arXiv subjects

Hongfang Liu

Publications and source records attributed to Hongfang Liu.

At least 19 recordsLinked to original sources

arXiv2026

Retrieval, not hallucinations, will be the limiting factor for LLM-based clinical AI tools

Discussions around large language model (LLM) errors in clinical artificial intelligence (AI) generally center around precision errors like hallucinations. This perspective, targeting both clinicians and AI researchers, seeks to shift that discussion to recall errors, particularly in retrieval of patient-level data needed for many clinical AI tools. The perspective outlines types of errors and mitigation strategies, describes research directions in LLMs and retrieval, and provides an overview of retrieval evaluation.

cs.IR↗

arXiv2026

Agentic AI Enhances Physician Trust in Clinical Decision Making

Medical AI has shifted from reasoning to agentic AI, a new paradigm that autonomously invokes external tools during reasoning, rendering intermediate reasoning steps and tool outputs transparent to users. Although proven to outperform previous models, physician trust in agentic AI remains largely unexplored. To address this, three physicians evaluated 315 multimodal clinical cases quantifying both process-oriented cognitive trust and outcome-oriented behavioral reliance. Comparing agentic AI against non-agentic baselines, physicians exhibited significantly higher cognitive and behavioral trust for the agentic model (P < 0.001). Specifically, on treatment planning tasks, physicians trusted the agentic reasoning most, preferring it in 89.57% of cases. Furthermore, process-oriented cognitive trust is significantly associated with outcome-oriented behavioral reliance (P < 0.001). However, measurable over-reliance on incorrect agentic outputs still exists, highlighting the inherent limitations of decision-logic transparency alone and underscoring the continuous need for rigorous clinician oversight.

cs.CY↗

arXiv2026

TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Models

Time series foundation models (TS-FMs) aim to learn generalizable temporal representations that can be adapted to a wide range of downstream tasks. In real-world multimodal settings, time series are frequently affected by temporal misalignment and partial modality missingness, where different modalities are observed at heterogeneous time scales or are partially absent. Existing approaches typically rely on naive imputation or masking strategies, which fail to account for cross-modal dependencies and often lead to misaligned or degraded representations. We propose TRACE, a conditional estimation paradigm for multimodal time series foundation model pipelines under missingness and irregular sampling, allowing incomplete target modalities to be systematically inferred from available auxiliary modalities. We evaluate TRACE on diverse multimodal benchmarks spanning healthcare and affective computing, including the MIMIC-IV clinical dataset and the CMU-MOSI and CMU-MOSEI benchmarks for multimodal sentiment analysis. Across a range of downstream prediction tasks and missing-modality settings, TRACE consistently outperforms prior multimodal fusion approaches, demonstrating improved robustness to severe modality missingness and more reliable cross-modal representations.

cs.AI↗

arXiv2026

Toward Global Large Language Models in Medicine

Despite continuous advances in medical technology, the global distribution of health care resources remains uneven. The development of large language models (LLMs) has transformed the landscape of medicine and holds promise for improving health care quality and expanding access to medical information globally. However, existing LLMs are primarily trained on high-resource languages, limiting their applicability in global medical scenarios. To address this gap, we constructed GlobMed, a large multilingual medical dataset, containing over 500,000 entries spanning 12 languages, including four low-resource languages. Building on this, we established GlobMed-Bench, which systematically assesses 56 state-of-the-art proprietary and open-weight LLMs across multiple multilingual medical tasks, revealing significant performance disparities across languages, particularly for low-resource languages. Additionally, we introduced GlobMed-LLMs, a suite of multilingual medical LLMs trained on GlobMed, with parameters ranging from 1.7B to 8B. GlobMed-LLMs achieved an average performance improvement of over 40% relative to baseline models, with a more than threefold increase in performance on low-resource languages. Together, these resources provide an important foundation for advancing the equitable development and application of LLMs globally, enabling broader language communities to benefit from technological advances.

