About background image

About Dr. Ling Huang

Research Fellow in Trustworthy Al for Healthcare at Imperial College London.

Dr. Ling Huang profile picture

About Me

Hi, I'm Dr. Ling Huang. I am a Postdoctoral Research Associate at Imperial College London (Institute of Clinical Science, Department of Medicine) and a member of the O'Regan Lab.

My research focuses on making artificial intelligence in healthcare trustworthy, transparent, and safe for clinical use. I specialize in uncertainty quantification, belief function theory, and multimodal medical data fusion. Currently, I am the Principal Investigator for a Dame Julia Higgins Fund project aimed at revolutionizing cancer survival analysis through trustworthy AI.

Before joining Imperial, I was a Postdoctoral Research Fellow at the National University of Singapore and the National University Hospital. I earned my PhD in Computer Science from the University of Technology of Compiègne, where my research was awarded the 2024 Best Thesis Prize by the French Society of Biological and Medical Engineering (SFGBM). I also proudly serve as an Editorial Board Member for the top-tier journal Information Fusion.

Download Full CV

Core Research Expertise

Theoretical Foundations

  • Dempster-Shafer Theory

    Developing robust mathematical frameworks to explicitly model epistemic uncertainty and conflicting evidence

  • Uncertainty Quantification

    Rigorously quantifying both data noise and model ignorance to prevent overconfident, erroneous AI predictions.

  • Causal Inference

    Applying causal methodologies to uncover complex, real-world relationships within observational healthcare data.

AI & Computational Methods

  • Trustworthy AI Systems

    Designing explainable and transparent deep learning architectures safe for high-stakes clinical deployment.

  • Multimodal Info Fusion

    Synthesizing complementary data from diverse, noisy modalities like medical imaging, EHRs, and clinical notes.

  • Natural Language Processing

    Adapting Large Language Models (LLMs) to accurately and safely extract insights from unstructured medical text.

Clinical Applications

  • Cardiovascular Computing

    Enhancing the robustness of echocardiogram analysis and heart failure prediction despite noisy imaging data.

  • Cancer Survival Analysis

    Integrating multimodal patient data to build highly reliable prognostic models for personalized oncology care.

  • Gene-Environment Analysis

    Investigating the complex, multifactorial interplay between genetic factors and environmental health exposures.

Grants & Funding

Dame Julia Higgins Postdoc Collaborative Research Fund | 2025 - 2026

Principal Investigator (PI)

Project: Revolutionizing Cancer Survival Analysis Through Trustworthy AI and Multimodal Integration

Dame Julia Higgins Postdoc Collaborative Research Fund | 2025 - 2026

Co-Principal Investigator (Co-PI)

Project: Automating Environmental Health Literature Screening Using Large Language Models

Honors & Awards

  • IJAR Best Paper Award BELIEF

    International Conference on Belief Functions (BELIEF) (2024)

  • Thesis Prize

    French Society of Biological and Medical Engineering (SFGBM) (2024)

  • Frontrunner 5000

    Top Articles from Outstanding S&T Journals of China (2021)

  • High Impact Paper

    Journal of Software (2019, 2020)

  • Excellent Graduation Thesis

    Zhejiang University of Technology (2019)

  • Chinese National Scholarship (2017)

Professional Service

Editorial Board Member

Information Fusion

Committee Member

International Conference on Belief Functions (BELIEF 2026)

Peer Reviewer

  • Information Fusion
  • Medical Image Analysis
  • Knowledge-Based Systems
  • International Journal of Approximate Reasoning (IJAR)