arXiv subjects

Zhandong Liu

Publications and source records attributed to Zhandong Liu.

14 recordsLinked to original sources

arXiv2026

Physics-Informed Deep Learning for False Ventricular Tachycardia Alarm Reduction in the ICU

False ventricular tachycardia (VT) alarms are a leading contributor to alarm fatigue in intensive care units. We propose a deep learning framework combining a 1D SE-ResNet with ICU-realistic data augmentations and a physics-informed auxiliary reconstruction task based on the three-element Windkessel hemodynamic model, implemented as a differentiable forward simulation. By requiring the network's latent representation to produce physiologically plausible arterial pressure waveforms, artifact-driven ECG patterns are penalized while true VT remains coherent across modalities. Evaluated on the VTaC benchmark under a strict real-time protocol (10-second pre-alarm window), our method achieves a 5-point Challenge Score improvement over prior state-of-the-art. Ablation studies confirm that the physics-informed objective is the primary performance driver, providing gains in accuracy, 2x label efficiency, and more localized and clinically meaningful ECG segments.

cs.LG↗

arXiv2026

Institution-Specific LLM Prompting Recovers PHI That De-identification Systems and Their Gold Standards Both Miss

Secondary use of electronic health records requires de-identification, yet existing systems miss \emph{institutionally situated} protected health information (PHI) such as hospital abbreviations, building names, and internal codes whose status is locally determined. We ask whether large language models (LLMs) with in-context learning (ICL) can close this gap and control the precision--recall trade-off. On 100 annotated pediatric oncology notes (5,322 PHI spans) from Texas Children's Hospital, we benchmarked eight LLMs against two purpose-built systems (Stanford TiDE, OpenMed PII) and two pattern-based baselines. Each LLM ran under three prompts of increasing specificity: (1) a HIPAA-aligned baseline, (2) baseline plus the institutional PHI categories it missed, and (3) prompt 2 plus instructions against over-redacting clinical content. We then compared 14~multi-agent and ensemble configurations against the best single prompt, with recall the primary safety metric. LLMs outperformed the purpose-built systems (best F1=0.918$\pm$0.001 vs.\ TiDE 0.779), with advantages concentrated in contextual categories. Naming the missed categories recovered 79\% (48/61) of them, and discouraging over-redaction restored precision. No agentic architecture beat calibrated single-pass prompting (F1 0.906--0.907), but LLM outputs surfaced 414~candidate annotation gaps; re-annotation confirmed 227~PHI spans, against which the final prompt reached recall=0.981 (F1=0.907$\pm$0.002). Well-calibrated ICL resolves both the institutional PHI gap and the precision--recall trade-off in one LLM call per note. LLMs cost more to run than traditional methods, but that cost buys a way to audit the reference standard. LLMs are a legitimate, adaptable alternative to purpose-built de-identification systems; institution-specific prompt development should be the primary adaptation strategy.

cs.CL↗

arXiv2026

Interpretable EEG biomarkers with bag-of-waves: Spatial and temporal waveform dictionaries for low-data regimes

Electroencephalography (EEG) is widely used to diagnose neurological conditions, but its analysis usually relies on either predefined spectral features or deep neural networks. Predefined features carry a strong bias, since they fix in advance what counts as informative, while deep neural networks and foundation models are hard to interpret and need large amounts of data and compute. We present bag-of-waves, an interpretable framework that learns a small dictionary of recurring EEG waveform templates, called atoms, using shift-invariant k-means without labels. The continuous EEG is then turned into a sequence of atom tokens, whose counts feed a simple downstream classifier or clustering step. We extend this representation in two ways: we add atom-to-atom transitions, which we call n- grams, to capture temporal structure, and we move from single-channel atoms to regional and cross-channel spatial atoms for the multichannel case. We test the method on three complementary datasets, each probing a different aspect: single-channel mouse genotype clustering with only sixteen animals (the low-data and temporal case), resting-state dementia classification (the spatial case), and the TUEV benchmark, a six-way classification of clinical EEG events (a high-data comparison against strong deep and foundation baselines). Across all three datasets, bag-of-waves achieves performance competitive with state-of-the-art deep and foundation models. Yet, it operates with a fraction of the parameter count and provides full interpretability: because every atom corresponds to an inspectable waveform, the method explicitly recovers known clinical morphologies that a neurophysiologist can directly validate. Its main advantage is that it works in the low-data regime where heavier models are a poor fit.

cs.LG↗

arXiv2026

TEDDY: A Pediatric Foundation Model for Risk Forewarning from ICD-Coded Diagnostic Histories