cs.CL↗

arXiv2025

Clinical Document Metadata Extraction: A Scoping Review

Clinical document metadata, such as document type, structure, author role, medical specialty, and encounter setting, is essential for accurate interpretation of information captured in clinical documents. However, vast documentation heterogeneity and drift over time challenge harmonization of document metadata. Automated extraction methods have emerged to coalesce metadata from disparate practices into target schema. This scoping review aims to catalog research on clinical document metadata extraction, identify methodological trends and applications, and highlight gaps. We followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines to identify articles that perform clinical document metadata extraction. We initially found and screened 266 articles published between January 2011 and August 2025, then comprehensively reviewed 67 we deemed relevant to our study. Among the articles included, 45 were methodological, 17 used document metadata as features in a downstream application, and 5 analyzed document metadata composition. We observe myriad purposes for methodological study and application types. Available labelled public data remains sparse except for structural section datasets. Methods for extracting document metadata have progressed from largely rule-based and traditional machine learning with ample feature engineering to transformer-based architectures with minimal feature engineering. The emergence of large language models has enabled broader exploration of generalizability across tasks and datasets, allowing the possibility of advanced clinical text processing systems. We anticipate that research will continue to expand into richer document metadata representations and integrate further into clinical applications and workflows.

cs.CL↗

arXiv2025

Desiderata for a biomedical knowledge network: opportunities, challenges and future Directions

Knowledge graphs, collectively as a knowledge network, have become critical tools for knowledge discovery in computable and explainable knowledge systems. Due to the semantic and structural complexities of biomedical data, these knowledge graphs need to enable dynamic reasoning over large evolving graphs and support fit-for-purpose abstraction, while establishing standards, preserving provenance and enforcing policy constraints for actionable discovery. A recent meeting of leading scientists discussed the opportunities, challenges and future directions of a biomedical knowledge network. Here we present six desiderata inspired by the meeting: (1) inference and reasoning in biomedical knowledge graphs need domain-centric approaches; (2) harmonized and accessible standards are required for knowledge graph representation and metadata; (3) robust validation of biomedical knowledge graphs needs multi-layered, context-aware approaches that are both rigorous and scalable; (4) the evolving and synergistic relationship between knowledge graphs and large language models is essential in empowering AI-driven biomedical discovery; (5) integrated development environments, public repositories, and governance frameworks are essential for secure and reproducible knowledge graph sharing; and (6) robust validation, provenance, and ethical governance are critical for trustworthy biomedical knowledge graphs. Addressing these key issues will be essential to realize the promises of a biomedical knowledge network in advancing biomedicine.

q-bio.OT↗

arXiv2025

An Agentic Model Context Protocol Framework for Medical Concept Standardization

The Observational Medical Outcomes Partnership (OMOP) common data model (CDM) provides a standardized representation of heterogeneous health data to support large-scale, multi-institutional research. One critical step in data standardization using OMOP CDM is the mapping of source medical terms to OMOP standard concepts, a procedure that is resource-intensive and error-prone. While large language models (LLMs) have the potential to facilitate this process, their tendency toward hallucination makes them unsuitable for clinical deployment without training and expert validation. Here, we developed a zero-training, hallucination-preventive mapping system based on the Model Context Protocol (MCP), a standardized and secure framework allowing LLMs to interact with external resources and tools. The system enables explainable mapping and significantly improves efficiency and accuracy with minimal effort. It provides real-time vocabulary lookups and structured reasoning outputs suitable for immediate use in both exploratory and production environments.

cs.AI↗

arXiv2025

Multi-Label Classification with Generative AI Models in Healthcare: A Case Study of Suicidality and Risk Factors

Suicide remains a pressing global health crisis, with over 720,000 deaths annually and millions more affected by suicide ideation (SI) and suicide attempts (SA). Early identification of suicidality-related factors (SrFs), including SI, SA, exposure to suicide (ES), and non-suicidal self-injury (NSSI), is critical for timely intervention. While prior studies have applied AI to detect SrFs in clinical notes, most treat suicidality as a binary classification task, overlooking the complexity of cooccurring risk factors. This study explores the use of generative large language models (LLMs), specifically GPT-3.5 and GPT-4.5, for multi-label classification (MLC) of SrFs from psychiatric electronic health records (EHRs). We present a novel end to end generative MLC pipeline and introduce advanced evaluation methods, including label set level metrics and a multilabel confusion matrix for error analysis. Finetuned GPT-3.5 achieved top performance with 0.94 partial match accuracy and 0.91 F1 score, while GPT-4.5 with guided prompting showed superior performance across label sets, including rare or minority label sets, indicating a more balanced and robust performance. Our findings reveal systematic error patterns, such as the conflation of SI and SA, and highlight the models tendency toward cautious over labeling. This work not only demonstrates the feasibility of using generative AI for complex clinical classification tasks but also provides a blueprint for structuring unstructured EHR data to support large scale clinical research and evidence based medicine.

