Improving Clinical Question Answering with Multi-Task Learning: A Joint Approach for Answer Extraction and Medical Categorization

2025-02-18

AI Summary

Existing clinical question-answering (CQA) systems struggle to perform fine-grained medical semantic classification of answers extracted from electronic medical records (EMRs), hindering structured retrieval and interpretable decision support. To address this, we propose the first joint multi-task learning framework for CQA that simultaneously models answer span extraction and fine-grained classification into five standardized clinical categories: diagnosis, medication, symptom, procedure, and laboratory test. Our architecture employs ClinicalBERT as a shared encoder and features a dual-head decoder—one for span prediction and another for category classification—trained end-to-end on the emrQA dataset. Experimental results demonstrate a 2.2-point improvement in F1-score over prior methods and achieve 90.7% accuracy in answer categorization. This significantly enhances the structured representation of EMR-derived clinical information and strengthens the foundation for explainable, category-aware clinical decision support.

Technology Category

• Natural Language Processing: Question Answering
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web question answering
• Web Mining and Content Analysis: Community question answering
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Clinical Question Answering (CQA) plays a crucial role in medical decision-making, enabling physicians to extract relevant information from Electronic Medical Records (EMRs). While transformer-based models such as BERT, BioBERT, and ClinicalBERT have demonstrated state-of-the-art performance in CQA, existing models lack the ability to categorize extracted answers, which is critical for structured retrieval, content filtering, and medical decision support. To address this limitation, we introduce a Multi-Task Learning (MTL) framework that jointly trains CQA models for both answer extraction and medical categorization. In addition to predicting answer spans, our model classifies responses into five standardized medical categories: Diagnosis, Medication, Symptoms, Procedure, and Lab Reports. This categorization enables more structured and interpretable outputs, making clinical QA models more useful in real-world healthcare settings. We evaluate our approach on emrQA, a large-scale dataset for medical question answering. Results show that MTL improves F1-score by 2.2% compared to standard fine-tuning, while achieving 90.7% accuracy in answer categorization. These findings suggest that MTL not only enhances CQA performance but also introduces an effective mechanism for categorization and structured medical information retrieval.

Problem

• Improves Clinical Question Answering accuracy
• Enables medical answer categorization
• Enhances structured medical information retrieval

Innovation

• Multi-Task Learning framework
• Answer extraction and categorization
• Standardized medical category classification