基于现实研究的血液感染风险早期预测模型的开发和应用
Xiefei Hu1, Shenshen Zhi1, Yang Li2
1Department of Clinical Laboratory, Chongqing Emergency Medical Center, School of Medicine, Chongqing University Central Hospital, Chongqing University, Chongqing, China.
BMC medical informatics and decision making
|May 14, 2025
概括
这项研究开发了一种使用常规实验室数据的AI模型,以早期预测血流感染 (BSI). 该XGBoost模型准确地识别BSI风险,帮助更快的诊断和降低死亡率.
科学领域:
- 医疗信息学 医疗信息学
- 传染性疾病 传染性疾病
- 人工智能在医学中的应用
背景情况:
- 血流感染 (BSI) 是一种严重的疾病,死亡率高,需要早期诊断.
- 目前用于BSI的诊断方法在特异性和速度方面存在局限性.
- 人工智能 (AI) 为早期疾病识别提供了一个有希望的方法.
研究的目的:
- 开发一个早期,快速和普遍适用的BSI风险预测模型.
- 确定用于BSI预测的常规实验室和临床监测指标的最佳组合.
- 帮助临床医生在早期诊断BSI使用机器学习.
主要方法:
- 利用了2582名疑似BSI患者的临床数据.
- 采用了特征选择技术,包括单变量逻辑回归,Boruta,Lasso和RFE-CV.
- 使用六种机器学习算法构建和评估BSI风险预测模型,包括XGBoost.
- 通过使用外部数据集和SHAP来验证最佳模型的可解释性.
主要成果:
- 确定了一组5个关键预测因素:白细胞计数,标准二碳酸盐,基过量,介质素-6和体温.
- 在XGBoost模型中,AUC值为0.782 (内部验证) 和0.776 (外部验证).
- 基于XGBoost模型的在线工具可供临床使用.
结论:
- 一个5个特征的机器学习模型使得BSI患者的早期和快速差异化成为可能.
- 该模型的最小预测器集增强了临床适用性,特别是在初级保健中.
- 在线工具应用程序可以提高BSI诊断效率并降低患者死亡率.
相关概念视频
01:18Steps in Outbreak Investigation
99
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:
99
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
106
Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
106