cs.CL↗

arXiv2025

Scaling Up Biomedical Vision-Language Models: Fine-Tuning, Instruction Tuning, and Multi-Modal Learning

To advance biomedical vison-language model capabilities through scaling up, fine-tuning, and instruction tuning, develop vision-language models with improved performance in handling long text, explore strategies to efficiently adopt vision language models for diverse multi-modal biomedical tasks, and examine the zero-shot learning performance. We developed two biomedical vision language models, BiomedGPT-Large and BiomedGPT-XLarge, based on an encoder-decoder-based transformer architecture. We fine-tuned the two models on 23 benchmark datasets from 6 multi-modal biomedical tasks including one image-only task (image classification), three language-only tasks (text understanding, text summarization and question answering), and two vision-language tasks (visual question answering and image captioning). We compared the developed scaled models with our previous BiomedGPT-Base model and existing prestigious models reported in the literature. We instruction-tuned the two models using a large-scale multi-modal biomedical instruction-tuning dataset and assessed the zero-shot learning performance and alignment accuracy.

cs.AI↗

arXiv2025

Chern Vector Protected Three-dimensional Quantized Hall Effect

Recently, Chern vector with arbitrary formula $\textbf{C}\!=\!(\mathcal{C}_{yz},\mathcal{C}_{xz},\mathcal{C}_{xy})$ in three-dimensional systems has been experimentally realized [\B{Nature 609, 925 (2022)}]. Motivated by these progresses, we propose the Chern vector $\textbf{C}\!=\!(0,m,n)$-protected quantized Hall effect in three-dimensional systems. By examining samples with Chern vector $\textbf{C}\!=\!(0,m,n)$ and dimensions $L_y$ and $L_z$ along the $y$- and $z$-directions, we demonstrate a topologically protected two-terminal response. This response can be reformulated as the sum of the transmission coefficients along the $x$- and $y$-directions, given by $(mL_y\!+\!nL_z)$. When applied to Hall bar setups, this topological mechanism gives rise to quantized Hall conductances, such as $G_{xy}$ and $G_{xz}$, which are expressed by $\pm(mL_y\!+\!nL_z)$. These Hall conductances exhibit a clear dependency on sample dimensions, illuminating the intrinsic three-dimensional nature. Finally, we propse potential candidates for experimental realization. Our findings not only deepen the understanding of the topological nature of Chern vectors but also enlighten the exploration of their transport properties.

cond-mat.mes-hall↗

arXiv2025

Three-dimensional quantum anomalous Hall effect in Weyl semimetals

The quantum anomalous Hall effect (QAHE) is a quantum phenomenon in which a two-dimensional system exhibits a quantized Hall resistance $h/e^2$ in the absence of magnetic field, where $h$ is the Planck constant and $e$ is the electron charge. In this work, we extend this novel phase to three dimensions and thus propose a three-dimensional QAHE exhibiting richer and more versatile transport behaviors. We first confirm this three-dimensional QAHE through the quantized Chern number, then establish its bulk-boundary correspondence, and finally reaffirm it via the distinctive transport properties. Remarkably, we find that the three-dimensional QAHE hosts two chiral surface states along one spatial direction while a pair of chiral hinge states along another direction, and the location of the hinge states depends sensitively on the Fermi energy. These two types of boundary states are further connected through a perpendicular chiral surface states, whose chirality is also Fermi energy dependent. Consequently, depending on the transport direction, its Hall resistance can quantize to $0$, $h/e^2$, or $\pm h/e^2$ when the Fermi energy is tuned across the charge neutral point. This three-dimensional QAHE not only fill the gap in the Hall effect family but also holds significant potentials in device applications such as in-memory computing.

