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 codeICD-10 disposal code, perform machine learning model trainingcode prediction. In addition, the combination codemedical 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,we provided the ICD code predicted by the best DNN classification model. We compared the elapsed timeF1 scores,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 DRGobtains the medical income that the hospital deserves. This allows doctors to predict the DRG early when the patient is hospitalized,to reduce the burden of medicalhealth 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,facilitating the payment of the patient.

天使投資人、策略合作夥伴