Social Media Side-Effect Tracking via NLP
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for identifying and tracking drug side-effects are limited by small sample sizes in clinical trials and reliance on busy healthcare professionals, leading to incomplete and inefficient post-market monitoring.
Innovation Solution
A system utilizing natural language processing, including side-effect recognizers, relationship extractors, and reporting systems, that aggregates data from social media to identify and track adverse effects associated with substances, leveraging recurrent neural networks and distributed databases for efficient data management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If clinical trials are conducted with limited patient numbers to comply with regulatory requirements, then the trial can be completed efficiently, but the reliability of side-effect identification deteriorates
Solution Approach 1:
The patent introduces social media data as an intermediary source to bridge the gap between limited clinical trial data and comprehensive side-effect identification. The system uses NLP processors to extract side-effect information from social media platforms, creating an additional data channel that complements traditional clinical trials and enhances detection reliability without extending trial duration
Solution Approach 2:
The patent transitions from a single-dimension approach (clinical trials only) to a multi-dimensional approach by incorporating social media data from different platforms and sources. This dimensional expansion allows the system to gather side-effect information from diverse user experiences, thereby improving identification reliability while maintaining efficient trial completion
2Device complexity
If drug companies rely on healthcare professionals to report side-effects after drug approval, then the reporting system is simple to maintain, but the completeness of side-effect tracking deteriorates due to professionals being busy with other tasks
Solution Approach 1:
The patent enables patients to self-report side-effects directly through social media platforms without requiring healthcare professionals to manually collect and submit reports. The NLP system automatically processes these self-generated reports, extracting side-effect information and relating it to specific drugs, thereby maintaining simple system architecture while dramatically improving information completeness
Solution Approach 2:
The patent replaces the manual mechanical process of healthcare professionals reporting side-effects with an automated NLP-based system that processes social media data. This substitution eliminates the bottleneck of professional availability while maintaining reporting simplicity through automated data extraction and analysis
3Loss of information
If social media data is processed to identify side-effects, then the comprehensiveness of side-effect tracking is improved, but the memory usage and data processing complexity increase
Solution Approach 1:
The patent segments the social media data processing task into distinct functional modules: data collection from multiple platforms, NLP processing for side-effect identification, relationship extraction for drug-side effect associations, and result aggregation. This segmentation manages complexity by organizing processing steps into manageable, independent components while maintaining comprehensive side-effect tracking
4Reliability
If extensive research and clinical trials are conducted to identify side-effects, then the reliability of side-effect identification is improved, but the time and resources required increase
Solution Approach 1:
The patent performs preliminary action by continuously monitoring and analyzing social media data before and during clinical trials. This ongoing preliminary analysis allows the system to identify potential side-effects early, enabling faster decision-making and reducing the overall time required for extensive research and trial processes while maintaining identification reliability
Data Source
AI summary
A system for determining adverse effects associated with a substance includes a side-effect recognizer, a relationship extractor, a processor, and a reporting system. The side-effect recognizer utilizes a first recurrent neural network (RNN) to identify a first portion of received data associated with an adverse effect to thereby determine the adverse effect associated with the received data. The relationship extractor utilizes a second RNN to identify a second portion of the received data associated with a substance and a third portion of the received data that indicates a relationship between the substance and the adverse effect to thereby determine the substance associated with the received data and the relationship between the substance and the adverse effect. The processor is in communication with the adverse effect recognizer and the substance relationship extractor and aggregates and relates the adverse effect, substance, and relationship. The reporting system is in communication with the processor and generates a report to convey the relationship between the substance and the adverse effect.