Ou Deng

Ou Deng, Shoji Nishimura, Atsushi Ogihara et al.

Retrieval-augmented generation (RAG) for biomedical knowledge faces a hierarchy-aware ontology grounding challenge: resources like HPO, DO, and MeSH use deep ``is-a" taxonomies, yet production stacks rely on Euclidean embeddings and ANN indexes. While hyperbolic embeddings suit hierarchical representation, they face two barriers: (i) lack of native vector database support, and (ii) risk of underperforming on entity-centric queries where hierarchy is irrelevant. We present HyEm, a lightweight retrieval layer integrating hyperbolic ontology embeddings into existing Euclidean ANN infrastructure. HyEm learns radius-controlled hyperbolic embeddings, stores origin log-mapped vectors in standard Euclidean databases for candidate retrieval, then applies exact hyperbolic reranking. A query-adaptive gate outputs continuous mixing weights, combining Euclidean semantic similarity with hyperbolic hierarchy distance at reranking time. Our bi-Lipschitz analysis under radius constraints provides practical guidance for ANN oversampling and dimensionality.Experiments on biomedical ontology subsets demonstrate HyEm preserves 94-98% of Euclidean baseline performance on entity-centric queries while substantially improving hierarchy-navigation and mixed-intent queries, maintaining indexability at moderate oversampling.

Ou Deng, Qun Jin

Addressing missing data in complex datasets including electronic health records (EHR) is critical for ensuring accurate analysis and decision-making in healthcare. This paper proposes dynamically adaptable structural equation modeling (SEM) using a self-attention method (SESA), an approach to data imputation in EHR. SESA innovates beyond traditional SEM-based methods by incorporating self-attention mechanisms, thereby enhancing model adaptability and accuracy across diverse EHR datasets. Such enhancement allows SESA to dynamically adjust and optimize imputation and overcome the limitations of static SEM frameworks. Our experimental analyses demonstrate the achievement of robust predictive SESA performance for effectively handling missing data in EHR. Moreover, the SESA architecture not only rectifies potential mis-specifications in SEM but also synergizes with causal discovery algorithms to refine its imputation logic based on underlying data structures. Such features highlight its capabilities and broadening applicational potential in EHR data analysis and beyond, marking a reasonable leap forward in the field of data imputation.

Ou Deng, Shoji Nishimura, Atsushi Ogihara et al.

This study proposes Evolutionary Causal Discovery (ECD) for causal discovery that tailors response variables, predictor variables, and corresponding operators to research datasets. Utilizing genetic programming for variable relationship parsing, the method proceeds with the Relative Impact Stratification (RIS) algorithm to assess the relative impact of predictor variables on the response variable, facilitating expression simplification and enhancing the interpretability of variable relationships. ECD proposes an expression tree to visualize the RIS results, offering a differentiated depiction of unknown causal relationships compared to conventional causal discovery. The ECD method represents an evolution and augmentation of existing causal discovery methods, providing an interpretable approach for analyzing variable relationships in complex systems, particularly in healthcare settings with Electronic Health Record (EHR) data. Experiments on both synthetic and real-world EHR datasets demonstrate the efficacy of ECD in uncovering patterns and mechanisms among variables, maintaining high accuracy and stability across different noise levels. On the real-world EHR dataset, ECD reveals the intricate relationships between the response variable and other predictive variables, aligning with the results of structural equation modeling and shapley additive explanations analyses.

Ou Deng, Ruichen Cong, Jianting Xu et al.

Symbolic regression promises readable equations but struggles to encode unit-aware thresholds and conditional logic. We propose logistic-gated operators (LGO) -- differentiable gates with learnable location and steepness -- embedded as typed primitives and mapped back to physical units for audit. Across two primary health datasets (ICU, NHANES), the hard-gate variant recovers clinically plausible cut-points: 71% (5/7) of assessed thresholds fall within 10% of guideline anchors and 100% within 20%, while using far fewer gates than the soft variant (ICU median 4.0 vs 10.0; NHANES 5.0 vs 12.5), and remaining within the competitive accuracy envelope of strong SR baselines. On predominantly smooth tasks, gates are pruned, preserving parsimony. The result is compact symbolic equations with explicit, unit-aware thresholds that can be audited against clinical anchors -- turning interpretability from a post-hoc explanation into a modeling constraint and equipping symbolic regression with a practical calculus for regime switching and governance-ready deployment.

Liying Chen, Ou Deng, Ting Fang et al.

Objective: Systemic lupus erythematosus (SLE) is a complex autoimmune disease characterized by unpredictable flares. This study aimed to develop a novel proteomics-based risk prediction model specifically for Asian SLE populations to enhance personalized disease management and early intervention. Methods: A longitudinal cohort study was conducted over 48 weeks, including 139 SLE patients monitored every 12 weeks. Patients were classified into flare (n = 53) and non-flare (n = 86) groups. Baseline plasma samples underwent data-independent acquisition (DIA) proteomics analysis, and phenome-wide Mendelian randomization (PheWAS) was performed to evaluate causal relationships between proteins and clinical predictors. Logistic regression (LR) and random forest (RF) models were used to integrate proteomic and clinical data for flare risk prediction. Results: Five proteins (SAA1, B4GALT5, GIT2, NAA15, and RPIA) were significantly associated with SLE Disease Activity Index-2K (SLEDAI-2K) scores and 1-year flare risk, implicating key pathways such as B-cell receptor signaling and platelet degranulation. SAA1 demonstrated causal effects on flare-related clinical markers, including hemoglobin and red blood cell counts. A combined model integrating clinical and proteomic data achieved the highest predictive accuracy (AUC = 0.769), surpassing individual models. SAA1 was highlighted as a priority biomarker for rapid flare discrimination. Conclusion: The integration of proteomic and clinical data significantly improves flare prediction in Asian SLE patients. The identification of key proteins and their causal relationships with flare-related clinical markers provides valuable insights for proactive SLE management and personalized therapeutic approaches.