Test Interruption Prediction from Patient Utterances and Feelings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical treatment techniques fail to predict interruptions in tests due to patient feelings of uneasiness, leading to potential test disruptions.
Innovation Solution
A test assist apparatus and method utilizing machine learning to analyze patient utterances, feelings, and test information to predict the probability of interruptions, with a prediction model trained on past interruptions, and outputting this probability for informed decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional medical treatment assist techniques are used, then patient information and medical interview information can be acquired and analyzed, but the ability to predict test interruptions caused by patient feelings such as uneasiness is lacking
Solution Approach 1:
The patent introduces an intermediary feeling recognition module that detects patient emotional states through non-verbal cues (facial expressions, body language, tone of voice) during tests. This intermediary system bridges the gap between raw test data and patient psychological state, enabling prediction of interruptions before they occur by identifying uneasiness or anxiety patterns in real-time.
Solution Approach 2:
The patent replaces traditional mechanical data collection methods with AI-based feeling recognition technology. Instead of relying solely on explicit patient reports or basic vital signs, the system uses machine learning models to interpret subtle emotional signals, substituting conventional measurement approaches with intelligent pattern recognition that can predict test interruptions.
2Reliability
If machine learning-based prediction is implemented, then test interruption probability can be predicted, but device complexity increases
Solution Approach 1:
The patent segments the prediction system into distinct functional modules: feeling recognition module, information acquisition module, prediction module, and output module. Each module handles specific tasks independently, making the complex AI-based prediction system more manageable and easier to integrate into existing medical equipment without overwhelming complexity.
Solution Approach 2:
The patent designs the feeling recognition module to serve multiple functions: detecting patient uneasiness, monitoring test progress, predicting interruptions, and providing real-time feedback. This multi-functionality reduces the need for separate dedicated systems, thereby managing complexity while maintaining high prediction accuracy.
Data Source
AI summary
This test assist apparatus includes: an acquiring section for acquiring utterance information which indicates the content of an utterance of a patient during a test performed on the patient, state information regarding the feelings of the patient during the test, and basic information regarding the test; an interruption predicting section for predicting a probability of interruption of the test performed on the patient, from the utterance information, the state information, and the basic information, with use of a prediction model for predicting a probability of interruption of a test, the prediction model being generated by machine learning in which samples of past test interruptions are used as training data; and an outputting section for outputting the probability of interruption.