Graph neural networks (GNNs) have gained significant attention in disease prediction where the latent embeddings of patients are modeled as nodes and the similarities among patients are represented through edges. The graph structure, which determines how information is aggregated and propagated, plays a crucial role in graph learning. Recent approaches typically create graphs based on patients\' latent embeddings, which may not accurately reflect their real-world closeness. Our analysis reveals that raw data, such as demographic attributes and laboratory results, offers a wealth of information for assessing patient similarities and can serve as a compensatory measure for graphs constructed exclusively from latent embeddings. In this study, we first construct adaptive graphs from both latent representations and raw data respectively, and then merge these graphs via weighted summation. Given that the graphs may contain extraneous and noisy connections, we apply degree-sensitive edge pruning and kNN sparsification techniques to selectively sparsify and prune these edges. We conducted intensive experiments on two diagnostic prediction datasets, and the results demonstrate that our proposed method surpasses current state-of-the-art techniques.

BACKGROUND: Early diagnosis in oral cancer is essential to reduce both morbidity and mortality. This study explores the use of uncertainty estimation in deep learning for early oral cancer diagnosis.
METHODS: We develop a Bayesian deep learning model termed \'Probabilistic HRNet\', which utilizes the ensemble MC dropout method on HRNet. Additionally, two oral lesion datasets with distinct distributions are created. We conduct a retrospective study to assess the predictive performance and uncertainty of Probabilistic HRNet across these datasets.
RESULTS: Probabilistic HRNet performs optimally on the In-domain test set, achieving an F1 score of 95.3% and an AUC of 96.9% by excluding the top 30% high-uncertainty samples. For evaluations on the Domain-shift test set, the results show an F1 score of 64.9% and an AUC of 80.3%. After excluding 30% of the high-uncertainty samples, these metrics improve to an F1 score of 74.4% and an AUC of 85.6%.
CONCLUSIONS: Redirecting samples with high uncertainty to experts for subsequent diagnosis significantly decreases the rates of misdiagnosis, which highlights that uncertainty estimation is vital to ensure safe decision making for computer-aided early oral cancer diagnosis.

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.

BACKGROUND: Integrating multi-omics data is emerging as a critical approach in enhancing our understanding of complex diseases. Innovative computational methods capable of managing high-dimensional and heterogeneous datasets are required to unlock the full potential of such rich and diverse data.
METHODS: We propose a Multi-Omics integration framework with auxiliary Classifiers-enhanced AuToencoders (MOCAT) to utilize intra- and inter-omics information comprehensively. Additionally, attention mechanisms with confidence learning are incorporated for enhanced feature representation and trustworthy prediction.
RESULTS: Extensive experiments were conducted on four benchmark datasets to evaluate the effectiveness of our proposed model, including BRCA, ROSMAP, LGG, and KIPAN. Our model significantly improved most evaluation measurements and consistently surpassed the state-of-the-art methods. Ablation studies showed that the auxiliary classifiers significantly boosted classification accuracy in the ROSMAP and LGG datasets. Moreover, the attention mechanisms and confidence evaluation block contributed to improvements in the predictive accuracy and generalizability of our model.
CONCLUSIONS: The proposed framework exhibits superior performance in disease classification and biomarker discovery, establishing itself as a robust and versatile tool for analyzing multi-layer biological data. This study highlights the significance of elaborated designed deep learning methodologies in dissecting complex disease phenotypes and improving the accuracy of disease predictions.

The prediction of disease can facilitate early intervention, comprehensive diagnosis and treatment, thereby benefiting healthcare and reducing medical costs. While single class and multi-class learning methods have been applied for disease prediction, they are inadequate in distinguishing between primary and secondary diagnoses, which is crucial for treatments. In this paper, label distribution is suggested to describe the diagnosis, which assigns the description degree to quantify the diagnosis. Additionally, a novel hierarchical label distribution learning (HLDL) model is proposed to make fine-grained predictions based on the hierarchical classification of diseases, taking into account the relationship among diseases. The experimental results on real-world datasets demonstrate that the HLDL model outperforms the baselines with statistical significance.

BACKGROUND: Muscle weakness is a prominent feature of Parkinson\'s disease, but whether the occurrence of this deficit in healthy adults is associated with subsequent PD diagnosis remains unclear.
OBJECTIVE: This study sought to examine the relationship between muscle strength, represented by grip strength and walking pace, and the risk of incident PD.
METHODS: A total of 422,531 participants from the UK biobank were included in this study. Longitudinal associations of grip strength and walking pace with the risk of incident PD were investigated by Cox proportional hazard models adjusting for several well-established risk factors. Subgroup and sensitivity analyses were also conducted for further validation.
RESULTS: After a median follow-up of 9.23 years, 2,118 (0.5%) individuals developed incident PD. For per 5 kg increment of absolute grip strength, there was a significant 10.2% reduction in the risk of incident PD (HR = 0.898, 95% CI [0.872-0.924], P < 0.001). Similarly, per 0.05 kg/kg increment of relative grip strength was related to a 9.2% reduced risk of incident PD (HR = 0.908, 95% CI [0.887-0.929], P < 0.001). Notably, the associations remained consistent when grip strength was calculated as quintiles. Moreover, participants with a slower walking pace demonstrated an elevated risk of incident PD (HR = 1.231, 95%CI [1.075-1.409], P = 0.003). Subgroup and sensitivity analyses further validated the robustness of the observed associations.
CONCLUSIONS: Our findings showed a negative association of grip strength and walking pace with the risk of incident PD independent of important confounding factors. These results hold potential implications for the early screening of people at high-risk of PD.

