The healthcare industry is on the cusp of a data and analytics golden age. We are moving steadily from a volume-based system to one that seeks to answer the overarching question, “Are we delivering value?” on a daily basis. Enterprise electronic medical record systems are ubiquitous, generating rich clinical and operational datasets. New technologies now provide access to cheap, unlimited data storage and processing power—good news, as the volume of healthcare data grew nearly 900% from 2016 to 2018 . Breakthroughs in methods and tooling have brought machine learning, natural language processing, artificial intelligence, and other advanced analytic techniques to the forefront. Interoperability standards continue to advance.
Category: Industry
-
Why causality is central to questions of algorithmic bias
Healthcare organizations increasingly rely on algorithms to guide decisions regarding patient care. If bias exists in the algorithms, organizations run the risk of treating patients unfairly. Although evidence of such bias has been documented, the good news is that steps can be taken to reduce bias.
-
The specter of failure and the specter of success
The disastrous launch
It’s been a warm winter, but the palm trees are nonetheless shrink-wrapped up and down Atlantic Avenue. Virginia is not their native environment, and their winter discomfort is the price we have to pay to maintain the fiction that Virginia Beach is a summer paradise.
-
Making the most of run charts for healthcare performance improvement
The run chart is a classic tool of quality improvement work. Depicted as a line graph, it provides insight into changes in a specific performance measure over time. The chart’s x axis presents chronological time intervals, while the y axis presents counts or rates of the data being measured.
-
UCLA Health: overcoming racial bias in predictive algorithms
Algorithmic bias—what it is, who it impacts, what it causes, and how it is best overcome—is a topic of increasing interest in healthcare.
-
When better is better than best: predictive model development
The field of machine learning (ML), a subset of artificial intelligence in which computer algorithms use statistics to find patterns in data that can predict future outcomes, is undergoing rapid development. New methods, many of which are available through open source tools, are highly flexible in that they can automatically approximate complex, nonlinear functional relationships between predictors and response variables.
-
Mastering change: the Behavioral Change Stairway Model
The imperative to collaborate to achieve common goals has long defined human interactions. Initially, this imperative was rooted in survival, but working in partnership is no less important today than it was for our ancestors.
-
A new solution for participants in CMS’s Primary Cares Initiative
NASHVILLE, Tenn., October 16, 2020—In response to the Centers for Medicare & Medicaid Services announcement of its new Primary Cares Initiative, Ursa Health has released a version of Ursa Studio, its ground-breaking analytics development platform, that will make it easier for organizations to meet the initiative’s goals. The Primary Cares Initiative is designed to spur value-based transformation in primary care by reducing administrative burdens, which will in turn accelerate innovations that improve both outcomes and the healthcare experience for Medicare beneficiaries.
-
Physician-defined measurement reduces SNF readmissions
Ursa Health recently worked with an integrated delivery system to reduce readmissions from skilled nursing facilities (SNFs). The geriatrician charged with leading the effort had summary data from the CMS QIO about the hospital’s readmission rates, but these did not help her to identify specific changes or to engage her colleagues, the hospitals, and the SNFs.
-
Working with dates and timezones in JavaScript: a survival guide
Many JavaScript developers approach dealing with dates and timezone issues with apprehension. And indeed, it’s easy to get turned in a knot as you’re trying to get times working sensibly for all your users. Nor are date and timezone problems the sort of issue that a great library can make easy. But with a solid understanding of the fundamentals, you’ll find that thinking through how to work with dates in JavaScript becomes a tractable problem.