Pediatric electronic health records capture developmentally structured clinical trajectories, yet their potential for generative healthcare foundation models remains largely unexplored. Here we present TEDDY (Temporal Event Decoder for Disease in Youth), a 1.84-million-parameter decoder transformer trained on approximately 73 million ICD-10 diagnoses from 1.6 million children at a single pediatric institution. TEDDY models longitudinal diagnosis trajectories and visit timing. Predictions were made before visit codes were revealed, limited to first occurrences, and evaluated against sex- and age-matched controls. Across 797 disease-onset prediction tasks spanning 16 ICD-10 chapters, TEDDY achieved a median AUC of 72.0%, outperforming same-data DenseNet (50.0%), CNN (57.2%), RNN (60.1%), and LSTM (62.7%) baselines on 96-99% of tasks. Performance held across sex and age and was strongest among lower-prevalence diagnoses; 202 of the 225 rarest conditions (90%) had 95% confidence intervals above chance. Predictive signal remained detectable more than two years before first recorded diagnosis, with median AUCs of 59.7% in the unrestricted analysis and 64.4% in a fixed-cohort sensitivity analysis. In asthma and attention-deficit/hyperactivity disorder benchmarks, AUCs were 79.3% and 84.7%, compared with 62.7% and 71.7% for the strongest comparators, including a general-purpose language model three orders of magnitude larger. Visit-timing predictions had a 3.0-day mean absolute restricted mean survival-time error over 365 days, although median and long-tail return intervals remained miscalibrated. Together, these results establish pediatric diagnostic histories as a substrate for compact generative models supporting broad, rare-disease, and long-horizon risk forecasting without population-scale data or billion-parameter models.

cs.LG↗

arXiv2026

RareCollab: an LLM-powered framework for multimodal reasoning in Mendelian disease diagnosis

Rare disease diagnosis increasingly relies on integrating genomic, phenotypic and transcriptomic evidence, yet these signals remain difficult to reconcile within a common interpretive framework. Here we present RareCollab, an LLM-powered framework for multimodal reasoning in Mendelian disease diagnosis that integrates more than 100 diagnostic evidence signals across DNA, RNA, phenotype, curated variant-level knowledge, and in-silico pathogenicity evidence. This design enables large language models to operate as calibrated, interpretable reasoning modules rather than as a single end-to-end ranker. We applied RareCollab to 890 patients from three cohorts, including 119 Undiagnosed Diseases Network probands with paired DNA and RNA data, constituting a large systematic benchmark for multimodal rare disease diagnosis under paired genomic and transcriptomic evaluation. In this real-world multimodal benchmark, RareCollab prioritized 94% of diagnostic genes within the top 10. Across recall thresholds from top 1 to top 10, it consistently outperformed proprietary phenotype-driven LLM baselines including Claude Sonnet 4.6 and GPT-5-mini by more than 25% on average and surpassed established state-of-the-art variant prioritization methods by 11%-24%. RareCollab also reshapes the diagnostic contribution of RNA evidence, which contributes to prioritization of the diagnostic gene in 35% of cases (42/119). Together, these results establish RareCollab as a scalable and interpretable framework for multimodal rare disease diagnosis.

q-bio.GN↗

arXiv2025

LA-MARRVEL: A Knowledge-Grounded, Language-Aware LLM Framework for Clinically Robust Rare Disease Gene Prioritization

Rare disease diagnosis requires matching variant-bearing genes to complex patient phenotypes across large and heterogeneous evidence sources. This process remains time-intensive in current clinical interpretation pipelines. To overcome these limitations, We present LA-MARRVEL, a knowledge-grounded, language-aware LLM framework and designed for clinical robustness and practical deployment. LA-MARRVEL delivers a 12-15 percentage-point absolute improvement in Recall@1 over established gene prioritization approaches, showing that architectural design can drive substantial accuracy gains. We found that the central contributor is structured, phenotype-rich prompt construction that explicitly encodes patient and disease phenotypes, preserving clinically meaningful context more effectively than disease labels alone. Across three real-world cohorts, LA-MARRVEL consistently improves gene-ranking performance, including in challenging cases where the causal gene was initially ranked lower by first-stage prioritization. For each candidate gene, the system delivers clinically relevant, ACMG-aligned reasoning that integrates phenotype concordance, inheritance patterns, and variant-level evidence into auditable explanations, enabling streamlined clinical review. These findings suggest that knowledge-grounded LLM layer can enhance existing rare-disease gene prioritization workflows without altering established diagnostic pipelines.

q-bio.GN↗

arXiv2025

Improving physics-informed neural network extrapolation via transfer learning and adaptive activation functions

