通过比较机器学习算法来预测COVID-19死亡率,使用数据集,包括胸部计算机断层扫描严重性得分数据
Seyed Salman Zakariaee1, Negar Naderi2, Mahdi Ebrahimi3
1Department of Medical Physics, Ilam University of Medical Sciences, Ilam, Iran.
Scientific reports
|July 14, 2023
概括
机器学习模型有效地使用综合数据预测COVID-19患者的死亡率,包括CT严重性得分. 随机森林算法表现出卓越的性能,能够及时分层风险,并改善患者的生存率.
科学领域:
- 医疗信息学 医疗信息学
- 放射学 放射学是一门学科.
- 计算生物学 计算生物学
背景情况:
- 人工智能 (AI) 和机器学习 (ML) 越来越多地用于COVID-19死亡率预测.
- 现有的模型主要使用人口统计数据,风险因素和实验室结果,仅限于对成像数据的关注.
- 需要预后模型,将成像表现与临床和实验室预测因素相结合.
研究的目的:
- 开发一个高效的ML预后模型来预测COVID-19死亡率.
- 评估胸部CT严重性得分 (CT-SS) 与其他预测因素结合的预后作用.
- 为了比较八种不同的ML算法用于死亡率预测的性能.
主要方法:
- 从6854个疑似COVID-19病例中回顾55个特征的回顾性审查.
- 奇平方测试以确定死亡率的重要预测因素.
- 八个ML算法 (J48,SVM,MLP,k-NN,NB,LR,RF,XGBoost) 的训练和测试.
- 使用准确度,精度,灵敏度,特异性和AUC的性能评估.
主要成果:
- 最终样本包括815名COVID-19阳性患者 (54.85%男性,平均年龄57.22±16.76岁).
- 随机森林 (RF) 算法实现了最高的性能:97.2%的准确性,100%的灵敏性,94.8%的精度,94.5%的特异性和99.9%的AUC.
- 其他ML算法显示出良好的预测性能,AUC从81.2%到93.9%不等.
结论:
- 基于ML的预测模型利用常规数据,包括CT-SS,可以准确地分层COVID-19患者的风险.
- 拟议的RF模型在预测COVID-19死亡率方面表现出高效率.
- 这种方法有助于早期识别高风险患者,优化资源配置,并可能提高生存率.
更多相关视频
08:05Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.2K
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
8.3K
相关概念视频
Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
42
Calcium-Scoring CT ScanA calcium-scoring CT scan, also known as coronary artery calcium (CAC) scan, detects calcium deposits in the coronary arteries. This test assesses the risk of coronary artery disease (CAD), which can lead to cardiovascular events such as angina, heart failure, and sudden cardiac arrest.A calcium-scoring CT scan is generally recommended for individuals at intermediate risk of CAD without symptoms. It includes:Men aged 40-75 and women aged 50-75: Especially those with a...
42
Comparing the Survival Analysis of Two or More Groups
226
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...
226
