Zhuohang Li
YOU?
Author Swipe
View article: Metabolic Reprogramming in Urological Tumors: New Perspectives from Tumor Metabolic Phenotypes to Therapeutic Targets
Metabolic Reprogramming in Urological Tumors: New Perspectives from Tumor Metabolic Phenotypes to Therapeutic Targets Open
View article: AniMarkerDB: a comprehensive database for exploring cell types and marker genes in livestock and poultry at single-cell resolution
AniMarkerDB: a comprehensive database for exploring cell types and marker genes in livestock and poultry at single-cell resolution Open
Single-cell RNA sequencing (scRNA-seq) has dramatically advanced the understanding of cellular heterogeneity. While numerous marker gene databases are available for humans and mice, a lack of systematic resources for livestock and poultry …
View article: Role of tertiary lymphoid structures in the tumour microenvironment and immunotherapy response of renal cell carcinoma
Role of tertiary lymphoid structures in the tumour microenvironment and immunotherapy response of renal cell carcinoma Open
In the tumour microenvironment (TME) of renal cell carcinoma (RCC), tertiary lymphoid structures (TLS) play a crucial role in anti‐tumour immune responses. Resembling secondary lymphoid organs, TLS comprises B cells, T cell zones, high end…
View article: TMCO1 as an Endoplasmic Reticulum Calcium Load-Activated Channel: Mechanisms and Disease Implications
TMCO1 as an Endoplasmic Reticulum Calcium Load-Activated Channel: Mechanisms and Disease Implications Open
Calcium ions (Ca2+) play a vital role in many biological processes. Transmembrane and coiled-coil domain 1 (TMCO1) has been characterized as an endoplasmic reticulum (ER) transmembrane protein in recent years. It keeps the cytoplasm and ER…
View article: A machine learning-based screening model for the early detection of prostate cancer developed using serum microRNA data from a mixed cohort of 8,741 participants
A machine learning-based screening model for the early detection of prostate cancer developed using serum microRNA data from a mixed cohort of 8,741 participants Open
View article: Top management team interlocking network and corporate unethical behavior: the moderating role of media coverage and knowledge background
Top management team interlocking network and corporate unethical behavior: the moderating role of media coverage and knowledge background Open
Recently, the increasing application of the top management team (TMT) interlocking network, formed by executives holding top positions in multiple companies, has underscored their crucial role in corporate governance. Drawing on social net…
View article: How education from children influences parents' green travel behavior? The mediating role of environmental protection commitment
How education from children influences parents' green travel behavior? The mediating role of environmental protection commitment Open
The transmission of green ideas within families is no longer limited to the older generations instilling ideas into the younger generations. Younger generations are increasingly influencing the green travel behavior of older generations wi…
View article: Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark
Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark Open
Multimodal language analysis is a rapidly evolving field that leverages multiple modalities to enhance the understanding of high-level semantics underlying human conversational utterances. Despite its significance, little research has inve…
View article: How Do Core Management Team Network Ties Affect Green Innovation? Evidence from the Chinese ICT Industry
How Do Core Management Team Network Ties Affect Green Innovation? Evidence from the Chinese ICT Industry Open
In the context of green sustainable development, improving the quality of green innovation (GI) has become an urgent issue for enterprises. Corporate social networks play a vital role in improving the quality of GI, but there is a lack of …
View article: Development and validation of a deep learning-based automated computed tomography image segmentation and diagnostic model for infectious hydronephrosis: a retrospective multicentre cohort study
Development and validation of a deep learning-based automated computed tomography image segmentation and diagnostic model for infectious hydronephrosis: a retrospective multicentre cohort study Open
View article: Large language models are less effective at clinical prediction tasks than locally trained machine learning models
Large language models are less effective at clinical prediction tasks than locally trained machine learning models Open
Objectives To determine the extent to which current large language models (LLMs) can serve as substitutes for traditional machine learning (ML) as clinical predictors using data from electronic health records (EHRs), we investigated variou…
View article: Application test methods and impact of generative artificial intelligence in engineering management
Application test methods and impact of generative artificial intelligence in engineering management Open
Engineering management is the key to the successful implementation of projects, but it has always faced problems such as low efficiency and limited intelligence level. The rise of generative artificial intelligence has brought new opportun…
View article: A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithm
A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithm Open
Recent advances in Large Language Models have led to remarkable achievements across a variety of Natural Language Processing tasks, making prompt engineering increasingly central to guiding model outputs. While manual methods can be effect…
View article: Contrast‐enhanced ultrasound enables precision diagnosis of preoperative muscle invasion in bladder cancer: a prospective study
Contrast‐enhanced ultrasound enables precision diagnosis of preoperative muscle invasion in bladder cancer: a prospective study Open
Bladder cancer's high mortality underscores the need for precise staging, especially to differentiate between nonmuscle invasive bladder cancer (NMIBC) and muscle invasive bladder cancer (MIBC) types. This prospective study evaluated the e…