Physics-Informed Neural Networks (PINNs) are deep learning models that incorporate the governing physical laws of a system into the learning process, making them well-suited for solving complex scientific and engineering problems. Recently, PINNs have gained widespread attention as a powerful framework for combining physical principles with data-driven modeling to improve prediction accuracy. Despite their successes, however, PINNs often exhibit poor extrapolation performance outside the training domain and are highly sensitive to the choice of activation functions (AFs). In this paper, we introduce a transfer learning (TL) method to improve the extrapolation capability of PINNs. Our approach applies transfer learning (TL) within an extended training domain, using only a small number of carefully selected collocation points. Additionally, we propose an adaptive AF that takes the form of a linear combination of standard AFs, which improves both the robustness and accuracy of the model. Through a series of experiments, we demonstrate that our method achieves an average of 40% reduction in relative L2 error and an average of 50% reduction in mean absolute error in the extrapolation domain, all without a significant increase in computational cost. The code is available at https://github.com/LiuzLab/PINN-extrapolation .

cs.LG↗

arXiv2025

ConSol: Sequential Probability Ratio Testing to Find Consistent LLM Reasoning Paths Efficiently

Recent advancements in large language models (LLMs) integrating explicit reasoning, such as OpenAI's o3-mini, DeepSeek-R1, and QWQ-32B, enable smaller models to solve complex tasks by generating intermediate reasoning steps prior to providing answers. However, this approach significantly increases computational costs, both monetarily and environmentally. The widely-used self-consistency method further exacerbates these costs by aggregating multiple reasoning paths to improve accuracy, often requiring between 40 to 64 samples per task. Although aggregation effectively reduces variance and bias, additional sampling can lead to diminishing returns when early samples yield consistent results. To address inefficiencies, we propose leveraging Sequential Probability Ratio Testing (SPRT) to dynamically terminate sampling once sufficient consistency is achieved. We calibrate SPRT parameters specifically for LLM applications, accounting for sensitivity to detect the mode of the distribution. Our experiments demonstrate that incorporating SPRT significantly enhances token efficiency, achieving comparable accuracy to self-consistency methods but at a substantially reduced computational cost. To promote transparency and facilitate reproducibility, we have made the source code and datasets used in our experiments publicly available at our GitHub repository: https://github.com/LiuzLab/consol, or available as a PyPI package: pip install consol. We hope that this resource will support further research and encourage the development of new methods building upon our work.

cs.LG↗

arXiv2025

Survey and Improvement Strategies for Gene Prioritization with Large Language Models

Rare diseases are challenging to diagnose due to limited patient data and genetic diversity. Despite advances in variant prioritization, many cases remain undiagnosed. While large language models (LLMs) have performed well in medical exams, their effectiveness in diagnosing rare genetic diseases has not been assessed. To identify causal genes, we benchmarked various LLMs for gene prioritization. Using multi-agent and Human Phenotype Ontology (HPO) classification, we categorized patients based on phenotypes and solvability levels. As gene set size increased, LLM performance deteriorated, so we used a divide-and-conquer strategy to break the task into smaller subsets. At baseline, GPT-4 outperformed other LLMs, achieving near 30% accuracy in ranking causal genes correctly. The multi-agent and HPO approaches helped distinguish confidently solved cases from challenging ones, highlighting the importance of known gene-phenotype associations and phenotype specificity. We found that cases with specific phenotypes or clear associations were more accurately solved. However, we observed biases toward well-studied genes and input order sensitivity, which hindered gene prioritization. Our divide-and-conquer strategy improved accuracy by overcoming these biases. By utilizing HPO classification, novel multi-agent techniques, and our LLM strategy, we improved causal gene identification accuracy compared to our baseline evaluation. This approach streamlines rare disease diagnosis, facilitates reanalysis of unsolved cases, and accelerates gene discovery, supporting the development of targeted diagnostics and therapies.

q-bio.GN↗

arXiv2024

Assessing and Enhancing Large Language Models in Rare Disease Question-answering

Despite the impressive capabilities of Large Language Models (LLMs) in general medical domains, questions remain about their performance in diagnosing rare diseases. To answer this question, we aim to assess the diagnostic performance of LLMs in rare diseases, and explore methods to enhance their effectiveness in this area. In this work, we introduce a rare disease question-answering (ReDis-QA) dataset to evaluate the performance of LLMs in diagnosing rare diseases. Specifically, we collected 1360 high-quality question-answer pairs within the ReDis-QA dataset, covering 205 rare diseases. Additionally, we annotated meta-data for each question, facilitating the extraction of subsets specific to any given disease and its property. Based on the ReDis-QA dataset, we benchmarked several open-source LLMs, revealing that diagnosing rare diseases remains a significant challenge for these models. To facilitate retrieval augmentation generation for rare disease diagnosis, we collect the first rare diseases corpus (ReCOP), sourced from the National Organization for Rare Disorders (NORD) database. Specifically, we split the report of each rare disease into multiple chunks, each representing a different property of the disease, including their overview, symptoms, causes, effects, related disorders, diagnosis, and standard therapies. This structure ensures that the information within each chunk aligns consistently with a question. Experiment results demonstrate that ReCOP can effectively improve the accuracy of LLMs on the ReDis-QA dataset by an average of 8%. Moreover, it significantly guides LLMs to generate trustworthy answers and explanations that can be traced back to existing literature.

