Automatic multilabel detection of ICD10 codes in Dutch cardiology discharge letters using neural networks
Open Access
- 26 February 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in npj Digital Medicine
- Vol. 4 (1), 1-10
- https://doi.org/10.1038/s41746-021-00404-9
Abstract
Standard reference terminology of diagnoses and risk factors is crucial for billing, epidemiological studies, and inter/intranational comparisons of diseases. The International Classification of Disease (ICD) is a standardized and widely used method, but the manual classification is an enormously time-consuming endeavor. Natural language processing together with machine learning allows automated structuring of diagnoses using ICD-10 codes, but the limited performance of machine learning models, the necessity of gigantic datasets, and poor reliability of terminal parts of these codes restricted clinical usability. We aimed to create a high performing pipeline for automated classification of reliable ICD-10 codes in the free medical text in cardiology. We focussed on frequently used and well-defined three- and four-digit ICD-10 codes that still have enough granularity to be clinically relevant such as atrial fibrillation (I48), acute myocardial infarction (I21), or dilated cardiomyopathy (I42.0). Our pipeline uses a deep neural network known as a Bidirectional Gated Recurrent Unit Neural Network and was trained and tested with 5548 discharge letters and validated in 5089 discharge and procedural letters. As in clinical practice discharge letters may be labeled with more than one code, we assessed the single- and multilabel performance of main diagnoses and cardiovascular risk factors. We investigated using both the entire body of text and only the summary paragraph, supplemented by age and sex. Given the privacy-sensitive information included in discharge letters, we added a de-identification step. The performance was high, with F1 scores of 0.76–0.99 for three-character and 0.87–0.98 for four-character ICD-10 codes, and was best when using complete discharge letters. Adding variables age/sex did not affect results. For model interpretability, word coefficients were provided and qualitative assessment of classification was manually performed. Because of its high performance, this pipeline can be useful to decrease the administrative burden of classifying discharge diagnoses and may serve as a scaffold for reimbursement and research applications.Keywords
This publication has 27 references indexed in Scilit:
- DEDUCE: A pattern matching method for automatic de-identification of Dutch medical textTelematics and Informatics, 2018
- Automatic ICD-10 coding algorithm using an improved longest common subsequence based on semantic similarityPLOS ONE, 2017
- Automatic Diagnosis Coding of Radiology Reports: A Comparison of Deep Learning and Conventional Classification MethodsPublished by Association for Computational Linguistics (ACL) ,2017
- ICD-10: History and ContextAmerican Journal of Neuroradiology, 2016
- Automatic classification of diseases from free-text death certificates for real-time surveillanceBMC Medical Informatics and Decision Making, 2015
- Diagnosis code assignment: models and evaluation metricsJournal of the American Medical Informatics Association, 2014
- Mining electronic health records: towards better research applications and clinical careNature Reviews Genetics, 2012
- Introduction to Scientific Programming and Simulation Using RPublished by Taylor & Francis Ltd ,2009
- Reliability of diagnoses coding with ICD-10International Journal of Medical Informatics, 2008
- Automating the Assignment of Diagnosis Codes to Patient Encounters Using Example-based and Machine Learning TechniquesJournal of the American Medical Informatics Association, 2006