ICD10 Automatic Coding System for Medical Record Classification
Summary Use NLP techniques to realize the automatic coding of ICD10. According to the input of the patient’s age, gender, medical order, admissions, progress note, surgical records, discharge, ICD-10 diagnostic code and ICD-10 disposal code, perform machine learning model training and code prediction. In addition, the combination code and medical order-related coding rules in practice are used to establish corresponding rules to optimize the accuracy of AI prediction.
The coders classify disease according to the medical records. Each group was randomly assigned the medical records, and we provided the ICD code predicted by the best DNN classification model. We compared the elapsed time and F1 scores, and then analyzed them with paired samples. The results showed that the ICD codes that provide predictions can increase the average F1 of coders from the median from 0.832 to 0.922 (P <0.05).
At the part of the health insurance declaration, it is accurately classified as the drop point of the correct DRG and obtains the medical income that the hospital deserves. This allows doctors to predict the DRG early when the patient is hospitalized, and to reduce the burden of medical and health insurance. On the patient side, the pre-coded mechanism can be used by the insurance company as the underwriting basis when the patient is hospitalized, speeding up the hospitalization underwriting payment mechanism, and facilitating the payment of the patient.
Technical Film
Keyword medicine Intelligent Information System Interdisciplinary integration
More like this
Provide the latest information of AI research centers and applied industries
本網站使用您的Cookie於優化網站及您的購物經驗。繼續瀏覽網站即表示您同意本公司隱私權政策,您可至隱私權政策了解詳細資訊。