预测COVID-19短期再感染的高风险因素在风湿病患者中:基于XGBoost算法的一个建模研究
Yao Liang1, Siwei Xie2, Xuqi Zheng1
1Department of Rheumatology and Immunology, Third Affiliated Hospital of Sun Yat-Sen University, 600 Tianhe Road, Tianhe District, Guangzhou, China.
机器学习模型预测了风湿性疾病患者的短期COVID-19再感染风险. 焦虑,疲劳和药物缓慢显著影响再感染的可能性,指导有针对性的预防策略.
科学领域:
- 类风湿病学 类风湿病学
- 传染性疾病 传染性疾病
- 人工智能的人工智能
背景情况:
- 短期的COVID-19再感染为风湿性疾病患者带来了管理挑战.
- 预测和减轻再感染风险对于改善患者的治疗结果至关重要.
研究的目的:
- 开发和验证可解释的机器学习模型,用于预测风湿性疾病患者的短期COVID-19再感染.
- 确定与再感染风险相关的关键临床和心理因素.
主要方法:
- 使用可解释的机器学习开发了四种预测模型,这些模型基于来自543名类风湿病患者的数据.
- 评估了心理健康 (FACIT-F,PHQ-9,GAD-7,PSQI) 和健康状况 (EQ-5D-3L,VAS) 的情况.
- 模型性能使用AUC,AUPRC和G-平均值进行评估,并对可解释性进行SHAP分析.
主要成果:
- 极端梯度增强 (XGBoost) 模型实现了0.91.91的AUC.
- 重要的预测因素包括葡萄糖皮质体缩,csDMARDs缩,症状计数和GAD-7分数.
- 较高的FACIT-F得分与较低的再感染风险有关.
结论:
- 可解释的AI模型有效地预测了类风湿性疾病患者的短期COVID-19再感染风险.
- 焦虑 (GAD-7),疲劳 (FACIT-F),药物逐渐减少和最初的疾病活动是关键预测因素.
- 研究结果支持有针对性的干预措施,以减少这种脆弱人群的再感染率.
更多相关视频
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
08:51Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts
Published on: September 20, 2024
相关概念视频
Steps in Outbreak Investigation
Factors Affecting the Risk of Infection
The integrity and count of the white blood cells help the body resist pathogens and fight infection. When impaired, it reduces the body's resistance to pathogens. The acidic pH levels of the gastrointestinal, genitourinary tracts, and skin...
Pulmonary Tuberculosis I
Causative Organism
The primary infectious agent causing tuberculosis is Mycobacterium tuberculosis, a slow-growing, acid-fast, aerobic rod that exhibits sensitivity to heat and ultraviolet light. Instances of Mycobacterium bovis and Mycobacterium avium contributing to the development of TB infection are rare.
Mode of...
Genome-wide Association Studies-GWAS
GWAS does not require the identification of the target gene involved in...
The JAK-STAT Signaling Pathway
