Disease Prediction with Edge-Variational Graph Convolutional Networks

A novel interactive deep cascade spectral graph convolutional network with multi-relational graphs for disease prediction

Graph neural networks (GNNs) have recently grown in popularity for disease prediction. Existing GNN-based methods primarily build the graph topological structure around a single modality and combine it with other modalities to acquire feature representations of acquisitions. The complicated relationship in each modality, however, may not be well highlighted due to its specificity. Further, relatively shallow networks restrict adequate extraction of high-level features, affecting disease prediction performance. Accordingly, this paper develops a new interactive deep cascade spectral graph convolutional network with multi-relational graphs (IDCGN) for disease prediction tasks. Its crucial points lie in constructing multiple relational graphs and dual cascade spectral graph convolution branches with interaction (DCSGBI). Specifically, the former designs a pairwise imaging-based edge generator and a pairwise non-imaging-based edge generator from different modalities by devising two learnable networks, which adaptively capture graph structures and provide various views of the same acquisition to aid in disease diagnosis. Again, DCSGBI is established to enrich high-level semantic information and low-level details of disease data. It devises a cascade spectral graph convolution operator for each branch and incorporates the interaction strategy between different branches into the network, successfully forming a deep model and capturing complementary information from diverse branches. In this manner, more favorable and sufficient features are learned for a reliable diagnosis. Experiments on several disease datasets reveal that IDCGN exceeds state-of-the-art models and achieves promising results.

Brain-region specific autism prediction from electroencephalogram signals using graph convolution neural network

BACKGROUND

Brain variations are responsible for developmental impairments, including autism spectrum disorder (ASD). EEG signals efficiently detect neurological conditions by revealing crucial information about brain function abnormalities.

OBJECTIVE

This study aims to utilize EEG data collected from both autistic and typically developing children to investigate the potential of a Graph Convolutional Neural Network (GCNN) in predicting ASD based on neurological abnormalities revealed through EEG signals.

METHODS

In this study, EEG data were gathered from eight autistic children and eight typically developing children diagnosed using the Childhood Autism Rating Scale at the Central Institute of Psychiatry, Ranchi. EEG recording was done using a HydroCel GSN with 257 channels, and 71 channels with 10-10 international equivalents were utilized. Electrodes were divided into 12 brain regions. A GCNN was introduced for ASD prediction, preceded by autoregressive and spectral feature extraction.

RESULTS

The anterior-frontal brain region, crucial for cognitive functions like emotion, memory, and social interaction, proved most predictive of ASD, achieving 87.07% accuracy. This underscores the suitability of the GCNN method for EEG-based ASD detection.

CONCLUSION

The detailed dataset collected enhances understanding of the neurological basis of ASD, benefiting healthcare practitioners involved in ASD diagnosis.

Uncertainty-aware deep learning for trustworthy prediction of long-term outcome after endovascular thrombectomy

Acute ischemic stroke (AIS) is a leading global cause of mortality and morbidity. Improving long-term outcome predictions after thrombectomy can enhance treatment quality by supporting clinical decision-making. With the advent of interpretable deep learning methods in recent years, it is now possible to develop trustworthy, high-performing prediction models. This study introduces an uncertainty-aware, graph deep learning model that predicts endovascular thrombectomy outcomes using clinical features and imaging biomarkers. The model targets long-term functional outcomes, defined by the three-month modified Rankin Score (mRS), and mortality rates. A sample of 220 AIS patients in the anterior circulation who underwent endovascular thrombectomy (EVT) was included, with 81 (37%) demonstrating good outcomes (mRS ≤ 2). The performance of the different algorithms evaluated was comparable, with the maximum validation under the curve (AUC) reaching 0.87 using graph convolutional networks (GCN) for mRS prediction and 0.86 using fully connected networks (FCN) for mortality prediction. Moderate performance was obtained at admission (AUC of 0.76 using GCN), which improved to 0.84 post-thrombectomy and to 0.89 a day after stroke. Reliable uncertainty prediction of the model could be demonstrated.

