Donghan M. Yang
YOU?
Author Swipe
View article: Association of PD-L1 expression with systemic immune parameters in non-small cell lung cancer
Association of PD-L1 expression with systemic immune parameters in non-small cell lung cancer Open
NSCLC PD-L1 expression is associated with few systemic immune parameters, suggesting that effects on anti-tumor immunity may occur predominantly in the tumor microenvironment and that blood-based assays are unlikely to provide meaningful s…
View article: GAS-MIL: Group-Aggregative Selection Multi-Instance Learning for Ensemble of Foundation Models in Digital Pathology Image Analysis
GAS-MIL: Group-Aggregative Selection Multi-Instance Learning for Ensemble of Foundation Models in Digital Pathology Image Analysis Open
Foundation models (FMs) have transformed computational pathology by providing powerful, general-purpose feature extractors. However, adapting and benchmarking individual FMs for specific diagnostic tasks is often time-consuming and resourc…
View article: Comparative Risk of Infection and Prevalence of Combination Targeted Therapy in Psoriatic Arthritis
Comparative Risk of Infection and Prevalence of Combination Targeted Therapy in Psoriatic Arthritis Open
Importance Achieving good disease control in psoriatic arthritis (PsA) remains a major challenge. Combining multiple systemic immunomodulatory therapies has been shown to be beneficial in other immune-mediated diseases with reasonable safe…
View article: In Silico Drug Screening with Mechanistic Insight: A Cross-Attention Framework for Predicting Drug-Gene Interactions
In Silico Drug Screening with Mechanistic Insight: A Cross-Attention Framework for Predicting Drug-Gene Interactions Open
Identifying how drug molecular structures interact with specific gene targets remains a key challenge in cancer precision medicine. Although large-scale in vitro drug screening datasets are available, most computational models fail to eluc…
View article: SBDH-Reader: a large language model-powered method for extracting social and behavioral determinants of health from clinical notes
SBDH-Reader: a large language model-powered method for extracting social and behavioral determinants of health from clinical notes Open
Objective Social and behavioral determinants of health (SBDH) are increasingly recognized as essential for prognostication and informing targeted interventions. Clinical notes often contain details about SBDH in unstructured format. Conven…
View article: MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science
MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science Open
We introduce MedAgentGym, a scalable and interactive training environment designed to enhance coding-based biomedical reasoning capabilities in large language model (LLM) agents. MedAgentGym comprises 72,413 task instances across 129 categ…
View article: A deep learning model for clinical outcome prediction using longitudinal inpatient electronic health records
A deep learning model for clinical outcome prediction using longitudinal inpatient electronic health records Open
Objectives Recent advances in deep learning show significant potential in analyzing continuous monitoring electronic health records (EHR) data for clinical outcome prediction. We aim to develop a Transformer-based, Encounter-level Clinical…
View article: SBDH-Reader: an LLM-powered method for extracting social and behavioral determinants of health from clinical notes
SBDH-Reader: an LLM-powered method for extracting social and behavioral determinants of health from clinical notes Open
Objective Social and behavioral determinants of health (SBDH) are increasingly recognized as essential for prognostication and informing targeted interventions. Clinical notes often contain details about SBDH in unstructured format. Conven…
View article: N-Power AI: A Specialized Agent Framework for Automated Sample Size and Power Analysis in Clinical Trial Design
N-Power AI: A Specialized Agent Framework for Automated Sample Size and Power Analysis in Clinical Trial Design Open
Background Sample size and power analysis are essential in biomedical research and investigations, particularly in clinical trial design, as they ensure sufficient statistical power to detect meaningful effects. However, the complexity of …
View article: A deep learning model for clinical outcome prediction using longitudinal inpatient electronic health records
A deep learning model for clinical outcome prediction using longitudinal inpatient electronic health records Open
Objective Recent advances in deep learning show significant potential in analyzing continuous monitoring electronic health records (EHR) data for clinical outcome prediction. We aim to develop a Transformer-based, Encounter-level Clinical …
View article: Self-guided Knowledgeable Network of Thoughts: Amplifying Reasoning with Large Language Models
Self-guided Knowledgeable Network of Thoughts: Amplifying Reasoning with Large Language Models Open
We introduce Knowledgeable Network of Thoughts (kNoT): a prompt scheme that advances the capabilities of large language models (LLMs) beyond existing paradigms like Chain-of-Thought (CoT), Tree of Thoughts (ToT), and Graph of Thoughts (GoT…
View article: Incidence and Prevalence of Atherosclerotic Cardiovascular Disease in Cutaneous Lupus Erythematosus
Incidence and Prevalence of Atherosclerotic Cardiovascular Disease in Cutaneous Lupus Erythematosus Open
Importance Autoimmune diseases such as systemic lupus erythematosus (SLE) and psoriasis have been previously associated with an increased risk of atherosclerotic cardiovascular disease (ASCVD). Whether similar increased ASCVD risk is seen …
