Unlock instant, AI-driven research and patent intelligence for your innovation.

Incremental processing method for medical data

A processing method and technology of medical data, applied in medical data mining, medical informatics, informatics, etc., can solve the problems of limited hospital data and insufficient use of data, and achieve the effect of improving accuracy

Inactive Publication Date: 2018-09-14
CENT SOUTH UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Existing methods need a large amount of data support to achieve a high accuracy. At present, due to the island problem, the data of most hospitals is still limited
Moreover, the hospital's data is changing every day, and new data is added every day. These methods have not fully utilized the newly added data.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Incremental processing method for medical data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention aims at the problem that current medical data cannot be fully utilized. It is difficult to realize data sharing due to user privacy issues, differences in hospital platforms, and differences in data formats. Therefore, the hospital uses its own small amount of data and relies on artificial intelligence to train a system that can be used for auxiliary diagnosis to assist doctors in diagnosing some difficult diseases, improve the accuracy of diagnosis, and enable doctors to treat patients better.

[0020] The technical solution can fully utilize the data when the amount of data is small, and realize the corresponding medical auxiliary diagnosis function. Moreover, as the amount of hospital data increases, the information in the new data can be learned incrementally. It is not necessary to use all the data for retraining, but only to use the newly added data for training. As the amount of data increases, the accuracy rate will continue to improve. I...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an incremental processing method for medical data and aims at the problem that current medical data cannot be fully utilized. Data sharing is difficult to realize due to involving in privacy of users, differences in hospital platforms and differences in data formats. Therefore, a system capable of being used for assisting in diagnosis is trained by using a small amount of own data in a hospital and relying on artificial intelligence and is used for assisting doctors in diagnosing some difficult diseases, and diagnosis accuracy is improved, so that the doctors can bettertreat patients. According to the method, incremental learning from new data can be performed continuously to continuously improve accuracy of the system, and a large amount of time is not needed to be consumed for recalculation during each time of incremental learning.

Description

technical field [0001] The invention relates to an incremental processing method for medical data. Background technique [0002] Deep learning is an algorithm for high-level abstraction of data with multiple processing layers that contain complex structures or consist of multiple nonlinear transformations. So far, there have been several deep learning frameworks, such as deep neural network, convolutional neural network, etc. These frameworks have been applied in many fields and achieved excellent results. Deep learning can also help doctors in the diagnosis of diseases. At present, more and more artificial intelligence and sensor technologies have been integrated into the medical field, making medical services gradually intelligent. [0003] Modern medicine is evidence-based medicine based on experiments. Doctors’ diagnosis and treatment conclusions must be based on corresponding diagnostic data. Imaging is an important basis for diagnosis. 80% to 90% of the data in the me...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G16H50/20G16H50/70
CPCG16H50/20G16H50/70
Inventor 许涛郭克华
Owner CENT SOUTH UNIV