This year I’ve had the pleasure of participating in a team at MIT identifying characteristics that make patients likely to be intensive care unit “Frequent Fliers” - patients with multiple ICU admissions in a short time span. This series will explore the implementation of text-based patient phenotyping we use as …

View comments.

We saw in the previous post that there is promise to using ICD9 codes for pre-classifying encounters more likely to have our concepts of interest. In this post we’ll walk through building simple logistic regression classifiers based on a training data set, and will evaluate their performance on a …

View comments.

With the background work done in the previous posts, let’s get to the meat of the problem. I’m currently working with a team from an excellent MIT course, Secondary Analysis of Health Records, led by Dr. Leo Anthony Celi. My team is composed of 4 clinicians and 3 …

View comments.

In the previous post I showed a convenient way to navigate the ICD9 hierarchy with Python, now let’s use that to extract the full taxonomy of ICD9 codes for patients who we’ll using to train a classifier. In this post we’ll be extracting the original ICD9 codes …

View comments.

One tricky thing to deal with in the transition from MIMIC II to MIMIC III has been that IDs have changed and are sometimes missing, so work that a collaborating team did to annotate patient notes in MIMIC II is not translatable to MIMIC III. This notebook shows one way …

View comments.