Neural Network AD Prediction Using MMSE Orientation Scores
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting Alzheimer's Disease (AD) from Mild Cognitive Impairment (MCI) patients are limited by the complexity of MRI scans and the need for combined structural and functional data analysis, which is not efficiently addressed by existing technologies.
Innovation Solution
A neural network training system that utilizes historical MMSE scores and Alzheimer's markers to train a neural network, reducing the reliance on brain MRI data by incorporating MMSE change data and orientation scores to enhance prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If MRI scans are used for AD prediction, then structural information is obtained, but data complexity increases and requires sophisticated analysis
Solution Approach 1:
The patent extracts only the most relevant features from MMSE data (orientation scores and their changes) rather than using complete MRI scans. This extraction principle reduces the complexity of input data while maintaining prediction accuracy by focusing on discriminative features that specifically indicate AD progression from MCI.
Solution Approach 2:
The patent creates a simplified representation (copy) of cognitive function data through MMSE orientation scores that substitutes for complex MRI structural information. This copied data form maintains the essential diagnostic information while being much easier to process and analyze.
2Measurement precision
If combined structural and functional data analysis is performed, then prediction accuracy improves, but computational requirements increase
Solution Approach 1:
The patent merges MMSE orientation change data with Alzheimer's marker data into a unified neural network input. This combination integrates structural biomarker information with functional cognitive assessment data, achieving improved prediction accuracy through multi-source data fusion while keeping computational requirements manageable.
Solution Approach 2:
The patent transforms MMSE scores into derived parameters (orientation changes between time points) that capture disease progression dynamics. This parameter transformation converts static cognitive test results into dynamic progression indicators, enhancing predictive power without requiring intensive computational resources.
3Ease of manufacture
If MMSE change data and orientation scores are used, then reliance on MRI data is reduced, but data processing complexity increases
Solution Approach 1:
The patent performs preliminary processing of MMSE data by calculating orientation score changes between different time points before feeding into the neural network. This pre-computation of derived features simplifies the main prediction task and reduces the complexity of real-time data processing requirements.
Data Source
AI summary
The present disclosure relates to a method for providing biomarker for early detection of Alzheimer's Disease (AD), and particularly to a method that is able to enhance the accuracy of predicting AD from Mild Cognitive Impairment (MCI) patients using the Hippocampus magnetic resonance imaging (MRI) scans and Mini-Mental State Examination (MMSE) data. The providing MRI images containing the anatomical structure of Hippocampus biomarker and MMSE data as a training data set; training a processor using the training data set, and the training comprising acts of receiving MRI images and MMSE data as a testing data set from a target; and classifying the test data by the trained processor to include aggregating predictions.