View article: I-Viewer: An Online Digital Pathology Analysis Platform with Agentic-RAG AI Copilot
I-Viewer: An Online Digital Pathology Analysis Platform with Agentic-RAG AI Copilot Open
Digital pathology has seen significant advancements in artificial intelligence (AI) applications. However, challenges persist in integrating these solutions into digital pathology platforms for human and AI collaborations. We introduce I-V…
View article: Multi-Agent LLMs Ensemble for Efficient Atrial Fibrillation Annotation of ECG Reports
Multi-Agent LLMs Ensemble for Efficient Atrial Fibrillation Annotation of ECG Reports Open
This study introduces a novel multiagent ensemble method powered by LLMs to address a key challenge in ML - data labeling, particularly in large-scale EHR datasets. Manual labeling of such datasets requires domain expertise and is labor-in…
View article: Cmai: Predicting Antigen-Antibody Interactions from Massive Sequencing Data
Cmai: Predicting Antigen-Antibody Interactions from Massive Sequencing Data Open
The interaction between antigens and antibodies (B cell receptors, BCRs) is the key step underlying the function of the humoral immune system in various biological contexts. The capability to profile the landscape of antigen-binding affini…
View article: Deep Learning-Based Automated Measurement of Murine Bone Length in Radiographs
Deep Learning-Based Automated Measurement of Murine Bone Length in Radiographs Open
Genetic mouse models of skeletal abnormalities have demonstrated promise in the identification of phenotypes relevant to human skeletal diseases. Traditionally, phenotypes are assessed by manually examining radiographs, a tedious and poten…
View article: Enhancing Medical Imaging Segmentation with GB-SAM: A Novel Approach to Tissue Segmentation Using Granular Box Prompts
Enhancing Medical Imaging Segmentation with GB-SAM: A Novel Approach to Tissue Segmentation Using Granular Box Prompts Open
Recent advances in foundation models have revolutionized model development in digital pathology, reducing dependence on extensive manual annotations required by traditional methods. The ability of foundation models to generalize well with …
View article: Deep learning of cell spatial organizations identifies clinically relevant insights in tissue images
Deep learning of cell spatial organizations identifies clinically relevant insights in tissue images Open
Recent advancements in tissue imaging techniques have facilitated the visualization and identification of various cell types within physiological and pathological contexts. Despite the emergence of cell-cell interaction studies, there is a…
View article: pan-MHC and cross-Species Prediction of T Cell Receptor-Antigen Binding
pan-MHC and cross-Species Prediction of T Cell Receptor-Antigen Binding Open
SUMMARY Profiling the binding of T cell receptors (TCRs) of T cells to antigenic peptides presented by MHC proteins is one of the most important unsolved problems in modern immunology. Experimental methods to probe TCR-antigen interactions…
View article: Drilling Parameters Multi-Objective Optimization Method Based on PSO-Bi-LSTM
Drilling Parameters Multi-Objective Optimization Method Based on PSO-Bi-LSTM Open
The increasing exploration and development of complex oil and gas fields pose challenges to drilling efficiency and safety due to the presence of formations with varying hardness, abrasiveness, and rigidity. Consequently, there is a growin…
View article: Comprehensive characterization of patient-derived xenograft models of pediatric leukemia
Comprehensive characterization of patient-derived xenograft models of pediatric leukemia Open
Patient-derived xenografts (PDX) remain valuable models for understanding the biology and for developing novel therapeutics. To expand current PDX models of childhood leukemia, we have developed new PDX models from Hispanic patients, a sub…
View article: Osteosarcoma Explorer: A Data Commons With Clinical, Genomic, Protein, and Tissue Imaging Data for Osteosarcoma Research
Osteosarcoma Explorer: A Data Commons With Clinical, Genomic, Protein, and Tissue Imaging Data for Osteosarcoma Research Open
PURPOSE Osteosarcoma research advancement requires enhanced data integration across different modalities and sources. Current osteosarcoma research, encompassing clinical, genomic, protein, and tissue imaging data, is hindered by the siloe…
View article: A Deep Learning Onion Peeling Approach to Measure Oral Epithelium Layer Number
A Deep Learning Onion Peeling Approach to Measure Oral Epithelium Layer Number Open
Head and neck squamous cell carcinoma (HNSCC), specifically in the oral cavity (oral squamous cell carcinoma, OSCC), is a common, complex cancer that significantly affects patients’ quality of life. Early diagnosis typically improves progn…
View article: Deep Learning of Cell Spatial Organizations Identifies Clinically Relevant Insights in Tissue Images
Deep Learning of Cell Spatial Organizations Identifies Clinically Relevant Insights in Tissue Images Open
Recent advancements in tissue imaging techniques have facilitated the visualization and identification of various cell types within physiological and pathological contexts. Despite the emergence of cell-cell interaction studies, there is a…
View article: Early Gas Kick Warning Based on Temporal Autoencoder
Early Gas Kick Warning Based on Temporal Autoencoder Open
The timing of the data is not taken into account by the majority of risk warnings today. However, identifying temporal fluctuations in data, which is a vital method for detecting risk, is neglected by the majority of intelligent gas kick w…