Mimic-IV-ICD: A new benchmark for eXtreme MultiLabel Classification
Abstract
Clinical notes are assigned ICD codes - sets of codes for diagnoses and procedures. In the recent years, predictive machine learning models have been built for automatic ICD coding. However, there is a lack of widely accepted benchmarks for automated ICD coding models based on large-scale public EHR data. This paper proposes a public benchmark suite for ICD-10 coding using a large EHR dataset derived from MIMIC-IV, the most recent public EHR dataset. We implement and compare several popular methods for ICD coding prediction tasks to standardize data preprocessing and establish a comprehensive ICD coding benchmark dataset. This approach fosters reproducibility and model comparison, accelerating progress toward employing automated ICD coding in future studies. Furthermore, we create a new ICD-9 benchmark using MIMIC-IV data, providing more data points and a higher number of ICD codes than MIMIC-III. Our open-source code offers easy access to data processing steps, benchmark creation, and experiment replication for those with MIMIC-IV access, providing insights, guidance, and protocols to efficiently develop ICD coding models.
Cite
@article{arxiv.2304.13998,
title = {Mimic-IV-ICD: A new benchmark for eXtreme MultiLabel Classification},
author = {Thanh-Tung Nguyen and Viktor Schlegel and Abhinav Kashyap and Stefan Winkler and Shao-Syuan Huang and Jie-Jyun Liu and Chih-Jen Lin},
journal= {arXiv preprint arXiv:2304.13998},
year = {2023}
}
Comments
Benchmark, Multilabel, Classification