一个可解释的机器学习框架,用于分析心肺疾病与气候污染物传感器数据之间的相互作用.
Vito Telesca1, Maríca Rondinone1
1Department of Engineering, University of Basilicata, 85100 Potenza, Italy.
Sensors (Basel, Switzerland)
|August 14, 2025
概括
机器学习模型根据环境因素预测心肺呼吸系统疾病急诊室的入院情况. 高一氧化碳,湿度,低压和温和的温度增加了住院人数,有助于公共卫生规划.
科学领域:
- 环境健康 环境健康
- 流行病学 流行病学
- 机器学习 机器学习
背景情况:
- 心肺呼吸道疾病 (CRD) 构成了严重的公共卫生负担.
- 环境因素越来越多地被认为是导致CRD恶化的因素.
- 需要有效的工具来将环境数据与健康结果联系起来,以便主动管理.
研究的目的:
- 开发和验证可解释的机器学习 (ML) 框架.
- 分析环境因素与CRDs每日急诊室 (ER) 招生之间的关系.
- 确定影响CRD录取的关键环境变量和关键暴露值.
主要方法:
- 利用了11年的 (2013-2023) 健康和环境数据 (气象,空气质量).
- 与四个ML模型进行了比较,使用了10倍的交叉验证以获得可靠性.
- 应用SHAP用于全球模型解释性和LIME用于本地分析和值识别.
主要成果:
- XGBoost 显示出优异的预测性能 (R2 = 0.901,MAE = 0.047).
- 确定了影响因素:高一氧化碳 (CO),相对湿度 (RH),低气压 (P_atm) 和温和的平均温度 (Tavg).
- 确定了增加CRD入院风险的临界值:CO > 0.84 mg/m3,P_atm ≤ 1006.81 hPa,Tavg ≤ 17.19 °C,RH > 70.33%. 这种值是指:
结论:
- 可解释的ML模型有效地将环境条件与CRD ER输入联系起来.
- 调查结果支持加强公共卫生监测和医疗保健资源分配.
- 该框架为环境监测和预防性医疗保健策略提供了有价值的工具.
更多相关视频
14:28Software for Analysis of Heart Rate and Blood Pressure Time-series Data from the Valsalva Maneuver
Published on: June 27, 2025
388
08:51Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts
Published on: September 20, 2024
1.5K
相关概念视频
Assessment of Respiration
1.3K
The respiratory system's basic structures and primary functions lay the foundation for nurses' comprehensive respiratory assessments. This assessment includes subjective and objective data to gauge the patient's respiratory health.
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like...
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like...
1.3K
Asthma-II: Pathophysiology and Classification
2.8K
Asthma is a prevalent chronic respiratory condition marked by inflammation and hyperresponsiveness of the airways. Its pathophysiology involves complex interactions among inflammatory pathways, immune responses, and neural mechanisms.
Additionally, environmental and genetic factors play crucial roles in determining an individual's susceptibility to asthma and the severity of their condition.
Critical processes in asthma pathophysiology include:
Additionally, environmental and genetic factors play crucial roles in determining an individual's susceptibility to asthma and the severity of their condition.
Critical processes in asthma pathophysiology include:
2.8K
