从国家监测系统中估计急性C型肝炎病例中注射药物使用的患病率:基于随机森林的多重推算的应用
Shaoman Yin1, Kathleen N Ly, Laurie K Barker
1Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, Georgia.
Journal of public health management and practice : JPHMP
|July 23, 2024
概括
在型肝炎监测中,准确地归算注射药物使用 (IDU) 数据至关重要. 随机森林方法,特别是快速射频 (fRF),显著提高了IDU估计的数据准确性和效率.
科学领域:
- 公共卫生 公共卫生
- 流行病学 流行病学
- 数据科学数据科学数据科学
背景情况:
- 注射药物使用 (IDU) 是病毒性肝炎,艾滋病毒和过量综合症的关键驱动因素.
- 监控系统中缺少的IDU数据阻碍了对相关感染的理解.
- 链式方程多重推算 (MICE) 是一种常见的缺失数据方法,但其用于IDU推算的使用需要进一步研究.
研究的目的:
- 评估不同MICE模型的准确性和效率,用于在国家C型肝炎监测中归因缺少的注射药物使用数据.
- 为了比较基于随机森林 (RF) 的MICE归算与传统方法的类似列表删除 (LD).
主要方法:
- 利用了2019-2021年国家可通报疾病监测系统的急性型肝炎数据.
- 将LD与三个MICE模型进行比较:逻辑回归,预测平均匹配 (PMM) 和射频 (标准射频[sRF]和快速射频[fRF]).
- 使用偏差和根平均平方误差评估归算准确性;使用置信区间宽度评估效率.
主要成果:
- 估计的注射使用率从63.5% (LD) 增加到85.1% (fRF).
- 基于射频的MICE,特别是fRF,在LD,后勤回归和PMM上表现出卓越的准确性和效率.
- 即使数据不随机地丢失,fRF归算仍然很强大.
结论:
- 基于射频的MICE归算,特别是fRF,是解决国家可通知的疾病监测系统等监控系统中缺少的IDU数据的有价值方法.
- 纳入指定的IDU数据可以加强对IDU驱动的综合症的监测和预防策略.
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
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
7.5K
相关概念视频
Drug Accumulation During Multiple Dosing: Repetitive IV Injections
532
Calculating drug dosage and accumulation in multiple-dose regimens is crucial for achieving therapeutic efficacy while avoiding toxicity. This involves determining the plasma drug concentrations over time to optimize dosing schedules. The principle of superposition is fundamental in this process, allowing for the prediction of drug concentration in plasma following multiple doses based on single-dose data.The principle of superposition asserts that the plasma concentration-time curves from...
532
Steps in Outbreak Investigation
780
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
780
