基于常规血液和生化检测数据,构建可解释的机器学习勃起功能障碍诊断模型
Yanghao Tai1,2, Bin Chen1, Yingming Kong1
1Third Hospital of Shanxi Medical University, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences Tongji Shanxi Hospital, Taiyuan, 030032, China.
European journal of medical research
|February 26, 2026
概括
机器学习模型分析了常规血液标记物,以确定勃起功能障碍 (ED) 的潜在风险因素. 葡萄糖血红蛋白,乳酸脱酶和红细胞分布宽度的升高与ED易感性增加有关.
科学领域:
- 泌尿器科 泌尿器科 泌尿器科 泌尿器科
- 生物化学 生物化学
- 数据科学数据科学数据科学
背景情况:
- 勃起功能障碍 (ED) 的发病率很高,但由于目前的限制和患者的不情愿,诊断是具有挑战性的.
- 机器学习 (ML) 在疾病诊断方面表现有前途,但尚未使用标准血液标记物应用于ED.
研究的目的:
- 通过机器学习探索常规血液和生化标志物用于勃起功能障碍的诊断潜力.
- 为了确定特定的血液参数与增加易受性障碍的相关性.
主要方法:
- 利用了来自国家健康和营养检查调查 (2001-2004) 的数据.
- 采用特征选择 (博鲁塔算法) 和逐步回归.
- 开发和评估了多种ML模型,包括后勤回归,XGBoost,SVM,LightGBM和CatBoost,并通过SHAP分析进行解释.
主要成果:
- 包括945名ED患者和2520名没有ED患者;在常规血液参数中观察到显著差异.
- 常规血液和生化标志物,包括高血糖血红蛋白,乳酸脱酶和红细胞分布宽度,与ED风险增加相关.
- CatBoost模型在特定的标准化净收益门内证明了效用.
结论:
- 常规的血液和生化参数显示出了解勃起功能障碍的病因学的潜力.
- ML模型可以有效地分析这些标记,以评估ED风险.
- 对这些标记物的进一步研究可以改善ED诊断和管理.
相关概念视频
Disorders of the Male Reproductive System
5.2K
Men's health issues are increasingly recognized as significant, with several conditions posing common threats. Among these, testicular cancer is especially prevalent in younger men, particularly those aged 20 to 35 years. The disease often manifests as a painless mass in the testicles, sometimes accompanied by a sensation of heaviness or a dull ache.
Prostate disorders are another major concern. These conditions can impair urinary flow due to the prostate's location around the urethra....
Prostate disorders are another major concern. These conditions can impair urinary flow due to the prostate's location around the urethra....
5.2K
Errors occurring during blood pressure monitoring
1.6K
Blood pressure monitoring is a crucial clinical procedure in diagnosing and managing various cardiovascular conditions. Despite its significance, the accuracy of blood pressure measurements can be compromised by multiple factors, potentially leading to either falsely high or low readings. These inaccuracies are critical as they can significantly impact patient care. So, it is vital to understand these challenges deeply and adopt strategic approaches to minimize errors.
Several factors...
Several factors...
1.6K

