The Tuva Project Newsletter -- Mar 6 2026

Over the past couple weeks I’ve had several conversations debating Tuva’s logic for merging claims into acute IP encounters. Under-merge claims and you’ll end up with more encounters, leading to lower average cost per visit and average length of stay, among other issues. Over-merging has the opposite problem.

Ultimately we decided the existing logic makes sense and shouldn’t be changed.

But during this discussion we realized we had a lot of questions about same-day readmissions i.e. when a patient is discharged from the hospital and comes back the same day. For example:

• How often do same-day readmits happen?

• Where are patients being readmitted from (Home, Home Health, SNF/Rehab, Another Facility, etc.)?

• What percent of same-day readmits have the same primary diagnosis?

We ended up doing a fair amount of research on the topic and wrote it up in an article here, including code you can copy and run on any dataset in the Tuva data model.

If you’ve worked with claims datasets before then you know they come in all shapes and sizes, with all sorts of data quality problems. Often you’ll get a single medical claims data table that has both professional and institutional claims mixed in but no field to easily distinguish between the two types of claims. In that case, what do you do? Fortunately there are a few key heuristics you can follow which Coco walks through in this week’s knowledge video.

Here are some exciting new healthcare data & analytics jobs from the past week. As always, you can find these postings and more in the Tuva Slack #jobs channel.

• Midwest Data is hiring a Healthcare Analytics Engineer

• Aligned Marketplace is hiring a Data Engineer

• Complete Orthopedics is hiring a Data Architect

Thanks for reading and if you’d like to receive more content like this every week subscribe below. To learn more about the Tuva Project visit www.thetuvaproject.com.