What is it about?
Objectives: To investigate the variables influencing the clinical classification of myasthenia gravis and develop an intelligent classification model derived from clinical data. Methods: 437 patients with myasthenia gravis who were hospitalized in the outpatient clinic of Lingnan Famous Doctor Liu Xiaobin and the spleen and stomach ward of The First Affiliated Hospital of Guangzhou University of Chinese Medicine were retrospectively analyzed. Combining the decision tree and clinical experience, the disease classification strategy was explored, and the models of neural network, support vector machine and deep neural network for disease classification were constructed. Results: A straightforward and user-friendly disease classification retrieval table was created. Additionally, following comparison, the deep neural network produced the best classification accuracy. Conclusions: The study proposed and developed the first quantitative disease classification retrieval table for myasthenia gravis. The table is concise and clear, with clear criteria, and is characterized by objectivity, quantification, computer-free operation, convenience, and ease of use. Furthermore, a deep neural network model with high accuracy for myasthenia gravis classification was successfully realized, providing an effective AI-assisted diagnostic tool for the clinical work of myasthenia gravis.
Featured Image
Read the Original
This page is a summary of: A study on the construction of myasthenia gravis disease classification retrieval table and its intelligent classification model, January 2024, ACM (Association for Computing Machinery),
DOI: 10.1145/3675417.3675524.
You can read the full text:
Contributors
The following have contributed to this page