Prediction system for predicting occurrence of calcium oxalate kidney stone

Abstract

The invention provides a prediction system for predicting occurrence of calcium oxalate kidney stone, and belongs to the field of neural networks. The prediction system comprises an input module, a calculation module and an output module. I, the input module is used for transmitting the following information of a patient to the calculation module: gender, oxalic acid concentration in urine, aceticacid concentration in excrement, relative abundance value of g_Geobacter, relative abundance value of g_Kroppenstedtia, relative abundance value of g_Spharochaeta and relative abundance value of g_Oscillospira; II, a trained prediction network model for predicting the occurrence of calcium oxalate kidney stone is built in the calculation module; and III, the output module is used for outputting the probability value Y. Three clinical indexes and relative abundance values of four bacteria genus are combined, and a conventional algorithm is used, so that the occurrence of the kidney stone can be accurately predicted. The prediction effect of a random forest algorithm is the most accurate. The prediction method provided by the invention can accurately predict the kidney stone, especially calcium oxalate kidney stone, and can provide a basis for clinical diagnosis and treatment of kidney stone.

Description

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

AI Technical Summary

Benefits of technology

This patented technology uses three different types of data from medical tests or biological samples collected during an examination process to make predictions about how likely they are getting stuck with certain diseases such as renal calculi. Random-forest models have been shown to outperform traditional methods by providing more precise results than other techniques like machine learning.

Problems solved by technology

This patented problem addressed in this patents relates to finding ways to reduce damage from excessively high levels of certain compounds found within renal calculus called calcified materials during medical procedures such as lithotripsy surgery. Current techniques involve measuring these deposits through histopathology analysis but they cannot accurately determine if any new ones occur without subjecting subjects who may already suffer harm due to their symptoms.

Images