Technical Name 肝癌治療成效追蹤與術後復發預測輔助系統
Project Operator Department of Internal Medicine, College of Medicine, National Taiwan University
Project Host 梁嘉德
"The primary goal of this project is to establish a complete hospital-based liver cancer database, profiles for data feature extraction,develop different cancer, prediction models.
A Medical AI program to predict the poster treatment (including operationradiofrequency ablation) recurrence of liver cancer will be established. The program system will assist doctors in the medical decision, identify high-risk patients,adjust clinical follow-up programs."
Scientific Breakthrough
This system uses the textual clinical record, including various numerical test results, pathology reports, etc., to retrieve the required features through Regular Expressionthen trains models to predict the possibility of recurrence after treatment. Before we train models, we search for patient data from the database, remove unreasonable extreme values, standardize,select appropriate features. We train a robust model from unbalanced datamake accurate predictions for liver cancer recurrence after different treatment modalities, including surgeryradiofrequency ablation.
Industrial Applicability
The system uses a systematic feature extraction process to process various medical record text reportsintegrate them into a proprietary database. The program grabs specific features from the database for trainingpredicts the possibility of liver cancer recurrence through the AI model. When using the hospital, it only needs to provide the patient's past medical records (features required for model prediction). The model can automatically predict whether the patient is likely to relapse again. The doctor can use this result as an auxiliary basis for diagnosis.
Matching Needs
Keyword Artificial intelligence machine learning Hepatocellular carcinoma treatment Radiofrequency Ablation(RFA) surgery clinical decision precision medicine database feature extraction
  • Contact
other people also saw