Predicting Mortality of Sepsis Patients in a Multi-Site Healthcare System using Supervised Machine Learning

机译：预测使用监督机器学习在多站点医疗保健系统中脓毒症患者的死亡率

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Introduction: Sepsis patients suffer from high rates of mortality, but it is difficult to diagnose and accurately predict who experience death while in-hospital or post-discharge. Methods: We trained and validated a supervised machine learning model to predict all-cause mortality between admission and 90-days after discharge using electronic healthcare record data from 10,593 patients with sepsis diagnosed during hospitalization at Geisinger Health System hospitals between 2006 and 2016. Results: Our model had an A UC of 0.8561, with recall and precision of 0.7732 and 0.6931 respectively. Conclusions: We have developed a predictive modelfor sepsis. This is a move towards providing personalized care for sepsis patients and help prevent death. Future work is needed to further refine this model.

机译：介绍：脓毒症患者患有高死亡率，但很难诊断，准确地预测谁在医院或出院后的死亡。方法：我们培训并验证了监督机床学习模型，以预测在2006年至2016年间景观卫生系统医院住院期间诊断的10,593例败血症患者的10,593名患者的10,593名患者入院后的入学和90天之间的所有因果的死亡率。结果：我们的模型具有0.8561的UC，分别召回和精度为0.7732和0.6931。结论：我们开发了一种预测的Modelfor败血症。这是为败血症患者提供个性化护理的举动，并有助于防止死亡。需要未来的工作来进一步改进此模型。

著录项

来源
《International Conference on Health Informatics and Medical Systems》|2018年|140p|共7页
会议地点
作者
Bogle Brittany; Balduino Ricardo; Wolk Donna M.; Farag Hosam A; Kethireddy Shravan; Chatterjee Avijit; Abedi Vida;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类 G20-53;
关键词
Sepsis; Electronic healthcare records; EHR; Machine learning; Mortality prediction model;

机译：败血症;电子医疗记录;EHR;机器学习;死亡预测模型;

相似文献

外文文献
中文文献
专利

1. Supervised machine learning for early predicting the sepsis patient: modified mean imputation and modified chi-square feature selection [J] . Shrestha Ujjwol, Alsadoon Abeer, Prasad P. W. C., Multimedia Tools and Applications . 2021,第13期

机译：监督机器学习早期预测败血症患者：修改平均归档和改进的Chi-Square特征选择
2. Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost [J] . Nianzong Hou, Mingzhe Li, Lu He, Journal of Translational Medicine . 2020,第1期

机译：预测MIMIC-III患者的30天死亡率术语 - 3：一种使用XGBoost的机器学习方法
3. Early Prediction of Mortality, Severity, and Length of Stay in the Intensive Care Unit of Sepsis Patients Based on Sepsis 3.0 by Machine Learning Models [J] . Longxiang Su, Xiang Zhou, Na Hong, Frontiers in Medicine . 2021,第a期

机译：基于机器学习模型的SEPSIS 3.0，早期预测死亡率，严重程度和败血症重症监护患者重症监护单位
4. Predicting Mortality of Sepsis Patients in a Multi-Site Healthcare System using Supervised Machine Learning [C] . Bogle Brittany, Balduino Ricardo, Wolk Donna M., International Conference on Health Informatics and Medical Systems . 2018

机译：预测使用监督机器学习在多站点医疗保健系统中脓毒症患者的死亡率
5. A Modified Q-Learning Approach for Predicting Mortality in Patients Diagnosed with Sepsis [D] . Dunn, Noah Michael. 2021

机译：一种改进的Q学习方法，用于预测患有败血症患者的死亡率
6. Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost [O] . Nianzong Hou, Mingzhe Li, Lu He, 2020

机译：预测MIMIC-III患者的30天死亡率术语 - 3：一种使用XGBoost的机器学习方法
7. Early Prediction of Mortality, Severity, and Length of Stay in the Intensive Care Unit of Sepsis Patients Based on Sepsis 3.0 by Machine Learning Models [O] . Longxiang Su, Zheng Xu, Fengxiang Chang, 2021

机译：基于机器学习模型的Sepsis 3.0，早期预测死亡率，严重程度和住院时间重症监护患者的重症监护单位
8. Development and Validation of a Machine Learning Algorithm and Hybrid System to Predict the Need for Life-Saving Interventions in Trauma Patients. [R] . Liu, N. T., Holcomb, J. B., Wade, C. E., 2014

机译：机器学习算法和混合系统的开发和验证，以预测创伤患者挽救生命的干预需求。

Predicting Mortality of Sepsis Patients in a Multi-Site Healthcare System using Supervised Machine Learning

摘要

著录项

相似文献

相关主题

期刊订阅