Neural Network Training Data Preprocessing for Dementia Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting dementia using historical medical data are not effective in providing accurate predictions compared to conventional machine learning methods.
Innovation Solution
A training data processing method that involves obtaining medical history data, setting disease types and time intervals, performing pre-processing operations, and inputting the processed data into a neural network to train the model, enhancing the prediction accuracy of a neural network model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional machine learning methods are used for prediction, then the process is simple, but the prediction accuracy is insufficient
Solution Approach 1:
The patent applies preliminary action by performing data preprocessing operations before training the neural network model. This includes obtaining medical history data, setting disease types and time intervals, and preprocessing the data to extract relevant features. By preparing the data in advance with specific preprocessing steps, the system achieves higher prediction accuracy while managing complexity through structured preparation phases.
2Reliability
If medical history data is processed with disease types and time intervals, then the prediction effect is improved, but the data processing complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the medical history data processing into distinct segments: setting disease types as categorical segments, defining time intervals as temporal segments, and preprocessing operations as transformation segments. This segmentation of the data processing pipeline allows for more reliable predictions through structured analysis while managing complexity by organizing processing into manageable, modular segments.
Data Source
AI summary
A training data processing method and an electronic device are provided. The method includes: obtaining medical history data including at least one first disease suffered by a user; setting a plurality of disease types according to a target disease; setting a time interval; obtaining at least one second disease in the time interval from the medical history data; performing a pre-processing operation on the second disease according to the disease types to obtain processed data; and inputting the processed data to a neural network to train the neural network.