Earlier this month, the European Medicines Agency held a workshop in London where it became very evident to the attendees just how much science that is required to happen in order to allow medical treatments to be developed and approved more quickly, and more personalised.
Among the attendees was IBM Watson and Google Cloud Platform, who teamed up in order to answer the difficult questions to which there still are few answers, Nature, the International Weekly Journal of Science writes.
The questions ranged from: “How many data are adequate to reliably predict clinical effect”, Which data sets are useful”, “How can these be managed”, and the list goes on and on. The most crucial question, however, was: “Is academia training enough mathematicians and medical-data scientists, who will have to develop and harness all this new potential?”, where the clear answer currently is no.
AI can be applied to analyse big data sets within medicine, such as genomics, transcriptomics and proteomics (this describes our genomes, identifies which of our genes are being expressed, and catalogue all proteins in a tissue sample).
“The presence or absence of a particular gene variant can put people in high- or low-risk groups for various diseases and identify in some cases which people with cancer are likely to respond to certain drugs”, Nature writes.
However, single molecular data sets do not contain enough information in order to predict an individual’s medical fate. Integrating different types of molecular data could potentially tell more however, this still remains a computational challenge.
“Even more would emerge if an individual’s molecular data were placed in the context of their physiology, behaviour and health. Electronic health records, the numbers of which are skyrocketing, could be useful here. So could disease registries, hospital and health-insurance records, as well as research publications and clinical-trial data”, Nature writes.
Today, data can be gathered from anything from apps to social media platforms, which have resulted in extreme masses of data, which is challenging to analyse. In order to collect and hold all this data within strict privacy regulations, non-negotiable for medical data, is another challenge too.
IBM and Hewlett-Packard are currently building systems that keeps the data locally, while allowing algorithms to “dip into them”, but the data is not transmitted anywhere else. “Now, the big question for scientists is how to take the next step to convert these artistic sketches of potential into scientific knowledge”, Nature writes.
Big data has the potential of reducing the amount of animals used in drug testing too, as well as the recruiting of patients to actual trials, which is another example of how AI can contribute to improving areas of industries that have been “problematic” before.
This article was first published at: http://www.nature.com/news/the-power-of-big-data-must-be-harnessed-for-medical-progress-1.21026
Photo Credit: Google