Treatment Decision Models Using Priority Feature Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The inefficiency in collecting information for personalized medicine and measure proposals due to the time and cost associated with gathering patient data hinders prompt and effective decision-making.
Innovation Solution
An information processing device that generates treatment decision models for each elapsed period, learns from input feature values, collects first and second outputs, and sets priority feature values based on these outputs to enhance data collection efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If various feature values are collected to ensure accurate treatment method selection, then measurement precision is improved, but loss of time and cost increase
Solution Approach 1:
The patent extracts and identifies the most critical feature values from the complete set of available features. The selection unit determines which feature values are essential for accurate treatment method selection, collecting only those necessary features rather than all available features, thereby reducing collection time while maintaining measurement precision.
Solution Approach 2:
The patent performs preliminary analysis to determine the relationship between feature values and treatment method accuracy before actual information collection. The selection unit pre-identifies which feature values contribute most to accurate predictions, allowing the system to collect only those pre-selected features in advance, thus reducing time loss during the actual collection process.
2Measurement precision
If various feature values are collected to ensure accurate treatment method selection, then measurement precision is improved, but cost increases
Solution Approach 1:
The patent extracts and identifies the most critical feature values from the complete set of available features. The selection unit determines which feature values are essential for accurate treatment method selection, collecting only those necessary features rather than all available features, thereby reducing collection costs while maintaining measurement precision.
Solution Approach 2:
The patent applies partial action by collecting only the essential subset of feature values needed for accurate treatment method selection, rather than collecting all available features. This partial collection approach reduces the quantity of information that needs to be gathered, thereby reducing costs while maintaining sufficient measurement precision for clinical decision-making.
3Manufacturing precision
If all types of feature value are input to the model, then manufacturing precision of treatment decision is improved, but productivity of information collection deteriorates
Solution Approach 1:
The patent extracts and identifies the most critical feature values from the complete set of available features. The selection unit determines which feature values are essential for accurate treatment method selection, inputting only those necessary features into the prediction model rather than all available features, thereby maintaining manufacturing precision while improving productivity.
Solution Approach 2:
The patent applies partial action by inputting only the essential subset of feature values into the prediction model, rather than all available features. This partial input approach reduces the time and resources required for information collection and processing, thereby improving productivity while maintaining sufficient manufacturing precision for accurate treatment decisions.
Data Source
AI summary
An information processing device 100 of the present disclosure includes: an acquisition unit 121 that acquires a model that is generated for each elapsed period, and has learned by machine learning to output a measure for a human by receiving input of a plurality of types of feature value representing a condition of the human; a collection unit 122 that collects first output that is obtained when a predetermined number of types of feature value are input to the model of each elapsed period, and second output that is obtained when some types of feature value in the predetermined number of types of feature value are input to the model of each elapsed period; and a setting unit 123 that sets, on the basis of the first output and the second output, types to be associated with the model of each elapsed period. Thereby, the information processing device 100 can be used for assistance of decision-making by a user, or the like.