Last winter, UK witnessed its worst flu season, as death rate tripled and doctors saw a major increase in patients. Some found the effects of their flu vaccine in vain because unexpected strains were looming. Generally, flu vaccine is developed six months ahead of a presumable epidemic season, sometimes, changes in weather and flu virus mutations will alter clinicians’ predictions, reducing the effectiveness of vaccine.
This is when machine learning can help. To enable a computer to learn on its own and make sound decisions thereafter is vital but often, clinicians are also armed with the necessary skills to make diagnosis. Thus, adopting an expensive technology to perform something ubiquitous may violate the efficiency and cost-effective values which most hospitals work towards to.
However, a different story runs for an epidemic outbreak prediction. Coupled with data from historic records, climate, demographics and geography, outbreak severity can be accurately predicted with the use of machine learning and this is especially important for developing countries with life-threatening epidemic seasons such as Malaria.
On the other hand, deep learning is useful to process multiple layers of nonlinear data or to make accurate decisions for a complex problem like outcome of clinical trials. Patients with the same diagnosis may react differently based on their demographics, genetic predisposition and health, so do drugs.
By predicting side effects and activation pathways, deep learning promises researchers with reliable directions of how to improve the efficiency of the clinical trials and hasten the drug development process.
While everything renders possibilities, it become clear that clinicians need to recognize when is the best time to employ machine or deep learning. With that, a group of experts are coming together to give share their insights and stories.
You can register for this exciting panel discussion here.
Session Focus: Update on Machine and Deep Learning
When: Thursday, December 13th 2018 (14.00-15.00)
Explore the possibilities of machine and deep learning in medicine and find out which areas render the best opportunities?
Attendees will gain the following knowledge:
Be informed of the latest use of machine learning and deep learning methods in various medical developments.
Review the practicality of adopting machine learning and deep learning in different medical settings.
Brainstorm better approaches of inculcating relevant talents into the medical sector for the development of machine learning and deep learning.
Benefits from first-hand information given by machine learning and deep learning frontiers.
Crystal Valentine, Vice President of Technology Strategy, MapR Technologies, USA
Leila Entezam, EQ-Centered Design Consultant, LEZAM.IT, USA
Christina Chen, Harvard Medical School, Nephrologist Beth Israel Deaconess Medical Center, USA
Saurabh Gombar, Clinical instructor, Stanford Health Care, USA