This month we spent 5 minutes with Nicholas Ho. Nick is the translational data scientist at the Brain and Mind Centre.
Can you please tell us about a day in your life?
As the translational data scientist at the Brain and Mind Centre at the University of Sydney, I provide data science support for research projects in the brain and mind sciences. Data science – as beautifully explained by Prof Jeannette Wing from Columbia University – is the “extraction of value from data” and this requires a range of methods including visualisation, machine learning, statistics and bioinformatics.
The morning commute is a great opportunity for me to catch up on emails, plan for the day ahead and catch up on the latest AFL and NRL news (proud Sydney Swans and Parramatta Eels supporter). Once I’m in the office, I start by checking the results of any analysis I’ve run overnight making sure that no errors have occurred. On a typical day, I would be working on multiple projects. For example, in the morning I might be developing a machine learning model to predict suicide in young people, by noon visualising the distribution of problem gambling in NSW, and in the afternoon developing a less invasive diagnostic tool for glioblastoma, an aggressive form of brain cancer, with micro RNA sequencing technology. Throughout the day, I meet with researchers to translate these latest findings into insights and I collaborate closely with my data science peers at the Centre for Translational Data Science and Sydney Informatics Hub in applying cutting-edge techniques to our research projects.
A day in the life of a data scientist is pretty good, I’m blessed to be able to work with researchers whose passion for their fields is contagious.
How do you define digital health?
Digital health is broadly the application of technologies to better understand and improve our health as a population and as individuals. As the question suggests, everyone has a different definition of digital health. In my work, digital health has a strong research flavour with the latest technologies, such as high throughput omics, and analytics techniques, such as machine learning and artificial intelligence. The commonality across definitions is that the growth of digital health can create more thorough data capture, greater research opportunities, faster clinical implementation of the latest translational research, informed distribution of limited health resources and wider dissemination of health education to the public.
What do you think will enable digital health projects and innovations to succeed?
As a data scientist in health research, success relies on multiple factors. First is the quality and quantity of data available. In computer science, there is the adage of “garbage in, garbage out” where the quality of the output is dependent on the quality of the input. Second, is modelling the health phenomena of interest which relies on sophisticated data science techniques . Third, is stakeholder buy-in from digital health consumers to clinicians and to policymakers. The third factor is quintessential for digital health innovations to achieve its goals.
Have you come across any surprises or challenges along the way?
The diversity in health research still surprises me to this day, but so has the similarity in goals across all these. I’ve worked previously in children’s cancer research at Westmead, in mosquito and malaria research in London and now in the brain and mind sciences at Sydney. The scale of data varies and the research objective might require different data science techniques, but the strong common goal we were all working towards is improving people’s health.
Connect with Nick: https://www.linkedin.com/in/nicholasklho/
A very big thank you to Nick Ho for being our June member feature.