Big Data and Healthcare Analytics Forum kicks off Monday: What to expect

By  | 

The HIMSS and Healthcare IT News Big Data and Healthcare Analytics Forum begins Monday morning in Boston.

Our team of reporters and editors has been gleaning insights about what actionable advice, basics like blocking and tackling, and visionary trends will be discussed at the event.

The core reality check found that healthcare as an industry is ready to move beyond the rhetoric and put data and information into action. And even though that won’t be easy, it is already happening in places like Charlotte, North Carolina and Blairsville, Georgia.

The following articles offer insights from expert speakers, lessons learned, hard-fought challenges, and a glimpse into the future of artificial intelligence, cognitive computing and machine learning.  

⇒ Big Data: Healthcare must move beyond the hype 
It’s a common situation with emerging technologies that the buzz around their vast potential promises more than real-world use actions deliver. But the difference with Big Data is the way healthcare refers to it as one big thing when, in reality, there are many Big Data technologies. What needs to happen? Good design and then a proper application of technologies to bridge technological possibilities with what hospitals really need to accomplish. 

⇒ Tips for reading Big Data results correctly
Big data is not going to be easy. Healthcare professionals are bound to make mistakes and take miscues from data sets along the way. MIT economist Joseph urges healthcare executives and caregivers not to over-interpret results and, instead, stick to strict research designs. 

⇒ Charlotte hospitals analyze social determinants of health to cut ER visits 
Facing an influx of immigrants coming into emergency departments for what turned out to be primary care needs, hospitals in the city got to know patients better by building a Big Data analysis model to study social determinants of health. It worked. The next step: Creating connections that more effectively align patients with the most appropriate resources. 

 MIT professor’s quick primer on two types of machine learning for healthcare 
John Guttag heads up the Data Driven Inference Group at MIT’s Computer Science and Artificial Intelligence Laboratory. Guttag broke down for us the two types of machine learning that matter most to healthcare organizations, those being supervised and unsupervised. And even though many of the machine learning, artificial intelligence and cognitive computing technologies available today from the likes of IBM Watson, Google, Microsoft and others have gained more traction in different industries, Guttag’s message for hospitals is to use today’s tech right now. 

⇒ Must-haves for machine learning to thrive in healthcare
To help health entities move forward with using today’s machine learning technologies Guttag also outlined what it takes to succeed in the new world with its growing sets of aggregated data, federal rules around information access and maturing technologies as the practices of machine learning move toward critical mass.