Falter Maarten, Godderis Dries, Scherrenberg Martijn, Kizilkilic Sevda Ece, Xu Linqi, Mertens Marc, Jansen Jan, Legroux Pascal, Kindermans Hanne, Sinnaeve Peter, Neven Frank, Dendale Paul
Faculty of Medicine and Life Sciences, Hasselt University, Agoralaan gebouw D, 3590 Diepenbeek, Hasselt, Belgium.
Heart Centre Hasselt, Jessa Hospital, Stadsomvaart 11, 3500 Hasselt, Belgium.
Eur Heart J Digit Health. 2024 Feb 9;5(3):229-234. doi: 10.1093/ehjdh/ztae008. eCollection 2024 May.
ICD codes are used for classification of hospitalizations. The codes are used for administrative, financial, and research purposes. It is known, however, that errors occur. Natural language processing (NLP) offers promising solutions for optimizing the process. To investigate methods for automatic classification of disease in unstructured medical records using NLP and to compare these to conventional ICD coding.
Two datasets were used: the open-source Medical Information Mart for Intensive Care (MIMIC)-III dataset ( = 55.177) and a dataset from a hospital in Belgium ( = 12.706). Automated searches using NLP algorithms were performed for the diagnoses 'atrial fibrillation (AF)' and 'heart failure (HF)'. Four methods were used: rule-based search, logistic regression, term frequency-inverse document frequency (TF-IDF), Extreme Gradient Boosting (XGBoost), and Bio-Bidirectional Encoder Representations from Transformers (BioBERT). All algorithms were developed on the MIMIC-III dataset. The best performing algorithm was then deployed on the Belgian dataset. After preprocessing a total of 1438 reports was retained in the Belgian dataset. XGBoost on TF-IDF matrix resulted in an accuracy of 0.94 and 0.92 for AF and HF, respectively. There were 211 mismatches between algorithm and ICD codes. One hundred and three were due to a difference in data availability or differing definitions. In the remaining 108 mismatches, 70% were due to incorrect labelling by the algorithm and 30% were due to erroneous ICD coding (2% of total hospitalizations).
A newly developed NLP algorithm attained a high accuracy for classifying disease in medical records. XGBoost outperformed the deep learning technique BioBERT. NLP algorithms could be used to identify ICD-coding errors and optimize and support the ICD-coding process.
国际疾病分类（ICD）编码用于住院病例分类。这些编码用于行政、财务和研究目的。然而，已知会出现错误。自然语言处理（NLP）为优化该过程提供了有前景的解决方案。研究使用NLP对非结构化医疗记录中的疾病进行自动分类的方法，并将其与传统的ICD编码进行比较。
使用了两个数据集：开源的重症监护医学信息库（MIMIC）-III数据集（n = 55,177）和比利时一家医院的数据集（n = 12,706）。使用NLP算法对“心房颤动（AF）”和“心力衰竭（HF）”诊断进行自动搜索。使用了四种方法：基于规则的搜索、逻辑回归、词频-逆文档频率（TF-IDF）、极端梯度提升（XGBoost）和生物双向编码器表征从变压器（BioBERT）。所有算法均在MIMIC-III数据集上开发。然后将性能最佳的算法部署到比利时数据集上。预处理后，比利时数据集中共保留了1438份报告。基于TF-IDF矩阵的XGBoost对AF和HF的准确率分别为0.94和0.
