<![CDATA[Headache disorders represent a significant global neurological challenge, yet medical diagnosis is often hindered by subjective patient complaints and limited facilities. This study proposes an integrated model combining Natural Language Processing (NLP) and Case-Based Reasoning (CBR) to enhance the accuracy of medical decision-making for headache cases. The model utilizes the Random Forest algorithm for NLP classification and Cosine Similarity within the CBR framework to identify case relevance. The dataset consists of medical records for two types of headaches: Cluster headache (G44.0) and Tension-type headache (G44.2). Experimental results demonstrate that data augmentation significantly improves model performance, increasing accuracy from 62% to 69%. For the G44.0 label, the model achieved a precision of 0.84, while the G44.2 label reached a recall of 0.87. Furthermore, the CBR system strengthens the diagnosis with a similarity level of up to 0.82 and continuous learning capabilities through the Retain stage. This integration effectively provides faster, more targeted diagnostic recommendations for medical professionals.]]>
Copyrights © 2026
