Question Generation System for Automated Medical Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Patients often provide limited or incomplete symptom information, which hinders accurate automatic diagnosis, necessitating a system to guide patients in providing more relevant information through targeted questioning.
Innovation Solution
A question generation system utilizing a knowledge graph to identify candidate symptoms and generate questions based on observed symptoms, incorporating dimensional information and discriminative scoring to enhance diagnostic accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automatic diagnosis is performed based on limited patient-provided symptom information, then the workload of doctors is reduced and more patients can be accommodated, but the accuracy of diagnosis deteriorates
Solution Approach 1:
The system implements feedback by automatically generating follow-up questions based on initial symptom inputs and patient responses. The question generation module continuously adapts the questioning process based on the patient's answers, refining the diagnostic query sequence to gather necessary information for accurate diagnosis while maintaining automated operation.
Solution Approach 2:
The system performs preliminary action by pre-generating candidate questions and symptom candidates before final diagnosis is reached. The question generation module prepares multiple potential follow-up questions based on the knowledge graph and current symptom state, selecting the most relevant questions in advance to guide the diagnostic process efficiently.
2Measurement precision
If more symptom information is collected from patients to improve diagnosis accuracy, then the quality of automatic diagnosis is improved, but the time and complexity of the diagnostic process increases
Solution Approach 1:
The system applies partial action by selectively collecting only the necessary symptom information required for accurate diagnosis rather than gathering all possible symptoms. The question generation module identifies and asks only for the most relevant missing information based on the knowledge graph, avoiding unnecessary questions that would waste time while still achieving diagnostic accuracy.
Solution Approach 2:
The diagnostic process is made dynamic through adaptive question generation. The system adjusts the questioning sequence based on patient responses, dynamically selecting the next most relevant question from candidate questions. This dynamic adaptation allows the system to efficiently gather necessary information without following a fixed, time-consuming questionnaire structure.
3Measurement precision
If a comprehensive questioning system is implemented to guide patients in providing complete information, then the quality of automatic diagnosis is improved, but the complexity of the system increases
Solution Approach 1:
The system is segmented into distinct functional modules: symptom input module, question generation module, knowledge graph module, and diagnosis module. The question generation module itself is segmented into sub-components including candidate question generation, question selection, and question output. This modular segmentation manages system complexity by allowing each module to be developed and maintained independently while working together to achieve accurate automatic diagnosis.
Data Source
AI summary
Systems and methods are disclosed for question generation to obtain more related medical information based on observed symptoms from a patient. In embodiments, possible diseases associated with the observed symptoms are generated by querying a knowledge graph. In embodiments, candidate symptoms associated with the possible diseases are also identified and are combined with the observed symptoms to obtain combined symptom sets. In embodiments, discriminative scores for the candidate symptom sets are determined and candidate symptoms with top discriminative scores are selected. In embodiments, these selected candidate symptoms may be checked for conflicts with observed symptoms and removed from further consideration if a conflict exists. In embodiments, one or more questions may be generated based on the remaining selected candidate systems to aid in collecting information about the patient. In embodiments, the process may be repeated with the updated observed symptoms.