Disease Diagnosis Scoring via Centralized Biomedical Data Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current decision support systems (DSSs) for diagnosing diseases face challenges due to fragmented patient data across multiple physicians and hospitals, leading to incomplete data sets and reduced prediction accuracy, especially for diseases affecting multiple organ systems and rare conditions, where false positives and false negatives are common.
Innovation Solution
A computer-implemented method that aggregates biomedical data from various sources using an embedding and randomizing function to generate a unique access key, allowing secure consolidation of patient data in a centralized repository, and evaluates disease indicators through rule sets to determine the presence of diseases by calculating a total score value based on the risk assessment from multiple organ systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If patient data is distributed across multiple independent physicians and hospitals, then data security and autonomy are maintained, but prediction accuracy and completeness of biomedical data are reduced
Solution Approach 1:
The patent introduces a centralized decision support system as an intermediary that collects and integrates patient data from multiple independent physicians and hospitals. This centralization enables comprehensive data analysis for accurate disease prediction while maintaining data security through controlled access mechanisms and standardized data exchange protocols.
Solution Approach 2:
The patent merges fragmented patient data from multiple independent sources into a unified data structure. By combining data from different physicians and hospitals into a standardized format, the system achieves complete biomedical data sets necessary for accurate prediction of diseases affecting multiple organ systems.
2Ease of operation
If only data from a single organ system is considered, then diagnosis simplicity is maintained, but detection accuracy for multi-organ diseases is reduced
Solution Approach 1:
The patent segments the diagnosis process into multiple independent evaluation modules, each dedicated to a specific organ system. Each module evaluates relevant patient data and generates a score, which are then aggregated to produce a comprehensive disease risk assessment. This segmentation maintains the simplicity of individual organ system evaluation while achieving accurate multi-organ disease detection through integrated results.
3Measurement precision
If highly accurate prediction methods are used for orphan diseases, then false positives increase, but false negatives decrease
Solution Approach 1:
The patent dynamically adjusts evaluation parameters and scoring thresholds based on the specific disease being predicted and the patient's individual characteristics. For orphan diseases, the system modifies the weightings and criteria in prediction rules to optimize the balance between sensitivity and specificity, reducing both false positives and false negatives through adaptive parameter adjustment.
Data Source
Figure 1a~1b
Figure 2
Figure 3a~3b
AI summary
A computer-implemented method for determining the presence of a disease in a patient, the method comprising: - Receiving (250) first rule sets comprising rules, the rules of each first rule set being grouped into one or more second rule sets, each second rule set comprising a score value; - Determining(251), for each first rule set, the highest score value of its second rule sets; - Calculating (252) a total score value for the disease as a derivative of the determined highest score values; - Returning (253) a first diagnosis result, the first diagnosis result being indicative of the presence of the disease in the patient, the first diagnosis result having assigned the total score value;