使用可解释的人工智能对临床数据进行尿管相关尿路感染的个体风险估计
Herdiantri Sufriyana1, Chieh Chen2, Hua-Sheng Chiu3
1Institute of Biomedical Informatics, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan; Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.
一种新的预测模型准确地识别了患有管相关尿路感染 (CAUTIs) 高风险的患者,有助于临床决策. 这种工具有助于排除低风险个体,减少不必要的干预.
科学领域:
- 医疗信息学 医疗信息学
- 临床预测建模临床预测建模
- 医疗保健相关的感染
背景情况:
- 导管相关的尿路感染 (CAUTIs) 代表了相当大的临床负担.
- 准确识别高风险患者对于有效的CAUTI预防和管理至关重要.
- 现有的CAUTI风险分层方法可能缺乏可解释性和外部验证.
研究的目的:
- 开发和外部验证可解释的CAUTIs的预后预测模型.
- 为了确定患有CAUTIs高风险的住院患者,在尿道导管治疗期间.
- 为临床医生提供可靠的CAUTI风险评估工具.
主要方法:
- 追溯队列研究设计,利用三家医院的数据进行开发和外部验证.
- 机器学习算法的应用,包括随机森林,用于预测建模.
- 严格评估模型校准,临床效用和歧视,然后进行可解释性评估.
主要成果:
- 一个随机的森林模型被选为最好的预测CAUTIs在6天内.
- 该模型的准确性很高,检测出97.63%的CAUTI阳性病例,并正确识别出97.36%的真阴性病例.
- 开发了一个基于网络的应用程序和基于纸张的nomogram,以促进模型的实施.
结论:
- 开发的预测模型准确地识别了大多数CAUTI阳性病例.
- 该模型有效排除了CAUTI风险较低的个体,支持临床决策.
- 该模型的可解释性增强了其临床实用性和可信度.
更多相关视频
07:34Isolation of Single Intracellular Bacterial Communities Generated from a Murine Model of Urinary Tract Infection for Downstream Single-cell Analysis
Published on: April 16, 2019
10:23Urinary Tract Infection in a Small Animal Model: Transurethral Catheterization of Male and Female Mice
Published on: December 1, 2017
相关概念视频
Healthcare Associated Infections II: Preventive Measures
The best practices for preventing healthcare-associated infections include hand hygiene, patient risk...
Healthcare Associated Infections I: Iatrogenic, Exogenic and Endogenic
HAIs significantly increase the cost of health care. Extended stays in healthcare institutions, increased disability, increased costs of medications, including specialized antibiotics, and prolonged recovery times add to the patient's expenses and the healthcare institution and funding bodies.
Steps in Outbreak Investigation
Receiver Operating Characteristic Plot
The Availability Heuristic
