Symptom Complaint Prioritization via KNN and ML Triage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Accurate prioritization of medical attention and treatment for user symptom complaints is often inaccurate, leading to untreated conditions and frustration for both patients and medical professionals.
Innovation Solution
A system utilizing a computing device with a KNN module to process symptom complaint data, correlate it with expert knowledge, and generate a triage urgency category label, along with a supervised machine-learning model to output a disease criticality score, thereby prioritizing medical attention effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to prioritize medical attention, then the process is simple, but the accuracy of prioritization is poor leading to untreated conditions
Solution Approach 1:
The patent introduces machine learning models (KNN algorithm and supervised learning models) as intermediaries between symptom inputs and prioritization decisions. These models act as mediators that process symptom data through trained algorithms to generate accurate prioritization recommendations, resolving the contradiction by embedding intelligent intermediaries within the decision-making process
Solution Approach 2:
The system performs preliminary actions by pre-training machine learning models with extensive medical data before actual use. The KNN model is trained with symptom-disease relationships, and supervised models are pre-trained with disease criticality data, enabling accurate real-time prioritization without complex runtime processing
2Measurement precision
If machine learning models are used to improve prioritization accuracy, then prioritization accuracy improves, but computational complexity increases
Solution Approach 1:
The patent segments the prioritization task into distinct modular components: a KNN model for initial symptom-disease matching, followed by separate supervised learning models for different aspects of criticality assessment. This segmentation allows each model to specialize in specific functions, improving overall accuracy while managing computational complexity through division of labor
Solution Approach 2:
The system applies partial action by using the KNN model to identify only the most relevant suspected diseases from the full symptom set, then applying supervised models only to those specific cases. This avoids excessive computation on all possible disease states while maintaining high accuracy for the most critical prioritization decisions
Data Source
AI summary
A system for prioritizing user symptom complaint inputs. The system includes a KNN module operating on at least a computing device configured to receive a plurality of symptom complaint datums, receive suspected disease state training data, calculate an optimal vector output utilizing a k-nearest neighbor algorithm and generate an optimal vector output containing a suspected disease state. The system includes a triage module operating on at least a computing device configured to receive the optimal vector output, generate a triage urgency category label, select triage training data as a function of the triage urgency label, generate using a supervised machine-learning model a disease criticality model, evaluate the disease criticality score, and display the ranked disease criticality score for each of the plurality of suspected disease states.