105 results about "Longitudinal data" patented technology

The invention discloses a chronic disease condition change event prediction device based on a recurrent neural network, and the device comprises a memory, a processor, and a computer program, a preprocessing module and a chronic disease condition change event prediction model are stored in the memory, and the prediction model comprises a preprocessing module, a condition feature extraction module,and a classification module. When the processor executes a computer program, the following steps are realized: receiving long-term longitudinal data generated by multiple hospitalization of a patient, performing data preprocessing on the number by the preprocessing module, and reconstructing the data of each hospitalization into a feature vector as a to-be-tested data set; Taking the to-be-detected data set as input, extracting disease characteristics by a disease characteristic extraction module, and inputting the disease characteristics into a classification module; And enabling the classification module to output the prediction probability of various events indicating that the illness state changes. The prediction device can predict the event that the chronic disease patient has markeddisease condition change in the target time window, thereby assisting the doctor to formulate reasonable diagnosis and treatment measures and reducing the medical expenditure.

The invention discloses a space-time cooperation segmentation method based on an infant brain tumor multi-modal MRI graph. The space-time cooperation segmentation method includes (1) obtaining the postoperation brain tumor MRI images; (2) mapping the vertical data to the time domain and the spatial domain for segmentation; wherein the time domain segmentation includes obtaining the pre-operation segmentation result and the vertical data to be segmented, aligning the pre-operation and postoperation images, and constructing a postoperation tumor growth model; and the spatial domain segmentation includes constructing a healthy infant brain template, extracting the Haar structure characteristics, obtaining the preliminary probability result through the combination of a structure random forest method and an AdaBoost frame, increasing labels by means of similarity area increasing algorithm, and obtaining the spatial domain segmentation result; and (3) constructing a four-dimensional graph model through the combination of the time domain segmentation result and the spatial domain segmentation result, and optimizing the obtained parameters to form an automatic segmentation result. The segmentation method improves the accuracy of the infant brain tumor area segmentation.