基于机器学习的肺栓塞预测预后使用营养和炎症指数
Zengzhi Lian1, Xue-Ni Wei2, Dayang Chai3
1Department of Pulmonary and Critical Care Medicine, Taicang Affiliated Hospital of Soochow University, Suzhou, Jiangsu Province, China.
概括
机器学习模型利用高级肺癌炎症指数 (ALI) 和中性粒对白蛋白比率 (NAR) 准确预测肺栓塞 (PE) 预后. 在这项研究中,XGBoost模型表现最好.
科学领域:
- 医疗信息学 医疗信息学
- 生物统计学 生物统计学
- 在瘤学瘤学.
背景情况:
- 肺栓塞 (PE) 预后预测对于患者管理至关重要.
- 营养和炎症指数提供了改善预后准确性的潜力.
- 晚期肺癌炎症指数 (ALI) 和中性粒细胞对白蛋白的比率 (NAR) 是关键指标.
研究的目的:
- 开发和评估用于预测PE预后的机器学习 (ML) 模型.
- 评估ALI和NAR在基于ML的预后模型中的实用性.
- 为了提高PE预后预测的准确性.
主要方法:
- 对312名患者 (254名幸存者,58名非幸存者) 的回顾性分析.
- 波鲁塔算法用于变量选择.
- 四个ML模型 (XGBoost,随机森林,物流回归,SVM) 被训练和评估.
主要成果:
- 该XGBoost模型实现了最高的性能:准确度0.882,F1得分0.889,AUC0.873.
- 确定了关键预测因素:呼吸衰竭,日志-ALI,白蛋白水平,年龄,透气血压和NAR.
- 所有评估的ML模型都在预测PE预后方面表现出有效性.
结论:
- 机器学习模型,特别是XGBoost,在预测PE预后方面表现强.
- 呼吸系统衰竭,ALI,白蛋白水平,年龄,透气血压和NAR是PE的显著预后因素.
- 该研究强调了将营养和炎症指数整合到ML模型中的潜力,以改善PE的临床决策.
更多相关视频
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
8.2K
07:57Establishment of a Minimally Invasive Rat Model of Pulmonary Embolism Using Autologous Blood Clots
Published on: October 25, 2024
273
相关概念视频
01:13Radiological Investigation III: Pulmonary Angiogram and PET Scan
86
Radiological investigations are paramount in the diagnosis and management of various pulmonary diseases. Two essential investigations are the Pulmonary Angiogram and the Positron Emission Tomography (PET) Scan.
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
86
01:19Blood Studies for Cardiovascular System II: CRP, Hcy, and Cardiac Natriuretic Peptide Markers
60
Cardiac biomarkers are critical in diagnosing, prognosing, and managing cardiovascular diseases. Routine measurement of specific biomarkers such as B-type natriuretic peptide (BNP), C-reactive protein (CRP), and homocysteine (Hcy) is common practice in clinical settings to evaluate heart function and predict cardiovascular events.
These markers indicate stress or strain on the heart muscle:
Natriuretic Peptides (BNP)
Cardiac myocytes produce these hormones in response to ventricular stretching...
These markers indicate stress or strain on the heart muscle:
Natriuretic Peptides (BNP)
Cardiac myocytes produce these hormones in response to ventricular stretching...
60