Missing social history makes automated medical coding challenging

Prerequisites

• [ x] Put an X between the brackets on this line if you have done all of the following:
  • Checked the online documentation: https://mimic.mit.edu/
  • Checked that your issue isn't already addressed: https://github.com/MIT-LCP/mimic-code/issues?utf8=%E2%9C%93&q=

Description

Automated medical coding (also called medical code prediction) is a growing machine learning task that aims to predict medical codes given a discharge summary. MIMIC-IV has become a popular dataset to train and evaluate such models. However, there is an issue. Since your de-identification algorithm removed the social history section, certain annotated medical codes are impossible to predict. For instance, the medical codes representing whether the patient smokes (e.g., F17.210 and Z87.891) are often annotated in MIMIC-IV without being mentioned in the discharge summary. This is because of the missing social history.

The consequences of the missing section are that the models are trained on labels that are impossible to predict and are evaluated unfairly every time the necessary information would have been in the social history. Consequently, MIMIC-IV is a noisier dataset for automated medical coding than MIMIC-III (MIMIC-III contains the social history).

Is there a way to de-identify the discharge summaries without removing the social histories?

Start by reviewing the MIMIC-IV online documentation and the issue's examples of missing social history and affected codes. Determine whether discharge summaries can retain social histories while meeting de-identification requirements; done would require a documented, validated approach rather than a small repository edit.