使用临床和人口学描述符,机器学习对部唾液腺瘤的分类
Luís Arthur de Melo Tassinari1, Anna Luíza Damaceno Araújo2,3, Sebastião Silvério de Sousa-Neto4
1Institute of Science and Technology (ICT-UNIFESP), Federal University of São Paulo, São José Dos Campos, São Paulo, Brazil.
机器学习模型对 palatal 唾液腺瘤的分类有前途,由于罕见的恶性亚型,实现高特异性但敏感性有限. XGBoost 展示了最好的性能.
科学领域:
- 在瘤学瘤学.
- 医疗信息学 医疗信息学
- 计算生物学 计算生物学
背景情况:
- 宫唾液腺瘤代表了一组多样化的瘤.
- 准确的临床分类对于适当的患者管理和治疗计划至关重要.
研究的目的:
- 评估机器学习 (ML) 模型在分类 palatal 唾液腺瘤中的有效性.
- 评估人口统计和临床数据对使用ML进行瘤分类的有用性.
主要方法:
- 四个ML模型 (XGBoost,MLP,SVM,RF) 在100名患者的数据上进行了训练和测试.
- 该研究采用超参数优化 (网格搜索) 和五倍交叉验证.
- 使用准确度,宏观平均灵敏度,特异性,精度和F1分数来衡量性能.
主要成果:
- XGBoost和MLP实现了最高的平均精度 (81%),其次是SVM (80%) 和RF (79%).
- 所有模型都表现出高特异性 (85% - 90%),但宏观平均敏感性低,F1分数低 (<75%).
- 模型的性能在多形腺瘤 (PA) 中很好,但在较罕见的恶性瘤中下降.
结论:
- ML是 palatal 唾液腺瘤分类的可行工具,提供高特异性.
- 敏感性有限的原因是罕见恶性瘤子类的代表性不足.
- XGBoost 成为了最强大的和计算效率最高的模型.
更多相关视频
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
06:22Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
Published on: September 19, 2025
相关概念视频
Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
Classification of Epithelial Tissues: Glandular Epithelium
Multicellular glands are formed during early development when epithelial budding...
