针对疾病诊断的Boruta,SHAP和Borutashap的比较性能分析:一项使用多个机器学习算法的研究
Chukwuebuka Joseph Ejiyi1, Zhen Qin1, Chiagoziem Chima Ukwuoma1
1School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China.
Network (Bristol, England)
|March 21, 2024
概括
通过识别关键特征和提高模型解释性,SHAP (夏普利增材扩展) 和LightGBM (LGBM) 显著改善了疾病诊断. 这种方法可以为医疗应用提供更准确,更易理解的诊断工具.
科学领域:
- 医疗信息学 医疗信息学
- 计算生物学 计算生物学
- 医疗保健中的机器学习
背景情况:
- 可解释机器学习 (ML) 模型对于疾病诊断和临床决策至关重要.
- 特性选择方法有助于在复杂的医疗数据集中识别关键指标.
- 现有的ML模型往往缺乏透明度,阻碍了临床采用.
研究的目的:
- 为了评估和比较疾病诊断的特征选择技术 (Boruta,SHAP,BorutaShap).
- 评估在选定的特征上训练的各种ML算法的性能.
- 提高医学诊断中的ML模型的可解释性.
主要方法:
- 使用Boruta,SHAP (夏普利添加式扩展) 和BorutaShap进行特征选择.
- 在预处理的医疗数据集上训练了六个ML算法 (LR,SVM,ETC,AdaBoost,RF,LGBM).
- 使用准确度,精度,回忆和F1分数来评估模型性能.
主要成果:
- SHAP表现出卓越的性能,在各种疾病数据集中达到高平均准确率 (例如,甲状腺99.55%).
- 在大多数疾病状态中,LightGBM (LGBM) 算法显示了最高的平均准确性 (91.00%).
- SHAP显著提高了模型的解释性,为疾病机制提供了洞察力.
结论:
- SHAP是用于疾病诊断的高效特征选择方法,提高了准确性和可解释性.
- 当与强大的特征选择相结合时,LGBM是一种强大的ML算法,用于疾病预测.
- 这项研究为开发更准确,更透明的诊断ML模型提供了宝贵的见解.
相关概念视频
01:15Receiver Operating Characteristic Plot
154
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
154
01:20Comparing the Survival Analysis of Two or More Groups
181
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...
181