Tom Sullivan reported on the Big Data and Healthcare Analytics Forum:
The University of Mississippi Medical Center is poised to deliver EHR data to in-house patients, starting in the next two weeks, to help determine whether they are at risk for a heart attack in the immediate future.
That’s just one of the big data initiatives UMMC is undertaking, which also include using geomapping and what chief health information officer John Showalter, MD described as “fully automated deep machine learning within our EHR,” that the hospital system will go-live with in early December. […]
As recently as 2011 only about 10 percent of healthcare organizations were using analytics tools, according to Shelley Pryce, HIMSS director of payer and life sciences, adding that estimates suggest by 2016 that statistic will climb to 50 percent.
Diana Manos reports on the funding of “digital health” (without defining precisely what that encompasses):
Funding for digital health is expected to be almost double what it was in 2013, according to a new study from StartUp Health. And that growth shows no signs of slowing down anytime soon.
The study found 347 companies raised $5 billion through the third quarter of 2014. In all of 2013, 2.8 billion was raised for digital health.
Nilay Shah and Jyotishman Pathak are worth reading in full. Pay careful attention to how language and ambition subtly morph from prediction to customized intervention, which requires causal inference. But notice also how this is not made explicit. (This is not unique to this piece. It is very common.) I’ve bolded some passages where the prediction-causal inference transitions are made.
The National Institutes of Health recently launched a Big Data to Knowledge Initiative (BD2K) to enable the biomedical research community to better access, manage, and utilize big data. Some early work is also being pursued through large collaborations such as the National Patient-Centered Research Network (PCORnet) and the consortium Optum Labs, a research collaborative that has brought together academic institutions, health care systems, provider organizations, life sciences companies, and membership and advocacy organizations. […]
One of the earliest uses of big data to generate new insights has been around predictive analytics. In addition to the typical administrative and clinical data, integrating additional data about the patient and his or her environment might provide better predictions and help target interventions to the right patients. These predictions may help identify areas to improve both quality and efficiency in health care in areas such as readmissions, adverse events, treatment optimization, and early identification of worsening health states or highest-need populations. […]
For example, hospitals are starting to use graph analytics to evaluate the relationship across many complex variables such as laboratory results, nursing notes, patient family history, diagnoses, medications, and patient surveys to identify patients who may be at risk of an adverse outcome. Better knowledge and efficient assessment of disparate facts about patients at risk could mean the difference between timely intervention and a missed window for treatment. […]
The insights from big data have the potential to touch multiple aspects of health care: evidence of safety and effectiveness of different treatments, comparative outcomes achieved with different delivery models, and predictive models for diagnosing, treating, and delivering care. […]
Relying on the evidence from randomized controlled trials has been a gold standard for making practice-changing decisions. While in many cases such trials may be necessary and justified, it will be critical to identify where the evidence generated by big data is adequate enough to change practice. In other cases, big data may generate new paradigms for increasing the efficiency of randomized clinical trials.
For example, as new knowledge is gained about the comparative benefits of second-line agents for treatment of diabetes, policy makers and expert groups may consider using this information to develop guidelines or recommendations or to guide future randomized trials. […]
By analyzing the data on their treatment outcomes, we may be able to learn something that will help us create better protocols for caring for them. The hope is to gain insights about what works and for whom.
The piece also comments on machine learning and natural language processing.
Jackie Crosby reports on big data efforts by Mayo Clinic and partners:
For decades, doctors, pharmacies and insurance companies have routinely collected vast troves of information about the care and well-being of millions of Americans for their own use. Now, aided by technology and driven by unrelenting pressure to reduce costs, the industry is scrambling to connect all of this disparate data in hopes of finding the best ways to treat the sick. […]
Although the Rochester-based health system is investing in a number of promising big data projects, an unfolding partnership with insurance giant UnitedHealth Group is its most ambitious. […]
Researchers who query [the] database [they and others contributed to] can access millions of patients across the decades, and compare whether one treatment worked better than another and how much was spent. […]
For the first time, it is possible to connect tens of millions of data sets from almost every facet of the health system — office visits, surgeries, lab tests, images, medical devices, prescriptions and more — and judge whether people got better or worse depending on what kind of care they got.
“This is a key point in history, where data that’s already being collected is really going to become the dominant driver in what happens in health care,” said Philip Bourne, who is leading the federal government’s push into big data for the National Institutes of Health. […]
“Out of more than 100 million patients, somebody’s got to be just like your patient — or close enough,” [said Dr. Rozalina McCoy, a Mayo Clinic endocrinologist]. […]
“Clinical trials are important,” McCoy said. “But ultimately with scarce resources, what if we can answer the question in a year by running models? It’s not a replacement for clinical trials, but it’s food for thought about research funding.”