View article: Association of 5α-reductase inhibitor prescription with immunotherapy efficacy in metastatic renal cell carcinoma: a multicenter retrospective analysis
Association of 5α-reductase inhibitor prescription with immunotherapy efficacy in metastatic renal cell carcinoma: a multicenter retrospective analysis Open
Background Immune checkpoint inhibitors (ICIs) have revolutionized the treatment of metastatic renal cell carcinoma (mRCC), but response rates remain heterogeneous, and reliable predictive biomarkers are lacking. Recent studies suggest tha…
View article: Heuristic-based Search Algorithm in Automatic Instruction-focused Prompt Optimization: A Survey
Heuristic-based Search Algorithm in Automatic Instruction-focused Prompt Optimization: A Survey Open
View article: Towards Statistical Factuality Guarantee for Large Vision-Language Models
Towards Statistical Factuality Guarantee for Large Vision-Language Models Open
View article: SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization
SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization Open
View article: Not the Models You Are Looking For: Traditional ML Outperforms LLMs in Clinical Prediction Tasks
Not the Models You Are Looking For: Traditional ML Outperforms LLMs in Clinical Prediction Tasks Open
Objectives To determine the extent to which current Large Language Models (LLMs) can serve as substitutes for traditional machine learning (ML) as clinical predictors using data from electronic health records (EHRs), we investigated variou…
View article: Analyzing Inference Privacy Risks Through Gradients In Machine Learning
Analyzing Inference Privacy Risks Through Gradients In Machine Learning Open
View article: Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation
Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation Open
Language models (LMs) are known to suffer from hallucinations and misinformation. Retrieval augmented generation (RAG) that retrieves verifiable information from an external knowledge corpus to complement the parametric knowledge in LMs pr…
View article: Screening Model for Bladder Cancer Early Detection With Serum <scp>miRNAs</scp> Based on Machine Learning: A Mixed‐Cohort Study Based on 16,189 Participants
Screening Model for Bladder Cancer Early Detection With Serum <span>miRNAs</span> Based on Machine Learning: A Mixed‐Cohort Study Based on 16,189 Participants Open
Background Early detection of bladder cancer (BCa) can have a positive impact on patients' prognosis. However, there is currently no widely accepted method for early screening of BCa. We aimed to develop an efficient, clinically applicable…
View article: Optimizing Large Language Models for Discharge Prediction: Best Practices in Leveraging Electronic Health Record Audit Logs
Optimizing Large Language Models for Discharge Prediction: Best Practices in Leveraging Electronic Health Record Audit Logs Open
Electronic Health Record (EHR) audit log data are increasingly utilized for clinical tasks, from workflow modeling to predictive analyses of discharge events, adverse kidney outcomes, and hospital readmissions. These data encapsulate user-…
View article: Exploring User-level Gradient Inversion with a Diffusion Prior
Exploring User-level Gradient Inversion with a Diffusion Prior Open
We explore user-level gradient inversion as a new attack surface in distributed learning. We first investigate existing attacks on their ability to make inferences about private information beyond training data reconstruction. Motivated by…
View article: Analyzing Inference Privacy Risks Through Gradients in Machine Learning
Analyzing Inference Privacy Risks Through Gradients in Machine Learning Open
In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a s…
View article: Screening model for prostate cancer early detection constructed using machine learning based on serum microRNAs in a mixed cohort
Screening model for prostate cancer early detection constructed using machine learning based on serum microRNAs in a mixed cohort Open
Background Early detection of prostate cancer (PCa) can improve the prognosis of patients. Currently, the role of the prostate specific antigen test for PCa screening remains debatable. We aimed to develop an efficient and clinically appli…
View article: Elucidating the role of MICAL1 in pan-cancer using integrated bioinformatics and experimental approaches
Elucidating the role of MICAL1 in pan-cancer using integrated bioinformatics and experimental approaches Open
Molecule interacting with CasL 1 (MICAL1) is a crucial protein involved in cell motility, axon guidance, cytoskeletal dynamics, and gene transcription. This pan-cancer study analyzed MICAL1 across 33 cancer types using bioinformatics and e…
View article: Antibacterial activity of cinnamon essential oil and its main component of cinnamaldehyde and the underlying mechanism
Antibacterial activity of cinnamon essential oil and its main component of cinnamaldehyde and the underlying mechanism Open
Background: Plant essential oils have long been regarded as repositories of antimicrobial agents. In recent years, they have emerged as potential alternatives or supplements to antimicrobial drugs. Although literature reviews and previous …
View article: Generating Synthetic Electronic Health Record Data Using Generative Adversarial Networks: Tutorial
Generating Synthetic Electronic Health Record Data Using Generative Adversarial Networks: Tutorial Open
Synthetic electronic health record (EHR) data generation has been increasingly recognized as an important solution to expand the accessibility and maximize the value of private health data on a large scale. Recent advances in machine learn…
View article: SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization
SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization Open
Designing optimal prompts for Large Language Models (LLMs) is a complicated and resource-intensive task, often requiring substantial human expertise and effort. Existing approaches typically separate the optimization of prompt instructions…