ICD intelligent coding method based on deep learning and knowledge graph

• Main Authors: ZHU WEI, CHENG LAN, ZHANG YOUSHU, XIAO SHANGHUA
• Format: Patent
• Language: Chinese; English
• Published: 10.12.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

The invention provides an ICD intelligent coding method based on deep learning and a knowledge graph. The method comprises the following steps of acquiring the electronic medical record data and the medical advice item data; performing data standardization processing on the electronic medical record data and the medical advice item data to obtain the standardized data; constructing a BERT+BiLSTM+CRF training diagnosis name identification model, and identifying the diagnosis name of the standardized data by using the model; calculating a final ICD code of each diagnosis name based on a BERT model; combining the ICD codes of the diagnosis names; and based on a disease charging item knowledge graph, according to the charging medical advice of the current medical record, calculating the diagnosis which consumes the most medical resources at this time, and taking the diagnosis as the main diagnosis. 本发明提出了一种基于深度学习和知识图谱的ICD智能编码的方法，包括：获取电子病历数据和医嘱项目数据；对所述电子病历数据和医嘱项目数据进行数据标准化处理，得到标准化处理后的数据；构建BERT+BiLSTM+CRF训练诊断名称识别模型，