Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Medication prediction system based on neural network

A prediction system and neural network technology, applied in the field of health care informatics, can solve problems such as deviation of prediction results and poor applicability of neural network models, and achieve the effects of improving appropriateness, better drug prediction results, and targeted drug prediction results.

Active Publication Date: 2021-10-26
深圳创知未来科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The existing neural network model can predict the dosage of the patient at the next moment, but the neural network model only predicts the dosage of the drug, the type of drug will not change, and it is not a neural network model for the individual patient, and the prediction results will be biased due to individual differences , the applicability of the neural network model is poor

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
  • Medication prediction system based on neural network
  • Medication prediction system based on neural network
  • Medication prediction system based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] In order to make the technical means, creative features, goals and effects of the present invention easy to understand, a neural network-based medication prediction system of the present invention will be described in detail below in conjunction with the embodiments and accompanying drawings.

[0023] Such as figure 1 As shown, the neural network-based medication prediction system 1 includes a basic information acquisition module 11, a total recovery duration prediction module 12, a tracking data acquisition module 13, a remaining duration prediction module 14, a duration setting and judgment module 15, and a drug efficacy survival analysis module 16. Drug efficacy curve optimization module 17, timing model fine-tuning module 18 and medication suggestion module 19.

[0024] The basic information acquisition module 11 acquires the basic information of the patient.

[0025] Basic information (such as figure 2 shown) includes the basic information of the patient, detect...

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 provides a medication prediction system based on a neural network, and the system is characterized by mainly comprising a total recovery time length prediction module which predicts the total recovery time length of a patient based on basic information through employing a pre-trained classification model; a residual time length prediction module which predicts the time length required when the patient reaches the recovery state by utilizing a pre-trained time sequence model based on the basic information and the tracking data; a duration setting and judging module which judges whether the sum of the medication duration delta t and the remaining duration T is close to the total duration of healing of the patient or not, wherein if the judgment result is not, the medicine effect survival analysis module obtains a medicine effect curve with medication stop as an ending event through a COX regression model, then the medicine effect curve is optimized; a time sequence model fine tuning module which performs fine tuning on the time sequence model based on the optimized medicine effect curve to obtain a personalized time sequence model; and a medication suggestion module which uses the personalized time sequence model to predict and obtain a medication prediction result as a reference for doctor medication adjustment.

Description

technical field [0001] The invention belongs to the technical field of medical care informatics, and in particular relates to a neural network-based medication prediction system. Background technique [0002] Artificial neural network is one of the most active branches of computational intelligence and machine learning research, and has been widely used in different fields such as machine fault diagnosis, speech recognition, and securities management. With the rapid growth of medical data scale, artificial neural network has become an emerging technology in the medical field due to its self-learning and self-optimization characteristics. Using this emerging technology can extract features of interest to medical staff from a large amount of medical data. Or relevant data, and then provide diagnosis and treatment reference for medical staff. [0003] In recent years, with the prosperity and development of medical technology and the explosive increase of medical knowledge, the...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G16H20/10G16H70/40G06K9/62G06N3/04G06N3/08
CPCG16H20/10G16H70/40G06N3/049G06N3/08G06N3/044G06F18/24G06F18/214
Inventor 郑越文朱杰章欣王妍应灵潇
Owner 深圳创知未来科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products