Medical Support Device Using Elapsed-Time Fall Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fall prediction methods place a heavy burden on patients and medical institutions, and have low accuracy due to neglecting the number of elapsed days from medical practices to the prediction timing.
Innovation Solution
A medical support device and method using a prediction model trained through machine learning to predict falls based on the number of elapsed days from medical practices, such as drug prescriptions and examinations, reducing the need for wearable sensors and improving prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If wearable terminals with sensors are attached to patients, then fall prediction can be performed, but the burden on patients and medical institutions increases
Solution Approach 1:
The patent extracts the fall prediction function from wearable devices and relocates it to a server-based system. The server acquires medical information (prescription dates, examination dates, etc.), calculates elapsed days, and performs predictions using stored prediction models, eliminating the need for patients to wear complex sensor devices while maintaining prediction capability
Solution Approach 2:
The server acts as an intermediary between medical information sources and fall prediction. It receives medical information from various sources, processes it by calculating elapsed days from medical practices to prediction dates, and generates predictions, thereby mediating the complex prediction task without requiring direct patient involvement
2Adaptability or versatility
If fall prediction is based on various types of information, then comprehensive prediction can be achieved, but the accuracy decreases due to neglecting elapsed days from medical practices
Solution Approach 1:
The patent transforms various medical information (prescription dates, examination dates, treatment dates) into a standardized parameter format by calculating elapsed days from each medical practice to the prediction date. This parameter transformation enables the prediction model to accurately capture temporal relationships and improve prediction accuracy while maintaining comprehensive data utilization
Data Source
AI summary
A processor acquires medical information including date information associated with a medical practice for a target patient and prediction date information for predicting a fall of the target patient, derives fall prediction information of the target patient using a prediction model that has been trained through machine learning to predict the fall of the target patient based on the number of elapsed days derived from the date information and the prediction date information, and notifies of the fall prediction information.