Skip to main content
ENTER
Customer pulse

Research Themes

  • Medical Images Data Analytics
  • AI and Machine Learning
  • Computational Science

This area can involve computational chemistry/physics/biology/biochemistry. The applications under this category may span a wide range of applications including, but not limited to health.

  • Natural Language Processing

Technologies related to processing and understanding of human languages in the form of speech or text.

  • Health Data Science

Health Data Science is an interdisciplinary field and the study of health data. It uses scientific methods, processes, algorithms and systems to extract knowledge and insights from structured and unstructured health data. The goal of health data science is to gain insights and knowledge from health data.

Our group is a multidisciplinary team committed with the research and development of technology based on Data Science for healthcare. There are five core areas of Data Science that we apply, develop, and improve for healthcare: Artificial Intelligence, Big Data, Machine Learning, Internet of Things (IoT), and Blockchain. Our group consists experienced data scientists, clinician, and biologist. Our group brings together diverse groups of stakeholders – leaders from academic research, clinical medicine, healthcare providers, government, non-governmental organizations, and others to participate in collaborative research, education, and project in Health Data Science.

  • Data Privacy and Security

Recent years have seen an outburst in clinical and genomic data stockpiled in huge biomedical data warehouses. Access to this data offers a unique opportunity to undertake biomedical research and may improve quality of care, reduce healthcare costs and advance personalized medicine. However, the availability of such data for widespread research activities is dependent on the protection of participants’ privacy.

In fact, biomedical data sharing is governed by legislations that aim to ensure that private information is properly used and adequately protected when disclosed for research purposes (such as the Common rule, HIPAA, and GDPR). The legislations generally permit data sharing when Informed consents is available or when the data is adequately de-identified.

Current technological methods for privacy preservation are outdated and cannot provide adequate protection for current biomedical data. The inadequacy of current privacy protection method, and the pressing need to benefit from the large biomedical data warehouses being built worldwide is our main driver for seeking new innovative solutions. Our research tries to solve the privacy problem in multiple contexts through novel de-identification methods, novel consent mechanisms as well as novel privacy-preserving data-mining techniques.

Research Directions

  • Develop advanced open-source solutions for automated, intelligent, and explainable data-driven decision-making to boost the government and private sector performance and the rate of productivity.
  • Develop advanced graph-based technologies to facilitate rapid enhancements for decision-making.
  • Leverage blockchain technology for creating less but clean data and analytics.
  • Develop advanced data security and privacy strategies and solutions.
  • Address the missing link between big data and business value by developing fast and actionable data solutions.
  • Accelerate quantum computing research for better big data processes and analyses.
Jul 10, 2026