Masud Jakir Hossain Bhuiyan, Kuo Chen-Cheng, Yeh Chih-Yang, Yang Hsuan-Chia, Lin Ming-Chin
Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei 11031, Taiwan.
International Center for Health Information Technology (ICHIT), College of Medical Science and Technology, Taipei Medical University, Taipei 11031, Taiwan.
Diagnostics (Basel). 2023 Jul 6;13(13):2297. doi: 10.3390/diagnostics13132297.
The International Classification of Diseases (ICD) code is a diagnostic classification standard that is frequently used as a referencing system in healthcare and insurance. However, it takes time and effort to find and use the right diagnosis code based on a patient's medical records. In response, deep learning (DL) methods have been developed to assist physicians in the ICD coding process. Our findings propose a deep learning model that utilized clinical notes from medical records to predict ICD-10 codes. Our research used text-based medical data from the outpatient department (OPD) of a university hospital from January to December 2016. The dataset used clinical notes from five departments, and a total of 21,953 medical records were collected. Clinical notes consisted of a subjective component, objective component, assessment, plan (SOAP) notes, diagnosis code, and a drug list. The dataset was divided into two groups: 90% for training and 10% for test cases. We applied natural language processing (NLP) technique (word embedding, Word2Vector) to process the data. A deep learning-based convolutional neural network (CNN) model was created based on the information presented above. Three metrics (precision, recall, and F-score) were used to calculate the achievement of the deep learning CNN model. Clinically acceptable results were achieved through the deep learning model for five departments (precision: 0.53-0.96; recall: 0.85-0.99; and F-score: 0.65-0.98). With a precision of 0.95, a recall of 0.99, and an F-score of 0.98, the deep learning model performed the best in the department of cardiology. Our proposed CNN model significantly improved the prediction performance for an automated ICD-10 code prediction system based on prior clinical information. This CNN model could reduce the laborious task of manual coding and could assist physicians in making a better diagnosis.
国际疾病分类（ICD）代码是一种诊断分类标准，在医疗保健和保险领域经常用作参考系统。然而，根据患者的病历查找并使用正确的诊断代码需要花费时间和精力。对此，人们开发了深度学习（DL）方法来协助医生进行ICD编码过程。我们的研究结果提出了一种深度学习模型，该模型利用病历中的临床记录来预测ICD-10代码。我们的研究使用了某大学医院门诊部2016年1月至12月基于文本的医疗数据。该数据集使用了五个科室的临床记录，共收集了21953份病历。临床记录包括主观部分、客观部分、评估、计划（SOAP）记录、诊断代码和药物清单。该数据集分为两组：90%用于训练，10%用于测试案例。我们应用自然语言处理（NLP）技术（词嵌入，Word2Vector）来处理数据。基于上述信息创建了一个基于深度学习的卷积神经网络（CNN）模型。使用三个指标（精确率、召回率和F值）来计算深度学习CNN模型的成果。通过深度学习模型在五个科室取得了临床可接受的结果（精确率：0.53 - 0.96；召回率：0.85 - 0.99；F值：0.65 - 0.98）。深度学习模型在心脏病科表现最佳，精确率为0.95，召回率为0.99，F值为0.98。我们提出的CNN模型显著提高了基于先前临床信息的自动ICD-10代码预测系统的预测性能。这种CNN模型可以减少人工编码的繁琐任务，并可以协助医生做出更好的诊断。