cs.CE↗

arXiv2014

A General Framework for Mixed Graphical Models

"Mixed Data" comprising a large number of heterogeneous variables (e.g. count, binary, continuous, skewed continuous, among other data types) are prevalent in varied areas such as genomics and proteomics, imaging genetics, national security, social networking, and Internet advertising. There have been limited efforts at statistically modeling such mixed data jointly, in part because of the lack of computationally amenable multivariate distributions that can capture direct dependencies between such mixed variables of different types. In this paper, we address this by introducing a novel class of Block Directed Markov Random Fields (BDMRFs). Using the basic building block of node-conditional univariate exponential families from Yang et al. (2012), we introduce a class of mixed conditional random field distributions, that are then chained according to a block-directed acyclic graph to form our class of Block Directed Markov Random Fields (BDMRFs). The Markov independence graph structure underlying a BDMRF thus has both directed and undirected edges. We introduce conditions under which these distributions exist and are normalizable, study several instances of our models, and propose scalable penalized conditional likelihood estimators with statistical guarantees for recovering the underlying network structure. Simulations as well as an application to learning mixed genomic networks from next generation sequencing expression data and mutation data demonstrate the versatility of our methods.

math.ST↗

arXiv2013

On the Reproducibility of TCGA Ovarian Cancer MicroRNA Profiles

Dysregulated microRNA (miRNA) expression is a well-established feature of human cancer. However, the role of specific miRNAs in determining cancer outcomes remains unclear. Using Level 3 expression data from the Cancer Genome Atlas (TCGA), we identified 61 miRNAs that are associated with overall survival in 469 ovarian cancers profiled by microarray (p<0.01). We also identified 12 miRNAs that are associated with survival when miRNAs were profiled in the same specimens using Next Generation Sequencing (miRNA-Seq) (p<0.01). Surprisingly, only 1 miRNA transcript is associated with ovarian cancer survival in both datasets. Our analyses indicate that this discrepancy is due to the fact that miRNA levels reported by the two platforms correlate poorly, even after correcting for potential issues inherent to signal detection algorithms. Further investigation is warranted.

q-bio.GN↗

arXiv2013

On Graphical Models via Univariate Exponential Family Distributions

Undirected graphical models, or Markov networks, are a popular class of statistical models, used in a wide variety of applications. Popular instances of this class include Gaussian graphical models and Ising models. In many settings, however, it might not be clear which subclass of graphical models to use, particularly for non-Gaussian and non-categorical data. In this paper, we consider a general sub-class of graphical models where the node-wise conditional distributions arise from exponential families. This allows us to derive multivariate graphical model distributions from univariate exponential family distributions, such as the Poisson, negative binomial, and exponential distributions. Our key contributions include a class of M-estimators to fit these graphical model distributions; and rigorous statistical analysis showing that these M-estimators recover the true graphical model structure exactly, with high probability. We provide examples of genomic and proteomic networks learned via instances of our class of graphical models derived from Poisson and exponential distributions.

math.ST↗

arXiv2012

A Log-Linear Graphical Model for Inferring Genetic Networks from High-Throughput Sequencing Data

Gaussian graphical models are often used to infer gene networks based on microarray expression data. Many scientists, however, have begun using high-throughput sequencing technologies to measure gene expression. As the resulting high-dimensional count data consists of counts of sequencing reads for each gene, Gaussian graphical models are not optimal for modeling gene networks based on this discrete data. We develop a novel method for estimating high-dimensional Poisson graphical models, the Log-Linear Graphical Model, allowing us to infer networks based on high-throughput sequencing data. Our model assumes a pair-wise Markov property: conditional on all other variables, each variable is Poisson. We estimate our model locally via neighborhood selection by fitting 1-norm penalized log-linear models. Additionally, we develop a fast parallel algorithm, an approach we call the Poisson Graphical Lasso, permitting us to fit our graphical model to high-dimensional genomic data sets. In simulations, we illustrate the effectiveness of our methods for recovering network structure from count data. A case study on breast cancer microRNAs, a novel application of graphical models, finds known regulators of breast cancer genes and discovers novel microRNA clusters and hubs that are targets for future research.

stat.AP↗