cond-mat.mes-hall↗

arXiv2024

Explainable Diagnosis Prediction through Neuro-Symbolic Integration

Diagnosis prediction is a critical task in healthcare, where timely and accurate identification of medical conditions can significantly impact patient outcomes. Traditional machine learning and deep learning models have achieved notable success in this domain but often lack interpretability which is a crucial requirement in clinical settings. In this study, we explore the use of neuro-symbolic methods, specifically Logical Neural Networks (LNNs), to develop explainable models for diagnosis prediction. Essentially, we design and implement LNN-based models that integrate domain-specific knowledge through logical rules with learnable thresholds. Our models, particularly $M_{\text{multi-pathway}}$ and $M_{\text{comprehensive}}$, demonstrate superior performance over traditional models such as Logistic Regression, SVM, and Random Forest, achieving higher accuracy (up to 80.52\%) and AUROC scores (up to 0.8457) in the case study of diabetes prediction. The learned weights and thresholds within the LNN models provide direct insights into feature contributions, enhancing interpretability without compromising predictive power. These findings highlight the potential of neuro-symbolic approaches in bridging the gap between accuracy and explainability in healthcare AI applications. By offering transparent and adaptable diagnostic models, our work contributes to the advancement of precision medicine and supports the development of equitable healthcare solutions. Future research will focus on extending these methods to larger and more diverse datasets to further validate their applicability across different medical conditions and populations.

cs.LG↗

arXiv2024

Suicide Phenotyping from Clinical Notes in Safety-Net Psychiatric Hospital Using Multi-Label Classification with Pre-Trained Language Models

Accurate identification and categorization of suicidal events can yield better suicide precautions, reducing operational burden, and improving care quality in high-acuity psychiatric settings. Pre-trained language models offer promise for identifying suicidality from unstructured clinical narratives. We evaluated the performance of four BERT-based models using two fine-tuning strategies (multiple single-label and single multi-label) for detecting coexisting suicidal events from 500 annotated psychiatric evaluation notes. The notes were labeled for suicidal ideation (SI), suicide attempts (SA), exposure to suicide (ES), and non-suicidal self-injury (NSSI). RoBERTa outperformed other models using multiple single-label classification strategy (acc=0.86, F1=0.78). MentalBERT (acc=0.83, F1=0.74) also exceeded BioClinicalBERT (acc=0.82, F1=0.72) which outperformed BERT (acc=0.80, F1=0.70). RoBERTa fine-tuned with single multi-label classification further improved the model performance (acc=0.88, F1=0.81). The findings highlight that the model optimization, pretraining with domain-relevant data, and the single multi-label classification strategy enhance the model performance of suicide phenotyping. Keywords: EHR-based Phenotyping; Natural Language Processing; Secondary Use of EHR Data; Suicide Classification; BERT-based Model; Psychiatry; Mental Health

cs.CL↗

arXiv2024

Large Language Models Struggle in Token-Level Clinical Named Entity Recognition

Large Language Models (LLMs) have revolutionized various sectors, including healthcare where they are employed in diverse applications. Their utility is particularly significant in the context of rare diseases, where data scarcity, complexity, and specificity pose considerable challenges. In the clinical domain, Named Entity Recognition (NER) stands out as an essential task and it plays a crucial role in extracting relevant information from clinical texts. Despite the promise of LLMs, current research mostly concentrates on document-level NER, identifying entities in a more general context across entire documents, without extracting their precise location. Additionally, efforts have been directed towards adapting ChatGPT for token-level NER. However, there is a significant research gap when it comes to employing token-level NER for clinical texts, especially with the use of local open-source LLMs. This study aims to bridge this gap by investigating the effectiveness of both proprietary and local LLMs in token-level clinical NER. Essentially, we delve into the capabilities of these models through a series of experiments involving zero-shot prompting, few-shot prompting, retrieval-augmented generation (RAG), and instruction-fine-tuning. Our exploration reveals the inherent challenges LLMs face in token-level NER, particularly in the context of rare diseases, and suggests possible improvements for their application in healthcare. This research contributes to narrowing a significant gap in healthcare informatics and offers insights that could lead to a more refined application of LLMs in the healthcare sector.

