见树又见林：机器学习预测烧伤患者的生存情况。
Seeing the forest beyond the trees: Predicting survival in burn patients with machine learning.
机构信息
Loyola University Medical Center, Department of Surgery, 2160 S. 1st Avenue, Maywood, IL 60153, USA; One:MAP Section of Surgical Analytics, Department of Surgery, Loyola University Chicago, 2160 S. 1st Avenue, Maywood, IL 60153, USA.
DePaul University, College of Computing and Digital Media, Department of Predictive Analytics, 243 South Wabash Avenue, Chicago, IL 60604, USA.
出版信息
Am J Surg. 2018 Mar;215(3):411-416. doi: 10.1016/j.amjsurg.2017.10.027. Epub 2017 Nov 7.
BACKGROUND
This study aims to identify predictors of survival for burn patients at the patient and hospital level using machine learning techniques.
METHODS
The HCUP SID for California, Florida and New York were used to identify patients admitted with a burn diagnosis and merged with hospital data from the AHA Annual Survey. Random forest and stochastic gradient boosting (SGB) were used to identify predictors of survival at the patient and hospital level from the top performing model.
RESULTS
We analyzed 31,350 patients from 670 hospitals. SGB (AUC 0.93) and random forest (AUC 0.82) best identified patient factors such as age and absence of renal failure (p < 0.001) and hospital factors such as full time residents (p < 0.001) and nurses (p = 0.004) to be associated with increased survival.
CONCLUSIONS
Patient and hospital factors are predictive of survival in burn patients. It is difficult to control patient factors, but hospital factors can inform decisions about where burn patients should be treated.
背景
本研究旨在利用机器学习技术，从患者和医院层面确定烧伤患者的生存预测因素。
方法
使用 HCUP SID（加利福尼亚州、佛罗里达州和纽约州）识别诊断为烧伤的住院患者，并与 AHA 年度调查中的医院数据合并。随机森林和随机梯度提升（SGB）用于从表现最佳的模型中确定患者和医院层面的生存预测因素。
结果
我们分析了来自 670 家医院的 31350 名患者。SGB（AUC 0.93）和随机森林（AUC 0.82）最佳识别了患者因素，如年龄和无肾衰竭（p<0.001），以及医院因素，如全职住院医师（p<0.001）和护士（p=0.004）与生存率增加相关。
结论
患者和医院因素可预测烧伤患者的生存情况。控制患者因素较为困难，但医院因素可以为烧伤患者应在何处接受治疗提供决策依据。
Zotero 插件