Re-tear after arthroscopic rotator cuff repair can be predicted using deep learning algorithm

The application of artificial intelligence technology in the medical field has become increasingly prevalent, yet there remains significant room for exploration in its deep implementation. Within the field of orthopedics, which integrates closely with AI due to its extensive data requirements, rotator cuff injuries are a commonly encountered condition in joint motion. One of the most severe complications following rotator cuff repair surgery is the recurrence of tears, which has a significant impact on both patients and healthcare professionals. To address this issue, we utilized the innovative EV-GCN algorithm to train a predictive model. We collected medical records of 1,631 patients who underwent rotator cuff repair surgery at a single center over a span of 5 years. In the end, our model successfully predicted postoperative re-tear before the surgery using 62 preoperative variables with an accuracy of 96.93%, and achieved an accuracy of 79.55% on an independent external dataset of 518 cases from other centers. This model outperforms human doctors in predicting outcomes with high accuracy. Through this methodology and research, our aim is to utilize preoperative prediction models to assist in making informed medical decisions during and after surgery, leading to improved treatment effectiveness. This research method and strategy can be applied to other medical fields, and the research findings can assist in making healthcare decisions.

Exploring Alzheimer's disease: a comprehensive brain connectome-based survey

Dementia is an escalating global health challenge, with Alzheimer's disease (AD) at its forefront. Substantial evidence highlights the accumulation of AD-related pathological proteins in specific brain regions and their subsequent dissemination throughout the broader area along the brain network, leading to disruptions in both individual brain regions and their interconnections. Although a comprehensive understanding of the neurodegeneration-brain network link is lacking, it is undeniable that brain networks play a pivotal role in the development and progression of AD. To thoroughly elucidate the intricate network of elements and connections constituting the human brain, the concept of the brain connectome was introduced. Research based on the connectome holds immense potential for revealing the mechanisms underlying disease development, and it has become a prominent topic that has attracted the attention of numerous researchers. In this review, we aim to systematically summarize studies on brain networks within the context of AD, critically analyze the strengths and weaknesses of existing methodologies, and offer novel perspectives and insights, intending to serve as inspiration for future research.

CylinGCN: Cylindrical structures segmentation in 3D biomedical optical imaging by a contour-based graph convolutional network

Cylindrical organs, e.g., blood vessels, airways, and intestines, are ubiquitous structures in biomedical optical imaging analysis. Image segmentation of these structures serves as a vital step in tissue physiology analysis. Traditional model-driven segmentation methods seek to fit the structure by constructing a corresponding topological geometry based on domain knowledge. Classification-based deep learning methods neglect the geometric features of the cylindrical structure and therefore cannot ensure the continuity of the segmentation surface. In this paper, by treating the cylindrical structures as a 3D graph, we introduce a novel contour-based graph neural network for 3D cylindrical structure segmentation in biomedical optical imaging. Our proposed method, which we named CylinGCN, adopts a novel learnable framework that extracts semantic features and complex topological relationships in the 3D volumetric data to achieve continuous and effective 3D segmentation. Our CylinGCN consists of a multiscale 3D semantic feature extractor for extracting inter-frame multiscale semantic features, and a residual graph convolutional network (GCN) contour generator that combines the semantic features and cylindrical topological priors to generate segmentation contours. We tested the CylinGCN framework on two types of optical tomographic imaging data, small animal whole body photoacoustic tomography (PAT) and endoscopic airway optical coherence tomography (OCT), and the results show that CylinGCN achieves state-of-the-art performance. Code will be released at https://github.com/lzc-smu/CylinGCN.git.

Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization

Despite their promise, circulating tumor DNA (ctDNA)-based assays for multi-cancer early detection face challenges in test performance, due mostly to the limited abundance of ctDNA and its inherent variability. To address these challenges, published assays to date demanded a very high-depth sequencing, resulting in an elevated price of test. Herein, we developed a multimodal assay called SPOT-MAS (screening for the presence of tumor by methylation and size) to simultaneously profile methylomics, fragmentomics, copy number, and end motifs in a single workflow using targeted and shallow genome-wide sequencing (~0.55×) of cell-free DNA. We applied SPOT-MAS to 738 non-metastatic patients with breast, colorectal, gastric, lung, and liver cancer, and 1550 healthy controls. We then employed machine learning to extract multiple cancer and tissue-specific signatures for detecting and locating cancer. SPOT-MAS successfully detected the five cancer types with a sensitivity of 72.4% at 97.0% specificity. The sensitivities for detecting early-stage cancers were 73.9% and 62.3% for stages I and II, respectively, increasing to 88.3% for non-metastatic stage IIIA. For tumor-of-origin, our assay achieved an accuracy of 0.7. Our study demonstrates comparable performance to other ctDNA-based assays while requiring significantly lower sequencing depth, making it economically feasible for population-wide screening.

A review of multi-omics data integration through deep learning approaches for disease diagnosis, prognosis, and treatment

Accurate diagnosis is the key to providing prompt and explicit treatment and disease management. The recognized biological method for the molecular diagnosis of infectious pathogens is polymerase chain reaction (PCR). Recently, deep learning approaches are playing a vital role in accurately identifying disease-related genes for diagnosis, prognosis, and treatment. The models reduce the time and cost used by wet-lab experimental procedures. Consequently, sophisticated computational approaches have been developed to facilitate the detection of cancer, a leading cause of death globally, and other complex diseases. In this review, we systematically evaluate the recent trends in multi-omics data analysis based on deep learning techniques and their application in disease prediction. We highlight the current challenges in the field and discuss how advances in deep learning methods and their optimization for application is vital in overcoming them. Ultimately, this review promotes the development of novel deep-learning methodologies for data integration, which is essential for disease detection and treatment.

Multi-model adaptive fusion-based graph network for Alzheimer's disease prediction

Alzheimer's disease (AD) is a common cognitive disorder. Recently, many computer-aided diagnostic techniques have been used for AD prediction utilizing deep learning technology, among which graph neural networks have received increasing attention owing to their ability to model sample relationships on large population graphs. Most of the existing graph-based methods predict diseases according to a single model, which makes it difficult to select an appropriate node embedding algorithm for a certain classification task. Moreover, integrating data from different patterns into a unified model to improve the quality of disease diagnosis remains a challenge. Hence, in this study, we aimed to develop a multi-model fusion framework for AD prediction. A spectral graph attention model was used to aggregate intra- and inter-cluster node embeddings of normal and diseased populations, whereafter, a bilinear aggregation model was applied as an auxiliary model to enhance the abnormality degree in different categories of populations, and finally, an adaptive fusion module was designed to dynamically fuse the results of both models and enhance AD prediction. Compared to other comparison methods, the model proposed in this study provides the best results.

DHDIP: An interpretable model for hypertension and hyperlipidemia prediction based on EMR data

BACKGROUND AND OBJECTIVE

Traditional hypertension and hyperlipidemia prediction models suffer from uneven modeling data sources, small sample sizes, and a lack of uniform standards for the index system, resulting in the model failing to fulfill clinical applications. To address this issue, this work will offer DHDIP, an interpretable hypertension and hyperlipidemia prediction model based on EMR data.

METHODS

First, we will select massive high-dimensional, unstructured EMR data as a unified modeling data source, and propose a pre-processing algorithm for EMR data to solve the problem that EMR data cannot be directly processed by machine learning algorithms. Second, a variety of mainstream models such as XGBoost, CatBoost, and RandomForest are selected for modeling, and the best adaptation algorithms are identified by performance comparison. Finally, the SHAP framework was introduced into the DHDIP model, thus identifying the main factors contributing to hypertension and hyperlipidemia, effectively enhancing the interpretability of the model.

RESULTS

The DHDIP model's MSE value is 0.0285, and its LOSS value is 0.0054, both of which are better than previous studies.

CONCLUSION

The model balances performance and interpretability. Multi-objective learning allows for a more thorough analysis and prediction of the condition, which not only lowers the cost of disease prediction but also aids physicians in clinical diagnosis. In addition, the datasets and source code are available from this link: https://github.com/Xiaoyao-Jia/DHDIP.