Knowledge Graph Therapy Scoring for Rapid Literature Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining the efficacy of therapies are time-consuming, expensive, and biased, with published literature expanding rapidly, making it impossible for healthcare providers to identify and evaluate new or alternative therapies, leading to outdated guidelines and potential conflicts with newly discovered treatments.
Innovation Solution
A method that utilizes a knowledge graph to analyze and score potential therapies based on patient profiles, incorporating accepted therapies defined by subject matter experts, and identifying unbounded therapy options by generating relative efficacy structures from published literature, allowing for the identification and evaluation of novel therapies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual review of published literature is performed by subject-matter experts, then therapy efficacy can be evaluated, but the process becomes time-consuming and expensive
Solution Approach 1:
The patent introduces an automated literature review system as an intermediary between published literature and subject-matter experts. This system uses natural language processing and machine learning to automatically extract, analyze, and synthesize therapy efficacy information from published literature, providing structured insights to experts while eliminating their time-consuming manual review work
Solution Approach 2:
The patent replaces the mechanical manual review process with an automated computational system. Machine learning models and natural language processing algorithms substitute for human experts in the initial literature screening and analysis phases, dramatically reducing time and cost while maintaining evaluation quality
2Adaptability or versatility
If the set of accepted therapies is expanded to include new treatment options, then patient outcomes can be improved, but the process becomes laborious and lengthy
Solution Approach 1:
The patent implements preliminary automated analysis of new therapies against established efficacy criteria before they are considered for addition to the accepted set. The system pre-screens potential therapies using machine learning models trained on historical literature, identifying promising candidates that meet predefined standards, thereby accelerating the approval process while maintaining rigor
Solution Approach 2:
The patent establishes a feedback loop where outcomes from using new therapies are continuously monitored and fed back into the system. This feedback mechanism allows the automated system to learn from real-world performance data, refining its evaluation criteria and enabling faster, more accurate assessment of future therapy candidates
3Reliability
If manual literature review is used to determine best practices, then therapy guidelines can be established, but the guidelines become outdated quickly due to rapid literature expansion
Solution Approach 1:
The patent implements continuous automated literature monitoring and analysis that operates without interruption. The system continuously ingests new published literature, analyzes it using machine learning models, and updates therapy guidelines in real-time or near-real-time, ensuring guidelines remain current with the latest research without requiring periodic manual reviews
Solution Approach 2:
The patent transforms static, periodic guideline updates into a dynamic, continuous process. The automated system adapts guideline recommendations based on emerging literature, allowing guidelines to evolve dynamically as new evidence becomes available, rather than remaining fixed until the next manual review cycle
Data Source
AI summary
Techniques for unbounded therapy evaluation are provided. A request to suggest a potential therapy based on a patient profile is received. A plurality of accepted therapies is determined based on the patient profile, where the plurality of accepted therapies is based on stored definitions obtained from one or more subject matter experts. Next, a plurality of therapy components is identified based on the plurality of accepted therapies. A plurality of potential therapies is then identified based on the plurality of therapy components, where none of the plurality of potential therapies are included in the plurality of accepted therapies. A score is generated for a potential therapy of the plurality of potential therapies based on analyzing a knowledge graph, where the score indicates a suitability of the potential therapy for a patient associated with the patient profile. Finally, the potential therapy is provided, along with an indication of the score.