Voice, Text, and Facial Analysis for Brain Dysfunction Screening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies for diagnosing brain dysfunctions such as dementia and aphasia do not adequately consider the differences in symptoms, leading to inadequate estimation of the possibility of these conditions.
Innovation Solution
A program and information processing device that outputs questions by voice and text, receives answers, determines correctness, and estimates the possibility of brain dysfunction based on the answers, using morphological and syntactic analysis, and optionally facial asymmetry analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If only voice-based question answering is used for dementia diagnosis, then the diagnosis process is simple, but the estimation accuracy of brain dysfunction is insufficient
Solution Approach 1:
The diagnosis system is segmented into multiple independent assessment modules: voice-based question answering module, text-based question answering module, and facial expression analysis module. Each module evaluates different aspects of language and cognitive function separately, allowing comprehensive assessment while maintaining operational simplicity through modular design.
Solution Approach 2:
The system employs a multi-functional assessment approach where the same subject undergoes multiple types of evaluations (voice questions, text questions, facial expression analysis) to comprehensively assess brain dysfunction. This universal assessment framework can detect various types of language disorders and cognitive impairments through different modalities.
2Measurement precision
If multiple types of questions (voice and text) are asked to improve diagnosis accuracy, then the estimation of brain dysfunction improves, but the complexity of the diagnosis system increases
Solution Approach 1:
The complex diagnosis system is divided into distinct functional segments: a voice output unit that speaks questions, a text output unit that displays questions, a voice input unit that captures responses, and a text input unit that receives written responses. Each segment handles specific tasks independently, making the overall system more manageable despite the multiple components required for comprehensive assessment.
3Measurement precision
If facial asymmetry analysis is added to speech analysis, then the detection accuracy of abnormal points improves, but the processing time and computational load increase
Solution Approach 1:
The system performs preliminary actions by capturing facial expressions and analyzing speech patterns during the question-answering process itself, rather than requiring separate, time-consuming analysis phases. The facial asymmetry analysis is conducted concurrently with the language assessment, utilizing the same time window and computational resources to evaluate both modalities simultaneously.
Data Source
AI summary
A non-transitory computer-readable medium, an information processing device, and an information processing method that causes a computer processor to execute a process that includes: outputting a first question by voice; receiving an answer to the first question from a subject; outputting a second question by text; receiving an answer to the second question from the subject; determining whether or not the answers to the first and second questions are correct; and estimating a possibility of a brain dysfunction of the subject based on correctness or incorrectness of the answers to the first and second questions.