Machine Learning Model for Predicting Biological Measurement Continuation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Medical professionals face challenges in managing patients who do not consistently measure their biological information, as they cannot determine if patients are continuously monitoring their health data without direct interaction.

Innovation Solution

An information processing method and device that utilize a machine learning trained model to analyze measurement-related information, deriving a measurement tendency score to predict if a patient will continue measuring biological information, allowing for targeted interventions to encourage continued monitoring.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If medical professionals manually monitor patient measurement compliance, then direct intervention capability is improved, but workload and time consumption increase significantly

Engineering Contradiction:

Improvepatient measurement compliance monitoringVSAvoidmedical professional time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables self-monitoring of measurement compliance through automated data collection from measurement devices and AI-based prediction of continuation probability, eliminating the need for manual monitoring by medical professionals while maintaining reliable tracking of patient compliance status

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system provides automated feedback by continuously analyzing measurement data and prediction results, then notifying both patients and medical professionals of compliance status and continuation probability, enabling timely interventions without consuming professional time

Inventive Principle:

Principle #23Feedback

2Measurement precision

If medical professionals manually determine patient measurement continuity, then accuracy of compliance assessment is improved, but device complexity and operational burden increase

Engineering Contradiction:

Improvecompliance assessment accuracyVSAvoidmonitoring system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system replaces manual assessment mechanisms with an AI-based prediction model that automatically analyzes measurement data patterns to determine continuation probability, achieving high measurement precision without requiring complex manual monitoring procedures

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system introduces an intermediary AI prediction model that mediates between raw measurement data and compliance assessment, automatically processing and interpreting measurement patterns to provide accurate continuity determination without direct professional involvement

Inventive Principle:

Principle #24Intermediary (Mediator)

3Loss of time

If the system predicts measurement continuation probability, then early intervention capability is improved, but data processing requirements increase

Engineering Contradiction:

Improveintervention timingVSAvoiddata processing volume

Core Design Contradiction:

Loss of timeVSQuantity of substance

Solution Approach 1:

The system extracts only the essential features from measurement data needed for continuation probability prediction, such as measurement frequency, timing patterns, and consistency metrics, thereby reducing data processing volume while maintaining sufficient information for timely intervention decisions

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS20250315100A1Information processing method, information processing device, information processing recording medium, method for generating machine learning trained model, and machine learning trained model

Publication Date: 2025.10.09 OMRON HEALTHCARE CO LTD

AI summary

An information processing method, an information processing device, an information processing recording medium, a method for generating a machine learning trained model, and a machine learning trained model, which can be used for management of a measurement subject of biological information. A processor acquires measurement-related information related to a result of measurement of biological information performed on a measurement subject for a predetermined period by a biological information measuring device, derives measurement tendency information indicating a level of a possibility that the measurement subject continuously measures the biological information in a future period after the predetermined period based on the measurement-related information, and performs processing based on the measurement tendency information.