Big Data solutions for cancer research
In the UK alone, there are over 350,000 new cases of the disease each year, meaning that every two minutes someone in the UK is diagnosed with the illness.
04 June 2020
By Mariusz Bogacki, Researcher and Science Communicator, Edinburgh
Cancer is a disease caused by an uncontrolled division of abnormal cells in a part of the body, and is one of the main healthcare challenges of modern times. In the UK alone, there are over 350,000 new cases of the disease each year, meaning that every two minutes someone in the UK is diagnosed with the illness. Despite significant improvements in cancer treatment in recent years, the disease accounts for 165,000 deaths every year. While we are still a long way from finding a cure for cancer, a convergence of biomedical research with developments in the growing field of Big Data offers some promising solutions.
In modern healthcare systems, from population cancer registries and electronic health records to large-scale genetic sequencing studies, collecting data is a common practice. However, processing and analysing such large amounts of data using traditional database and software techniques has become a complex and difficult task. Luckily, this is exactly what Big Data Science excels at: storing, analysing and extracting valuable information from massive volumes of both structured and unstructured data. Among the most promising aspects of Big Data cancer research, is the rapid acquisition and generation of huge amounts of information globally, and further study of it, using Machine Learning (ML) algorithms.
Thanks to Big Data, researchers and medical professionals are already able to collect larger than ever, highly detailed sets of information about a patient’s medical history, the particular type of illness they suffer from, and even monitor cancer cells growth and healthy cells death. Such data is being securely stored on online platforms accessible to scientists around the world for further analysis.
Large amounts of medical information collected nationally and internationally can then be analysed using ML algorithms, a form of artificial intelligence capable of improving automatically through experience. Databases are analysed using high-speed ML algorithms that scan and interact with data, ensuring high processing accuracy. As a result, biotech researchers are now able to see a much more detailed picture of an illness’ progress, compare treatments based on a large statistical sample and, more importantly, predict the next stages of its development.
The possibilities stemming from the convergence of biology, medicine, mathematics and technology seem infinite. In the near future, perhaps we could even see data scientists and researchers working alongside medical practitioners in hospitals or local GP practices.