Ruixuan HUANG

About

I have rich experience in data analysis, programming and modelling, and I am proficient in multiple programming languages and machine learning, deep learning models, including prediction models based on structured data, natural language processing models based on text data, graph neural network-based models, intelligent recommendation algorithms, and other mathematical models. I have good teamwork spirit, leadership and communication skills, and I can work collaboratively with team members from different backgrounds to solve problems efficiently.

Experience

• 科研人员 at Chan Molecular Epidemiology and Bioinformatics Laboratory
  Sep 2022 - Present · 3 yrs 10 mos

  • Conducted research on the application of machine learning and deep learning models in the fields of biology and medicine. • Focused on data collection, processing, model building, and optimization. • Conducted research on several topics, including lung adenocarcinoma-related gene prediction, drug redirection model building, causal relationship assessment between non-small cell lung cancer and microRNA and single nucleotide polymorphism, esophageal squamous cell carcinoma drug redirection model construction, 2019 novel coronavirus death risk factors based on machine learning, and bidirectional relationship assessment between sedentary behavior and neurological and psychiatric diseases, etc.

• 科研人员 at Hospital Authority Data Collaboration Laboratory
  Aug 2020 - Jun 2022 · 1 yr 11 mos

  • Conducted research on the development of a stroke patient risk assessment system based on machine learning and deep learning models. • Focused on data collection, processing, model building, and optimization. • Conducted research on several topics, including the development of a short-term mortality prediction model for stroke patients (using structured data models and natural language processing model), the construction of an intelligent medical decision-making system for stroke patients (using reinforcement learning networks), stroke category determination based on 3D-CT and MRI images, stroke location recognition (using image visual models), and causal relationship assessment between hemorrhagic stroke risk and red cell distribution width and mean red cell volume (using mathematical models).