Disease Network Co-occurrence Probability Calculation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current disease networks primarily provide topology maps and do not offer numerical probability values for disease co-occurrence, limiting their practical application in medical services and patient care.
Innovation Solution
A method is developed to calculate and provide disease co-occurrence probabilities by using a disease network where diseases are represented as nodes and correlations as edges, employing graph-based semi-supervised learning to score and rank the likelihood of co-occurring diseases based on correlation degrees and scale parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If disease networks provide only topology maps, then the network structure is simple and easy to visualize, but numerical probability information for disease co-occurrence is not provided
Solution Approach 1:
The patent transforms the disease network from a qualitative topology map into a quantitative probability model by introducing numerical parameters. Specifically, it calculates disease co-occurrence probabilities using graph-based semi-supervised learning, converting structural network information into meaningful probability values that indicate the likelihood of disease co-occurrence.
Solution Approach 2:
The patent introduces an intermediary computational layer (graph-based semi-supervised learning algorithm) that bridges the gap between simple network topology and clinical probability information. This intermediary process processes the network structure and generates probability scores without requiring direct clinical data input.
2Ease of operation
If disease networks include detailed molecular links and complex structures, then the network provides comprehensive biological information, but it does not provide practical help for medical research and patient care
Solution Approach 1:
The patent extracts the essential clinical utility information from complex biological networks by focusing specifically on disease co-occurrence probabilities. Instead of presenting all molecular details, it extracts and highlights the probability information that is most relevant for medical decision-making and patient care.
Solution Approach 2:
The patent transforms complex biological network data into simplified probability parameters that are directly applicable to clinical settings. By converting intricate molecular relationship data into single probability values, it makes the information actionable for doctors and researchers without losing the essential predictive capability.
3Reliability
If general disease network research is performed by biologists pursuing scientific discoveries, then theoretical understanding develops, but results are far from helping real medical service situations
Solution Approach 1:
The patent bridges the gap between theoretical biology and clinical practice by introducing probability parameters that have meaning in both domains. The graph-based semi-supervised learning approach maintains scientific rigor while producing outputs (probability values) that are directly interpretable and useful in clinical settings.
Solution Approach 2:
The patent creates a multi-functional tool that serves both research and clinical needs. The same disease network infrastructure supports both scientific discovery (through network analysis) and practical medical application (through probability-based predictions), eliminating the need for separate systems.
Data Source
AI summary
Disclosed is a method of providing a disease co-occurrence probability including (a) receiving a disease network in which respective diseases are shown as nodes and a correlation between diseases is shown as an edge between the nodes and (b) calculating, when at least one disease is given, a probability of an occurrence of another disease in addition to the given disease, the corresponding disease which accompanies the given disease, from the disease network.