机器学习用于对慢性病进行分类,并使用家庭测量预测肌素水平
Brady Metherall1, Anna K Berryman2, Georgia S Brennan2
1Mathematical Institute, University of Oxford, Radcliffe Observatory Quarter, Andrew Wiles Building, Woodstock Rd, Oxford, OX2 6GG, UK. metherall@maths.ox.ac.uk.
机器学习模型对早期慢性病 (CKD) 检测有希望. 随机森林 (RF) 在使用家庭特征对CKD进行分类方面表现优于人工神经网络 (ANN),这表明广泛查的潜力.
科学领域:
- 腎臟病學 (nephrology) 是一種醫學專業.
- 医疗信息学 医疗信息学
- 计算生物学 计算生物学
背景情况:
- 慢性病 (CKD) 是一个重要的全球健康问题.
- 早期发现CKD对于有效的患者管理和改善结果至关重要.
- 基于机器学习的CKD检测不同临床特征集的实用性需要进一步研究.
研究的目的:
- 评估人工神经网络 (ANN) 和随机森林 (RF) 的性能,用于CKD分类和肌素预测.
- 在CKD检测模型中比较家庭,监测和实验室临床特征的有效性.
- 确定与CKD相关的关键临床变量和并发症.
主要方法:
- 使用了400名患者的数据集,具有25个输入特征,分为家庭,监测和实验室特征集.
- 使用人工神经网络 (ANN) 和随机森林 (RF) 进行分类和回归任务.
- 进行了10倍的交叉验证,以评估模型性能,使用准确性,真正率 (TPR),真负率 (TNR) 和R平方 (R2) 等指标来进行肌素预测.
主要成果:
- 随机森林 (RF) 在使用家庭特征进行CKD分类时,比ANN (82.9%) 获得了更高的准确性 (92.5%).
- 在使用监测和实验室特征时,ANN和RF都表现出高精度 (超过98%).
- 实验室特征与家庭特征相比,对肌素预测的R2得分大约高出0.3分.
- 功能重要性分析强调了血红蛋白,血尿素,高血压和糖尿病是检测CKD的关键因素.
结论:
- 机器学习模型,特别是射频模型,对CKD诊断和分类有很大的前景.
- 使用在家功能与ML模型的使用可以促进早期发现CKD的全人口查.
- 识别关键的临床变量和并发性疾病可以加强现有知识,并有助于制定有针对性的CKD管理策略.
更多相关视频
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
相关概念视频
Factors Affecting Renal Clearance: Renal Impairment
One condition associated with renal failure is uremia. Uremia is characterized by impaired glomerular filtration and fluid accumulation in the body. This condition hinders the renal clearance of drugs, resulting in drug accumulation and potential...
Dialysis
Acute kidney injury develops suddenly and can be caused by pre-renal causes (e.g., hypovolemia, shock), intrinsic renal causes (e.g., acute tubular necrosis), or post-renal causes (e.g., urinary obstruction). In contrast, chronic renal failure progresses gradually over time and is often...
Determination of Renal Drug Clearance: Graphical and Midpoint Methods
The graphical method involves plotting the rate of drug excretion in urine against the plasma drug concentration. By analyzing the graph, the clearance can be calculated and obtained. Drugs rapidly excreted by the kidneys exhibit a...
Renal Clearance
Renal clearance refers to the volume of plasma cleared of a specific substance, such as creatinine, per unit of time. To measure clearance, urine samples are collected over a 24-hour period during each bladder voiding, followed by a single blood sample at the...
