سومین کنفرانس بین المللی مهندسی و علوم کامپیوتر و اولین کنفرانس ملی سامانه های هوشمند، کلان داده و رایانش پیشرفته

رفتن به صفحه اصلی

ارائه مجازی مقاله

کد مقاله CCES-1200

عنوان Unsupervised Learning Approach for Optimal Finger Selection in Nail Capillaroscopy for Systemic Lupus Erythematosus Diagnosis

نویسندگان Habibollah Jafari

چکیده This study investigated the use of unsupervised machine learning to identify hidden patterns in microvascular changes within patients with Systemic Lupus Erythematosus (SLE). Analyzing capillaroscopic data from eight fingers per patient using techniques like Principal Component Analysis (PCA) and K-Means clustering, we identified two distinct groups of fingers based on the severity of abnormalities. The analysis consistently highlighted the left middle, right middle, and right ring fingers as the most valuable for diagnostic purposes, demonstrating frequent and significant abnormalities. Consequently, the study suggests that focusing on these three fingers can improve the efficiency and accuracy of SLE capillaroscopy while maintaining diagnostic quality.

فایل ها

فایل ارایه مقالات پوستری

محتوای ارائه مجازی مقاله

نظرات