机器学习在医疗急救部门的诊断支持中
Claus Lohman Brasen1,2, Eline Sandvig Andersen3,4, Jeppe Buur Madsen3
1Department of Biochemistry and Immunology, Lillebaelt Hospital, University Hospital of Southern Denmark, Beriderbakken 4, 7100, Vejle, Denmark. claus.lohman.brasen@rsyd.dk.
机器学习算法可以帮助急诊室诊断,改善患者的治疗结果并减少错误. 这项研究证明了它们在预测患者结果和减少血液抽取方面的可行性和有效性.
科学领域:
- 医疗信息学医学信息学
- 医疗保健中的人工智能
- 临床决策支持系统临床决策支持系统
背景情况:
- 急诊室 (ED) 诊断是复杂的,并且越来越受到老龄化人口的挑战.
- 诊断错误和患者物流需要创新的解决方案.
- 机器学习 (ML) 提供了在高压ED环境中协助医生的潜力.
研究的目的:
- 评估训练ML算法的可行性,以支持ED医生.
- 评估这些算法的诊断准确性和预测能力.
- 确定ML辅助诊断对患者结果和资源利用的影响.
主要方法:
- 这是一项针对两个医院9190例ED入院的队列研究.
- 在80%的患者数据 (生化,护士注册数据) 上训练19个ML算法,用于19个结局.
- 对剩余20%的患者数据进行算法的验证.
主要成果:
- 机器学习算法在7天死亡率 (AUC 91.4%) 和30天死亡率 (AUC 91.3%) 等结果中实现了高预测精度.
- 算法在预测安全排放方面表现强 (AUC为87.3%).
- 生物化学分析清单的实施使随后的静脉穿刺减少了22%.
结论:
- 对于ED应用,可以开发具有高曲线下面积 (AUC) 的ML算法.
- 这些算法显示出减少诊断错误和改善患者物流的潜力.
- 该研究成功地证明了通过ML指导分析来减少静脉穿刺的可行性.
更多相关视频
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
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
相关概念视频
Steps in Outbreak Investigation
Documentation of Nursing Diagnosis
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters...
Issues And Trends In Healthcare Delivery System
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Assessment of Airway, Skin Color, and Use of Accessory Muscles
Introduction
The initial evaluation of a patient's respiratory system...
