporal convolutional networks (TCNs) in order to learn from both the spatial and temporal components of rs-fMRI data in an end-to-end fashion. In particular, this corresponds to intra-feature learning (i.e., learning temporal dynamics with TCNs) as well as inter-feature learning (i.e., leveraging interactions between ROI-wise dynamics with GNNs). We evaluate our model with an ablation study using 35,159 samples from the UK Biobank rs-fMRI database, as well as in the smaller Human Connectome Project (HCP) dataset, both in a unimodal and in a multimodal fashion. We also demonstrate that out architecture contains explainability-related features which easily map to realistic neurobiological insights. We suggest that this model could lay the groundwork for future deep learning architectures focused on leveraging the inherently and inextricably spatio-temporal nature of rs-fMRI data.
The genetic component of many common traits is associated with the gene expression and several variants act as expression quantitative loci, regulating the gene expression in a tissue specific manner. In this work, we applied tissue-specific cis-eQTL gene expression prediction models on the genotype of 808 samples including controls, subjects with mild cognitive impairment, and patients with Alzheimer's Disease. We then dissected the imputed transcriptomic profiles by means of different unsupervised and supervised machine learning approaches to identify potential biological associations. Our analysis suggests that unsupervised and supervised methods can provide complementary information, which can be integrated for a better characterization of the underlying biological system. In particular, a variational autoencoder representation of the transcriptomic profiles, followed by a support vector machine classification, has been used for tissue-specific gene prioritizations. Interestingly, the achieved gene prioritizations can be efficiently integrated as a feature selection step for improving the accuracy of deep learning classifier networks. The identified gene-tissue information suggests a potential role for inflammatory and regulatory processes in gut-brain axis related tissues. In line with the expected low heritability that can be apportioned to eQTL variants, we were able to achieve only relatively low prediction capability with deep learning classification models. However, our analysis revealed that the classification power strongly depends on the network structure, with recurrent neural networks being the best performing network class. Interestingly, cross-tissue analysis suggests a potentially greater role of models trained in brain tissues also by considering dementia-related endophenotypes. Overall, the present analysis suggests that the combination of supervised and unsupervised machine learning techniques can be used for the evaluation of high dimensional omics data.
Background: Identifying prediagnostic neurodegenerative disease is a critical issue in neurodegenerative disease research, and Alzheimer’s disease (AD) in particular, to identify populations suitable for preventive and early disease-modifying trials. Evidence from genetic and other studies suggests the neurodegeneration of Alzheimer’s disease measured by brain atrophy starts many years before diagnosis, but it is unclear whether these changes can be used to reliably detect prediagnostic sporadic disease. Methods: We trained a Bayesian machine learning neural network model to generate a neuroimaging phenotype and AD score representing the probability of AD using structural MRI data in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) Cohort (cut-off 0.5, AUC 0.92, PPV 0.90, NPV 0.93). We go on to validate the model in an independent real-world dataset of the National Alzheimer’s Coordinating Centre (AUC 0.74, PPV 0.65, NPV 0.80) and demonstrate the correlation of the AD-score with cognitive scores in those with an AD-score above 0.5. We then apply the model to a healthy population in the UK Biobank study to identify a cohort at risk for Alzheimer’s disease. Results: We show that the cohort with a neuroimaging Alzheimer’s phenotype has a cognitive profile in keeping with Alzheimer’s disease, with strong evidence for poorer fluid intelligence, and some evidence of poorer numeric memory, reaction time, working memory, and prospective memory. We found some evidence in the AD-score positive cohort for modifiable risk factors of hypertension and smoking. Conclusions: This approach demonstrates the feasibility of using AI methods to identify a potentially prediagnostic population at high risk for developing sporadic Alzheimer’s disease.
A question of fundamental biological significance is to what extent the expression of a subset of genes can be used to recover the full transcriptome, with important implications for biological discovery and clinical application. To address this challenge, we propose two novel deep learning methods, PMI and GAIN-GTEx, for gene expression imputation. In order to increase the applicability of our approach, we leverage data from GTEx v8, a reference resource that has generated a comprehensive collection of transcriptomes from a diverse set of human tissues. We show that our approaches compare favorably to several standard and state-of-the-art imputation methods in terms of predictive performance and runtime in two case studies and two imputation scenarios. In comparison conducted on the protein-coding genes, PMI attains the highest performance in inductive imputation whereas GAIN-GTEx outperforms the other methods in in-place imputation. Furthermore, our results indicate strong generalization on RNA-Seq data from 3 cancer types across varying levels of missingness. Our work can facilitate a cost-effective integration of large-scale RNA biorepositories into genomic studies of disease, with high applicability across diverse tissue types.
27 May 2021 in npj Systems Biology and Applications
Here, we performed a comprehensive intra-tissue and inter-tissue multilayer network analysis of the human transcriptome. We generated an atlas of communities in gene co-expression networks in 49 tissues (GTEx v8), evaluated their tissue specificity, and investigated their methodological implications. UMAP embeddings of gene expression from the communities (representing nearly 18% of all genes) robustly identified biologically-meaningful clusters. Notably, new gene expression data can be embedded into our algorithmically derived models to accelerate discoveries in high-dimensional molecular datasets and downstream diagnostic or prognostic applications. We demonstrate the generalisability of our approach through systematic testing in external genomic and transcriptomic datasets. Methodologically, prioritisation of the communities in a transcriptome-wide association study of the biomarker C-reactive protein (CRP) in 361,194 individuals in the UK Biobank identified genetically-determined expression changes associated with CRP and led to considerably improved performance. Furthermore, a deep learning framework applied to the communities in nearly 11,000 tumors profiled by The Cancer Genome Atlas across 33 different cancer types learned biologically-meaningful latent spaces, representing metastasis (p < 2.2 × 10−16) and stemness (p < 2.2 × 10−16). Our study provides a rich genomic resource to catalyse research into inter-tissue regulatory mechanisms, and their downstream consequences on human disease.