AKI Risk Prediction Model Using Preoperative Clinical Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a lack of effective prediction models for acute kidney injury (AKI) after non-cardiac surgery, particularly those that can be easily applied clinically and utilize non-cardiac clinical data from patients before surgery.
Innovation Solution
A system and method for predicting AKI after non-cardiac surgery, which includes a variable selection unit, a classification reference point setting unit, a prediction unit, and a preventive therapy information providing unit. This system selects relevant clinical data variables, calculates sensitivity and specificity, predicts AKI risk based on preset index sets and cutoff values, and provides information on preventive therapies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a prediction model using non-cardiac clinical data is developed, then the ease of operation and clinical applicability are improved, but the measurement precision and reliability of AKI risk prediction may worsen due to lack of specialized cardiac data
Solution Approach 1:
The patent develops a prediction model that uses universal non-cardiac clinical data (age, sex, comorbidities, laboratory values) to predict AKI risk across multiple surgical types. This multi-functional approach allows the same model to be applied to various non-cardiac surgeries without requiring surgery-specific cardiac data, thereby improving ease of operation while maintaining reasonable prediction accuracy through comprehensive use of available clinical parameters
2Ease of operation
If a simple scoring system is used for clinical application, then the ease of operation is improved, but the measurement precision of AKI risk prediction may deteriorate
Solution Approach 1:
The patent segments the prediction model into distinct components: variable selection (identifying relevant clinical factors), index assignment (assigning point values to each variable level), and risk stratification (categorizing patients into risk groups). This segmentation allows the complex prediction algorithm to be broken down into simple, manageable steps that can be easily performed in clinical settings while maintaining prediction precision through systematic evaluation of multiple risk factors
3Loss of time
If preoperative AKI risk is predicted using available clinical data, then the loss of time for postoperative assessment is reduced, but the reliability of prediction may worsen due to limitations in preoperative data completeness
Solution Approach 1:
The patent performs preliminary action by identifying and evaluating all relevant preoperative risk factors before surgery occurs. The model systematically assesses clinical data available prior to surgery (demographics, comorbidities, laboratory values) to predict AKI risk in advance. This preliminary evaluation enables early intervention and planning, reducing the need for extensive postoperative assessment while improving prediction reliability through comprehensive preoperative data collection and analysis
Data Source
AI summary
A method for predicting and reducing a risk of acute kidney injury (AKI) after non-cardiac surgery includes selecting factors associated with an occurrence of acute kidney injury after non-cardiac surgery, calculating sensitivity and specificity to a sum of combinations of indexes for each index set, and setting cutoff values for classification according to the sensitivity and specificity, and calculating a sum of indexes determined according to the index set preset for each variable, and classifying risk of acute kidney injury after non-cardiac surgery of the non-cardiac surgery patient on the basis of the cutoff values into four grades, and administering, based on the classified grade, an AKI preventive agent to the patient.