All you need to know about Healthcare Data & Analytics

Healthcare data, and by extension healthcare analytics, can be a confusing and somewhat opaque space (to put it mildly). There are many datasets available, both public and private, for a researcher, data scientist, or strategist to leverage. It can be very difficult to understand the nuances of each of those datasets, how to extract value from them and how to combine them so that the whole is more than the sum of its parts.

image created by Midjourney — “vibrant healthcare database ecosystem”

At Trilliant Health we have spent years sifting through datasets: organizing and re-organizing, appending and culling, joining and normalizing, all to generate useable and useful analytics through which our clients can make informed decisions. Our mission is to provide data and expertise to the healthcare economy such that organizations can maximize their ability to deliver care to patients. While this isn’t a new concept, some of the capabilities to successfully deliver it are: the advent of powerful distributed-compute systems in the last decade, the digitization of health care records and claims data and new laws that have made private datasets public.

If it were as simple as having access to the best data and technology, this problem would have already been solved by big tech companies like Google or Amazon. Healthcare delivery in the United States is complex, and even the most brilliant engineers & data scientists in the world (which we think we’ve got a few of) can’t deliver value without understanding how source data is generated or resultant datasets will be used. Our experts in healthcare strategy, economy, coding and operations contribute as much value to our products as our technical teams; it is through their insights that we are able to provide such value to our clients. The intersection of technical expertise and healthcare expertise is core to our function as a business; without it, we would simply be offering query-based access to a rather large database.

In a series of upcoming articles, we will explain what we do, how we do it and why we’ve chosen to frame and approach the problems in the manner presented. We’ve learned many lessons along the way and hope to share some of those so that others don’t have to struggle through the same mire.

We hope to publish a new article regularly, so stay tuned if we haven’t covered your favorite topic yet; chances are we will!

Series Outline

1. Care and feeding of Healthcare Datasets: common sources, reference datasets and pitfalls therein.
2. An introduction to claims data. (part 1)
3. An introduction to claims data: where the wild things are. (part 2)
4. What is a visit?
5. Why do I need a Provider Directory?
6. How to build a Demand Forecast.
7. Health Plan Price Transparency (things will get really interesting)…

We also have a few supplementary references:

1. Healthcare Data Glossary
2. CMS 1500 Claim Form Reference

If you have any comments, suggestions for future topics or other questions, please let me know!