cs.CL↗

arXiv2024

CancerLLM: A Large Language Model in Cancer Domain

Medical Large Language Models (LLMs) have demonstrated impressive performance on a wide variety of medical NLP tasks; however, there still lacks a LLM specifically designed for phenotyping identification and diagnosis in cancer domain. Moreover, these LLMs typically have several billions of parameters, making them computationally expensive for healthcare systems. Thus, in this study, we propose CancerLLM, a model with 7 billion parameters and a Mistral-style architecture, pre-trained on nearly 2.7M clinical notes and over 515K pathology reports covering 17 cancer types, followed by fine-tuning on two cancer-relevant tasks, including cancer phenotypes extraction and cancer diagnosis generation. Our evaluation demonstrated that the CancerLLM achieves state-of-the-art results with F1 score of 91.78% on phenotyping extraction and 86.81% on disganois generation. It outperformed existing LLMs, with an average F1 score improvement of 9.23%. Additionally, the CancerLLM demonstrated its efficiency on time and GPU usage, and robustness comparing with other LLMs. We demonstrated that CancerLLM can potentially provide an effective and robust solution to advance clinical research and practice in cancer domain

cs.CL↗

arXiv2024

Measurement of the Chern Number for Non-Hermitian Chern Insulators

The identification of the topological invariant of a topological system is crucial in experiments. However, due to the inherent non-Hermitian features, such determination is notably challenging in non-Hermitian systems. Here, we propose that the magnetic effect can be utilized to measure the Chern number of the non-Hermitian Chern insulator. We find that the splitting of non-Hermitian bands under the magnetic field is Chern number dependent. Consequently, one can easily identify the Chern number by analyzing these splitting sub-bands. From the experimental perspective, the measurement of non-Hermitian bands is demonstrated in LC electric circuits. Furthermore, we find that the non-Hermiticity can drive open (closed) orbits of sub-bands in the Hermitian limit closed (open), which can also be identified by our proposal. These phenomena highlight the distinctive capabilities of non-Hermitian systems. Our results facilitate the detection of Chern numbers for non-Hermitian systems and may motivate further studies of their topological properties.

cond-mat.mes-hall↗

arXiv2023

GRU-D-Weibull: A Novel Real-Time Individualized Endpoint Prediction

Accurate prediction models for individual-level endpoints and time-to-endpoints are crucial in clinical practice. In this study, we propose a novel approach, GRU-D-Weibull, which combines gated recurrent units with decay (GRU-D) to model the Weibull distribution. Our method enables real-time individualized endpoint prediction and population-level risk management. Using a cohort of 6,879 patients with stage 4 chronic kidney disease (CKD4), we evaluated the performance of GRU-D-Weibull in endpoint prediction. The C-index of GRU-D-Weibull was ~0.7 at the index date and increased to ~0.77 after 4.3 years of follow-up, similar to random survival forest. Our approach achieved an absolute L1-loss of ~1.1 years (SD 0.95) at the CKD4 index date and a minimum of ~0.45 years (SD0.3) at 4 years of follow-up, outperforming competing methods significantly. GRU-D-Weibull consistently constrained the predicted survival probability at the time of an event within a smaller and more fixed range compared to other models throughout the follow-up period. We observed significant correlations between the error in point estimates and missing proportions of input features at the index date (correlations from ~0.1 to ~0.3), which diminished within 1 year as more data became available. By post-training recalibration, we successfully aligned the predicted and observed survival probabilities across multiple prediction horizons at different time points during follow-up. Our findings demonstrate the considerable potential of GRU-D-Weibull as the next-generation architecture for endpoint risk management, capable of generating various endpoint estimates for real-time monitoring using clinical data.

cs.LG↗

arXiv2023

BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks

Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or modalities, often exhibit limited flexibility in real-world deployment and struggle to utilize holistic information. Generalist AI holds the potential to address these limitations due to its versatility in interpreting different data types and generating tailored outputs for diverse needs. However, existing biomedical generalist AI solutions are typically heavyweight and closed source to researchers, practitioners, and patients. Here, we propose BiomedGPT, the first open-source and lightweight vision-language foundation model, designed as a generalist capable of performing various biomedical tasks. BiomedGPT achieved state-of-the-art results in 16 out of 25 experiments while maintaining a computing-friendly model scale. We also conducted human evaluations to assess the capabilities of BiomedGPT in radiology visual question answering, report generation, and summarization. BiomedGPT exhibits robust prediction ability with a low error rate of 3.8% in question answering, satisfactory performance with an error rate of 8.3% in writing complex radiology reports, and competitive summarization ability with a nearly equivalent preference score to human experts. Our method demonstrates that effective training with diverse data can lead to more practical biomedical AI for improving diagnosis and workflow efficiency.

cs.CL↗