Artificial intelligence-based endometrial cancer risk screening method and system

Abstract

The invention provides an endometrial cancer risk screening method and system based on artificial intelligence. The method comprises a training process and a verification process. The system comprises a data processing module which is used for processing data, extracting feature information of the data, carrying out labeling processing and forming structured data; the Xgboost loss model module is used for training or predicting the structured data to obtain trained or predicted data; the Lasso model simplification module is used for simplifying features to obtain a feature data matrix; and the BR ridge model module is used for obtaining an endometrial cancer risk screening prediction model according to the trained data and obtaining an endometrial cancer risk prediction value according to the predicted data. The method can be widely used for cross section risk screening of outpatient service or physical examination conventional patients, missing detection of high-risk patients is avoided, meanwhile, automatic risk screening facilitates work of doctors, and efficiency is improved; and the risk prediction model can be moved forward to a patient end for preliminary screening, so that self-monitoring and management of the patient are facilitated.

Description

technical field [0001] The invention relates to the technical field of natural language processing and machine learning, and in particular to an artificial intelligence-based endometrial cancer risk screening method and system. Background technique [0002] Endometrial cancer is one of the three major cancers of the female reproductive system, and its morbidity and mortality are on the rise worldwide. With the increase in the incidence of endometrial cancer and the younger age of patients, early screening of patients with high risk of endometrial lesions is becoming more and more important. [0003] At present, the common screening methods for endometrial cancer are tumor markers combined with transvaginal uterine dual adnexal ultrasonography, or endometrial sampling combined with cytology. However, the first screening method is more suitable for postmenopausal women. For women of childbearing age, ultrasound provides limited screening information, lacks cutting values, and...

AI Technical Summary

Problems solved by technology

However, the first screening method is more suitable for postmenopausal women. For women of childbearing age, ultrasound provides limited screening information, lacks cut-off values, and has low accuracy

The second screening method for the patient's endometrium sampling will cause the patient's body to be invasive, and the disposable equipment is expensive. At the same time, the cytological examination has high requirements for the pathological diagnosis level of the hospital. This method is more suitable for Further screening for patients identified as high risk for endometrial cancer

Therefore, compared with the current relatively complete early screening system for cervical cancer, there is a lack of effective screening methods for endometrial cancer and precancerous lesions.

Images