Deep Learning-Based Feature Extraction with MRI Data in Neuroimaging Genetics for Alzheimer's Disease

Knowledge domains and emerging trends of Genome-wide association studies in Alzheimer's disease: A bibliometric analysis and visualization study from 2002 to 2022

OBJECTIVES

Alzheimer's disease (AD) is a neurodegenerative disorder characterized by a progressive decline in cognitive and behavioral function. Studies have shown that genetic factors are one of the main causes of AD risk. genome-wide association study (GWAS), as a novel and effective tool for studying the genetic risk of diseases, has attracted attention from researchers in recent years and a large number of studies have been conducted. This study aims to summarize the literature on GWAS in AD by bibliometric methods, analyze the current status, research hotspots and future trends in this field.

METHODS

We retrieved articles on GWAS in AD published between 2002 and 2022 from Web of Science. CiteSpace and VOSviewer software were applied to analyze the articles for the number of articles published, countries/regions and institutions of publication, authors and cited authors, highly cited literature, and research hotspots.

RESULTS

We retrieved a total of 2,751 articles. The United States had the highest number of publications in this field, and Columbia University was the institution with the most published articles. The identification of AD-related susceptibility genes and their effects on AD is one of the current research hotspots. Numerous risk genes have been identified, among which APOE, CLU, CD2AP, CD33, EPHA1, PICALM, CR1, ABCA7 and TREM2 are the current genes of interest. In addition, risk prediction for AD and research on other related diseases are also popular research directions in this field.

CONCLUSION

This study conducted a comprehensive analysis of GWAS in AD and identified the current research hotspots and research trends. In addition, we also pointed out the shortcomings of current research and suggested future research directions. This study can provide researchers with information about the knowledge structure and emerging trends in the field of GWAS in AD and provide guidance for future research.

Deep causal feature extraction and inference with neuroimaging genetic data

Alzheimer's disease (AD) is a severe public health issue in the world. Magnetic Resonance Imaging (MRI) offers a way to study brain differences between AD patients and healthy individuals through feature extraction and comparison. However, in most previous works, the extracted features were not aimed to be causal, hindering biological understanding and interpretation. In order to extract causal features, we propose using instrumental variable (IV) regression with genetic variants as IVs. Specifically, we propose Deep Feature Extraction via Instrumental Variable Regression (DeepFEIVR), which uses a nonlinear neural network to extract causal features from three-dimensional neuroimages to predict an outcome (eg, AD status in our application) while maintaining a linear relationship between the extracted features and IVs. DeepFEIVR not only can handle high dimensional individual-level data for model building, but also is applicable to GWAS summary data to test associations of the extracted features with the outcome in subsequent analysis. In addition, we propose an extension of DeepFEIVR, called DeepFEIVR-CA, for covariate adjustment (CA). We apply DeepFEIVR and DeepFEIVR-CA to the Alzheimer's Disease Neuroimaging Initiative (ADNI) individual-level data as training data for model building, then apply to the UK Biobank neuroimaging and the International Genomics of Alzheimer's Project (IGAP) AD GWAS summary data, showcasing how the extracted causal features are related to AD and various brain endophenotypes.