Experimental Evaluation and Development of a Silver-Standard for the MIMIC-III Clinical Coding Dataset
This work addresses data quality issues for researchers and practitioners in clinical NLP, but it is incremental as it builds on existing validation concerns without introducing a new coding method.
The authors tackled the problem of unreliable gold-standard codes in the MIMIC-III clinical coding dataset by developing an experimental methodology to assess code validity, showing that the most frequently assigned codes are under-coded by up to 35%.
Clinical coding is currently a labour-intensive, error-prone, but critical administrative process whereby hospital patient episodes are manually assigned codes by qualified staff from large, standardised taxonomic hierarchies of codes. Automating clinical coding has a long history in NLP research and has recently seen novel developments setting new state of the art results. A popular dataset used in this task is MIMIC-III, a large intensive care database that includes clinical free text notes and associated codes. We argue for the reconsideration of the validity MIMIC-III's assigned codes that are often treated as gold-standard, especially when MIMIC-III has not undergone secondary validation. This work presents an open-source, reproducible experimental methodology for assessing the validity of codes derived from EHR discharge summaries. We exemplify the methodology with MIMIC-III discharge summaries and show the most frequently assigned codes in MIMIC-III are under-coded up to 35%.