Hyper Optimization Approach for Disease Classification

EasyChair Preprint no. 11835

Abstract

This scientific paper explores an innovative approach to disease classification by leveraging advanced language models for the analysis of symptoms. Traditional methods of disease classification often rely on structured data and predefined criteria, which may limit their adaptability to evolving medical knowledge. In contrast, our proposed methodology utilizes state-of-the-art natural language processing techniques to extract meaningful insights from unstructured symptom descriptions. We employ advanced language models, such as GPT-3.5, to process and understand the nuanced language used in describing symptoms, enabling more accurate and dynamic disease classification. This paper presents the methodology, experimental results, and implications of employing language models to optimize disease classification based on symptom analysis.

Keyphrases: Classification, diagnosing, Disease

@Booklet{EasyChair:11835,
  author = {Amal Ali},
  title = {Hyper Optimization Approach for Disease Classification},
  howpublished = {EasyChair Preprint no. 11835},

  year = {EasyChair, 2024}}