Background: Increasing studies in the last decade have led to the widespread understanding that C4d, a split product of complement component 4 (C4), is a potential biomarker for systemic lupus erythematosus (SLE) and lupus nephritis (LN).Purpose: The aim of this review is to summarize the highlights of studies investigating the use of C4d as a biomarker for diagnosing and monitoring SLE and LN patients.Data collection: we searched PubMed/Medline and Wanfang databases using the terms \"C4d and systemic lupus erythematosus\", \"C4d and lupus nephritis\", and \"Complement C4d\".Results: The deposition of C4d on circulating blood cells has been shown in several clinical studies to be a potential diagnostic marker that can be used to monitor patients with SLE. In addition, C4d deposits on circulating blood cells may be a helpful diagnostic marker for LN, one of the most severe complications of SLE. Meanwhile, studies utilizing renal biopsy specimens have indicated that C4d deposition in the renal peritubular capillaries of LN patients may predict more severe LN or a worse patient prognosis. Generally, a high plasma C4d level and a high plasma C4d/C4 ratio may also be promising indicators that can be used to monitor patients with SLE and LN.Conclusions: C4d detection may be a novel strategy for further clinical prediction and therapy.

Parkinson\'s disease (PD) is one of the most common neuro-degenerative diseases characterized by α-synuclein accumulation and degeneration of dopaminergic neurons. Employing genome-wide sequencing, we identified a polymorphic USP8 allele (USP8D442G) significantly enriched in Chinese PD patients. To test the involvement of this polymorphism in PD pathogenesis, we derived dopaminergic neurons (DAn) from human-induced pluripotent stem cells (hiPSCs) reprogrammed from fibroblasts of PD patients harboring USP8D442G allele and their healthy siblings. In addition, we knock-in D442G polymorphic site into the endogenous USP8 gene of human embryonic stem cells (hESCs) and derived DAn from these knock-in hESCs to explore their cellular phenotypes and molecular mechanism. We found that expression of USP8D442G in DAn induces the accumulation and abnormal subcellular localization of α-Synuclein (α-Syn). Mechanistically, we demonstrate that D442G polymorphism enhances the interaction between α-Syn and USP8 and thus increases the K63-specific deubiquitination and stability of α-Syn . We discover a pathogenic polymorphism for PD that represent a promising therapeutic and diagnostic target for PD.

Patient representation learning aims to encode meaningful information about the patient\'s Electronic Health Records (EHR) in the form of a mathematical representation. Recent advances in deep learning have empowered Patient representation learning methods with greater representational power, allowing the learned representations to significantly improve the performance of disease prediction models. However, the inherent shortcomings of deep learning models, such as the need for massive amounts of labeled data and inexplicability, limit the performance of deep learning-based Patient representation learning methods to further improvements. In particular, learning robust patient representations is challenging when patient data is missing or insufficient. Although data augmentation techniques can tackle this deficiency, the complex data processing further weakens the inexplicability of patient representation learning models. To address the above challenges, this paper proposes an Explainable and Augmented Patient Representation Learning for disease prediction (EAPR). EAPR utilizes data augmentation controlled by confidence interval to enhance patient representation in the presence of limited patient data. Moreover, EAPR proposes to use two-stage gradient backpropagation to address the problem of unexplainable patient representation learning models due to the complex data enhancement process. The experimental results on real clinical data validate the effectiveness and explainability of the proposed approach.

The gut microbiome has been regarded as one of the fundamental determinants regulating human health, and multi-omics data profiling has been increasingly utilized to bolster the deep understanding of this complex system. However, stemming from cost or other constraints, the integration of multi-omics often suffers from incomplete views, which poses a great challenge for the comprehensive analysis. In this work, a novel deep model named Incomplete Multi-Omics Variational Neural Networks (IMOVNN) is proposed for incomplete data integration, disease prediction application and biomarker identification. Benefiting from the information bottleneck and the marginal-to-joint distribution integration mechanism, the IMOVNN can learn the marginal latent representation of each individual omics and the joint latent representation for better disease prediction. Moreover, owing to the feature-selective layer predicated upon the concrete distribution, the model is interpretable and can identify the most relevant features. Experiments on inflammatory bowel disease multi-omics datasets demonstrate that our method outperforms several state-of-the-art methods for disease prediction. In addition, IMOVNN has identified significant biomarkers from multi-omics data sources.