Neural Network Delirium Prediction via Feature Point Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting delirium in patients rely heavily on subjective evaluations, which can lead to inconsistencies and underestimation of delirium symptoms.
Innovation Solution
A method and system for generating a learned model using a neural network that predicts the probability of delirium based on changes in the relative positions of feature points in a subject's body within a moving image, thereby reducing subjective contribution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If subjective evaluation methods are used to detect delirium, then evaluation can be performed, but consistency and reliability are poor
Solution Approach 1:
The patent replaces subjective human evaluation with an automated computer-based system that uses neural networks to analyze video data. The system automatically detects feature points, tracks their movements, and predicts delirium probability, eliminating human subjectivity and improving evaluation consistency and reliability.
Solution Approach 2:
The patent creates a digital copy of the patient's behavior through video recording and extracts quantitative data from this copy. By analyzing the copied visual data through neural networks, the system can consistently reproduce evaluation results without the variability introduced by human observers.
2Measurement precision
If automated neural network analysis is implemented, then prediction accuracy improves, but processing load increases
Solution Approach 1:
The patent extracts only the necessary information from the video data by detecting and tracking specific feature points (eyes, nose, mouth, facial features). This selective extraction of relevant behavioral data reduces the processing load compared to analyzing entire video streams, while maintaining prediction accuracy through focused analysis of delirium-related movements.
Solution Approach 2:
The patent segments the complex task of delirium detection into distinct processing stages: feature point detection, movement tracking, data normalization, and neural network prediction. This segmentation allows each component to be optimized independently and reduces overall processing complexity by breaking down the complex analysis into manageable steps.
Data Source
AI summary
A method for generating a learned model applied to a prediction device that predicts a probability that a subject develops delirium based on a moving image in which the subject appears is provided. The method includes: acquiring first data corresponding to the moving image in which the subject appears; generating, based on the first data, second data corresponding to changes over time in relative positions of a plurality of feature points in a body of the subject in the moving image; generating third data indicating a determination result as to whether the subject develops delirium based on the moving image; and generating the learned model by causing a neural network to learn using the second data and the third data.