2 results about "Model integration" patented technology

The invention discloses an ovarian tumor recurrence risk probability prediction method based on multi-model integration, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring clinical detection data of a to-be-predicted target; wherein the clinical detection data comprises clinical detection data of ovarian cancer and clinical detection data of border ovarian tumor; inputting the clinical detection data into a pre-trained recurrence risk probability integration model, and outputting and obtaining an ovarian tumor recurrence risk probability prediction result of a to-be-predicted target; wherein the recurrence risk probability prediction integrated model is obtained by training a basic model and a meta-learning model through a training set and a test set, the training set and the test set are obtained by dividing a standard data set, and the standard data set is obtained by preprocessing multi-source clinical data. The accuracy and the stability of the ovarian tumor recurrence risk probability can be improved.

The embodiment of the application provides a kind of endometrial carcinoma classification method and system based on adaptive weighted ensemble learning, the method includes obtaining clinical data, and based on clinical data, the weighted training set capable of improving the identification ability of minority class is constructed;Balanced training set is input into initial double-branch characteristic learning model for model training, and target double-branch characteristic learning model is obtained when training ends, based on the encoding feature output by first parallel branch, complex pattern mining model integration framework is constructed, and based on the effective feature output by second parallel branch, supervised machine learning model integration framework is constructed;The verification set constructed in advance is input into complex pattern mining model integration framework and supervised machine learning model integration framework, and the dynamic weight of each integrated model in framework is adjusted based on the performance score output;Based on the prediction rule of the two integrated frameworks integrated after dynamic weight adjustment, data classification operation is carried out, and endometrial carcinoma classification result is obtained.