UCL Institute of Health Informatics

Dr Alvina Lai

Dr Alvina Lai

Associate Professor

Institute of Health Informatics

Faculty of Pop Health Sciences

Joined UCL
3rd Jun 2019

Research summary

I have worked on a wide range of topics, ranging from evolution to health genomics. I am particularly interested in how we can use real-world data to tackle cancer and infectious diseases. I would also like to expand my research to include non-communicable diseases such as metabolic disease, cardiovascular disease and diabetes.  


Cancer is a highly heterogeneous disease characterised by a myriad of subtypes. Despite advancement in healthcare services and treatment regimens, cancer patients still face significantly higher mortality rates and impairments in their quality of life. Cancer patients often have numerous interactions with healthcare systems, enabling the use of electronic health records for the generation of models on clinical events associated with cancer emergence and progression. Furthermore, the presence of additional disease(s) in an individual may influence the timing of cancer diagnosis, treatment and prognosis, as do demographic and socioeconomic factors.


We are interested in modelling cancer trajectories using electronic health records and multi-omics data to help bring us a step closer to achieving personalised care and to reveal how cancers progress from symptoms to neoplasm to death and how risk factors may influence these trajectories.


Early cancer diagnosis is of paramount importance if we are to improve survival chances and reduce treatment costs. We employ machine learning tools to predict the likelihood of cancer based on disease-specific and disease-agnostic risk factors. Details on how cancer phenotypes are choreographed throughout an individual’s lifespan will have immense translational implications as this information can improve cancer diagnoses, prognosis stratification, treatment recommendation/efficacy and resource utilisation.

Teaching summary

Providing exceptional mentorship is integral to my plan in making enduring contributions to the scientific community. I continue to play an active role in higher education teaching and research mentoring. As a versatile educator, I have experience in curriculum development and teaching a wide range of topics including: Cancer Biology, Research Methods, Quantitative Methods and Statistics, Cells and Genes, Biochemistry, Organisms, Molecular Genetics, Genome Evolution and Evolutionary Biology. As a testament to my pedagogical skills, I was awarded the Excellence in Teaching Award three times for scoring above 4.5/5.0 marks in the students’ evaluation of teaching.

I am involved in the education of the next generation of data scientists through my teaching roles in the MSc Health Data Analytics and MSc Health Data Science courses at UCL. I also contribute to several other MSc modules where student learning takes the form of traditional lecturing or a more contemporary blended learning approach (online and face-to-face).


Massey University
Doctorate, Doctor of Philosophy |


I am Associate Professor at UCL Institute of Health Informatics, experienced in both dry- and wet-lab research. My move to the University of Oxford for postdoctoral training is supported by two prestigious international peer-reviewed fellowships; EMBO and Human Frontier Science Program.

With a transdisciplinary background, my research track record spans two taxonomic kingdoms (animals and plants). Within the animal kingdom, my research has involved three phyla (vertebrates [humans], arthropods and platyhelminths) – ranging from topics on organismal animal biology using simple in vivo models for therapeutic insights to health informatics.

We are interested in harnessing real-world data collected in the form of electronic health records to understand how we can improve health and healthcare systems using data at scale to generate meaningful and actionable clinical insights. Employing health data linked across primary (GPs) and secondary (hospitals) care, we aim to use machine learning tools to gain population-wide insights into how to manage and treat diseases in ways that are most effective. To realise the underlying capabilities of electronic health records, results must be intricately linked to genomics data – our group also utilise multi-omics datasets from public repositories to help advance data science at scale, improve health, prevent the onset of disease, improve early diagnosis and innovate therapy.

We are a multi-disciplinary group of individuals connected through our enthusiasm of using data to save lives. We collaborate with data scientists, biologists, computational scientists, clinicians, epidemiologists and theoreticians to answer questions that are seemingly intractable and yet have real-world implications.

As long as you share a passion for data science, we invite you to get in touch if you would like to join the group as a student or a postdoctoral colleague. We are also keen to hear from potential collaborators to discuss areas of research synergy and ways in which we can contribute to your research.