Digital Phenotyping Models for Multi-Disease Drug Response Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional dementia diagnosis methods fail to accurately classify patients into pure-ADD or ADD dominant LBD mix, leading to ineffective treatment, and there is a need for precise classification to select appropriate clinical subjects during pharmaceutical development.
Innovation Solution
A digital phenotyping method using biometric data analysis with multiple diagnostic models to distinguish between Alzheimer's disease dementia (ADD), Lewy body dementia (LBD), Parkinson's disease, vascular dementia, depression, and anxiety, including training diagnostic models with brainwave data before and after drug administration to calculate validity and probability values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional dementia diagnosis methods are used, then the diagnosis process is simple, but the classification accuracy between pure-ADD and ADD dominant LBD mix is insufficient
Solution Approach 1:
The patent divides the diagnosis system into multiple independent diagnostic models, each specialized for detecting specific diseases (ADD, LBD, Parkinson's, vascular dementia, depression, anxiety). Each model processes biometric data independently and outputs a probability value, allowing accurate multi-disease classification without requiring a single complex system.
Solution Approach 2:
The patent creates a universal diagnostic framework where a single system can detect multiple different diseases using the same biometric data input. The disease diagnostic model includes multiple diagnostic models that can simultaneously identify various neurological and psychiatric conditions, making the system versatile and adaptable to different diagnostic needs.
2Measurement precision
If multiple diagnostic models are used to improve classification accuracy, then the diagnostic precision increases, but the computational complexity and data processing requirements increase
Solution Approach 1:
The patent segments the data processing task by assigning different diagnostic models to different diseases. Each model independently processes biometric data to generate a probability value for its specific disease, avoiding the need for a single model to process all diseases simultaneously. This reduces the computational burden on each individual model while maintaining overall diagnostic accuracy.
Solution Approach 2:
Each diagnostic model independently analyzes the biometric data and self-generates its own probability value without requiring complex coordination with other models. The system allows each specialized model to serve its own diagnostic function autonomously, simplifying the overall data processing architecture despite having multiple models.
3Reliability
If biometric data analysis is performed to accurately classify dementia types, then treatment effectiveness improves, but the time and resources required for diagnosis increase
Solution Approach 1:
The patent performs preliminary classification by having multiple diagnostic models simultaneously evaluate biometric data and generate probability values for different diseases. This parallel processing approach allows the system to pre-assess multiple disease possibilities at once, reducing the time required for accurate diagnosis compared to sequential evaluation methods.
Solution Approach 2:
The patent changes the diagnostic parameter from qualitative clinical assessment to quantitative probability values generated by diagnostic models. By converting disease detection into measurable probability outputs based on biometric data analysis, the system achieves reliable and accurate classification while streamlining the diagnostic process through objective, data-driven measurements.
Data Source
AI summary
Provided are a digital phenotyping method, apparatus, and recording medium for drug response classification and prediction. A digital phenotyping method for drug response classification and prediction that is performed by a computing device according to various embodiments of the present invention includes acquiring biometric data of a patient, and analyzing the acquired biometric data using a disease diagnostic model to perform a multiple disease diagnosis on the patient, in which the disease diagnostic model includes a plurality of diagnostic models that independently perform diagnoses of each of multiple distinct diseases based on the acquired biometric data.