Last year we reported on the presentation from Jennifer Quigley, Director at Registry & Bio Repository, about her use of Big Data in fighting cancer. The work that she was doing centred around the collection of data from pre and post treatment patients.
Through the use of extensive data collection techniques it is possible to create predictive models that allow doctors to accurately see how patients will react to treatments and whether one treatment may work better for one person or another. The work that her and the Registry & Bio Repository is doing is fantastic, but we wanted to revisit the subject given both its importance and progress over the last 6 months.
One of the biggest developments has been the more widespread use of IBM Watson, allowing for AI to be used in diagnosis and treatment of cancer. The use of the computer allows doctors to see which drugs are most likely to be effective in the treatment of their particular cancer, but given the extensive history that it holds, also allows them to investigate other drugs that are not necessarily specifically for cancer treatment. Given the huge database behind the technology, it means that it can analyze the effects that these drugs have on the body and this can then be used to target specific forms of cancer.
It is not only vast databases that exist across every type of cancer, the Dragon Master Foundation is a prime example of looking in detail at niche areas. The idea behind this foundation is to take tissue samples of brain tumours in children from five paediatric hospitals with the goal of creating an extensive database for one particular cancer type.
In terms of databases this one may be able to create a fairly large set, but what many people don’t realize is that our own genome sequencing is an almost unfathomable amount of data. The size of the database for a single person could technically be anything up to 150 Zettabytes (although this would involve taking the maximum amount of data from every cell in the human body). However, generally speaking it is around 200GB for the sake of usability. The ability to contrast and compare these across thousands of patients allows for in-depth analysis of the causes of cancer as well as the people who are most susceptible to specific types of cancer.
New technology is helping to identify potential cancer sufferers whilst also aiding those who are currently afflicted by the disease. Through looking at cancer in a systematic and data driven way, the potential for its prevention increases. If we can continue to look at it in this way the prediction that nobody under the age of 80 will die of cancer by 2050, may become a reality.