Medical Article Recommendation System for Clinical Decision Support
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Clinicians face time-intensive manual searches for relevant medical literature during patient visits, which limits the time available for informed decision-making due to the reliance on keyword-based searches and the inability to efficiently process multiple concepts simultaneously.
Innovation Solution
A computer-implemented system that identifies new appointment scheduling data, correlates it with historical patient data using a graph data structure, and automatically recommends relevant articles from databases, presenting them in a user-friendly format through a news feed, calendar, or electronic medical record.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If clinicians perform manual keyword-based searches in medical databases, then they can find relevant articles, but the process becomes time-intensive and reduces productivity
Solution Approach 1:
The system performs preliminary actions by automatically retrieving and pre-processing relevant medical articles before the clinician needs them. The article recommendation system proactively queries databases, filters results, and prepares articles for review, eliminating the need for clinicians to perform time-consuming manual searches during patient visits.
Solution Approach 2:
The patent introduces an intermediary article recommendation system that acts as a mediator between medical databases and clinicians. This system handles the complex search and filtering operations, translating clinician needs into database queries and presenting processed results, thereby shielding clinicians from the time-intensive manual search process while maintaining comprehensive article retrieval.
2Adaptability or versatility
If clinicians review multiple concepts simultaneously, then the scope of research expands, but the complexity of processing increases
Solution Approach 1:
The system segments the complex multi-concept search task into manageable components. It processes each concept separately through structured query construction, retrieves articles for each concept independently, and then integrates results with relevance scoring. This segmentation allows the system to handle multiple concepts simultaneously without overwhelming complexity.
Solution Approach 2:
The article recommendation system is designed with universal functionality to handle diverse medical concepts through a unified processing framework. The same query construction, retrieval, and ranking mechanisms work across different concepts and medical domains, allowing the system to expand its conceptual scope without proportionally increasing operational complexity.
3Reliability
If clinicians spend more time preparing for each patient appointment, then the quality of care improves, but the total number of patients they can see decreases
Solution Approach 1:
The system performs preliminary preparation by automatically identifying and presenting relevant articles before the clinician meets with the patient. Articles are retrieved and organized based on the patient's medical record and appointment context, allowing clinicians to review key information quickly during the appointment rather than preparing extensively beforehand.
Solution Approach 2:
The article recommendation system serves itself by automatically querying databases, filtering results, and presenting articles without requiring clinician intervention. The system autonomously processes patient data, generates search queries, retrieves relevant articles, and ranks them by relevance, freeing clinicians to focus on patient care rather than information gathering.
Data Source
AI summary
Methods, systems, and non-transitory computer readable mediums are disclosed for recommending medically-relevant articles. One method comprises receiving health data associated with a patient, storing the health data in a data structure as historical patient data, identifying new appointment scheduling data associated with the patient, determining an appointment subject associated with the new appointment scheduling data, determining a correlation between the new appointment scheduling data and the historical patient data, searching one or more databases for one or more relevant articles, retrieving the one or more relevant articles, generating a recommendation for the one or more relevant articles, and presenting the recommendation for the one or more relevant articles to a user through at least one of a news feed, a calendar, or an electronic medical record (EMR) associated with the patient.