Kidney Stone Probability Prediction Model Using eGFR and Urine pH
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high cost and limited availability of dual-energy computed tomography (CT) for differentiating uric-acid (UA) stone disease from non-UA stone disease in nephrolithiasis, along with concerns about radiation safety, hinder effective diagnosis and treatment.
Innovation Solution
A machine-learning-based method using a prediction model established with training data sets including estimated glomerular filtration rate (eGFR) and urine pH to determine the probability of a kidney stone being a UA stone, which is more accessible and safer than dual-energy CT.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dual-energy CT is used to differentiate UA stone disease from non-UA stone disease, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent creates a virtual copy of the dual-energy CT diagnostic capability through a machine learning prediction model. Instead of requiring the expensive and complex dual-energy CT hardware, the system uses a software-based prediction model trained on data from standard CT scans to replicate the differentiation function, making the technology accessible without the underlying hardware complexity
Solution Approach 2:
The patent replaces the physical dual-energy CT scanning system with an information-processing system. Rather than using specialized radiation imaging hardware, the system processes standard CT scan data through machine learning algorithms to achieve the same diagnostic purpose, substituting mechanical imaging equipment with computational analysis
2Measurement precision
If dual-energy CT is used to differentiate UA stone disease from non-UA stone disease, then measurement precision is improved, but object-affected harmful factors increase
Solution Approach 1:
The system copies the diagnostic function of dual-energy CT using standard CT scan data and machine learning algorithms, eliminating the need for additional radiation exposure from dual-energy scanning while maintaining differentiation capability
Solution Approach 2:
The patent uses readily available standard CT scan data as input material, which can be obtained from routine imaging without requiring specialized dual-energy equipment. This approach leverages existing diagnostic data rather than requiring additional radiation exposure for specialized scanning
3Measurement precision
If dual-energy CT equipment is deployed, then measurement precision is improved, but loss of energy increases
Solution Approach 1:
The patent replaces energy-intensive dual-energy CT hardware with a computational approach that processes existing CT data through machine learning algorithms, significantly reducing the energy requirements for achieving the same diagnostic differentiation
Data Source
AI summary
A method for determining a probability of a kidney stone in a subject being a uric-acid (UA) stone includes steps of: establishing, by using a machine learning algorithm, a prediction model based on a plurality of training data sets that are related to a plurality of patients, each of the plurality of training data sets at least including an estimated glomerular filtration rate (eGFR) and a value of urine pH; and feeding an input variable set into the prediction model so as to obtain the probability of the kidney stone in the subject being a UA stone. The input variable set is related to the subject and including an eGFR and a value of urine pH of the subject.