Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality: A retrospective study
Aim of the study: The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting sh...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2020-12-01
|
Series: | Resuscitation Plus |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666520420300461 |
id |
doaj-629368b162684190955e9f9478bece7f |
---|---|
record_format |
Article |
spelling |
doaj-629368b162684190955e9f9478bece7f2021-03-19T07:30:40ZengElsevierResuscitation Plus2666-52042020-12-014100046Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality: A retrospective studyJussi Pirneskoski0Joonas Tamminen1Antti Kallonen2Jouni Nurmi3Markku Kuisma4Klaus T. Olkkola5Sanna Hoppu6Department of Emergency Medicine and Services, University of Helsinki and HUS Helsinki University Hospital, Helsinki, Finland; Corresponding author at: Department of Emergency Medicine and Services, University of Helsinki and HUS Helsinki University Hospital, PO Box 340, 00029 HUS, Helsinki, Finland.Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland; Emergency Medical Services, Tampere University Hospital, Tampere, FinlandFaculty of Medicine and Health Technology, Tampere University, Tampere, FinlandDepartment of Emergency Medicine and Services, University of Helsinki and HUS Helsinki University Hospital, Helsinki, FinlandDepartment of Emergency Medicine and Services, University of Helsinki and HUS Helsinki University Hospital, Helsinki, FinlandDepartment of Anaesthesiology, Intensive Care and Pain Medicine, University of Helsinki and HUS Helsinki University Hospital, Helsinki, FinlandEmergency Medical Services, Tampere University Hospital, Tampere, FinlandAim of the study: The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting short-term mortality. Thus, we aimed to compare the mortality prediction accuracy of NEWS and random forest machine learning using prehospital vital signs. Methods: In this retrospective study, all electronic ambulance mission reports between 2008 and 2015 in a single EMS system were collected. Adult patients (≥ 18 years) were included in the analysis. Random forest models with and without blood glucose were compared to the traditional NEWS for predicting one-day mortality. A ten-fold cross-validation method was applied to train and validate the random forest models. Results: A total of 26,458 patients were included in the study of whom 278 (1.0%) died within one day of ambulance mission. The area under the receiver operating characteristic curve for one-day mortality was 0.836 (95% CI, 0.810−0.860) for NEWS, 0.858 (95% CI, 0.832−0.883) for a random forest trained with NEWS variables only and 0.868 (0.843−0.892) for a random forest trained with NEWS variables and blood glucose. Conclusion: A random forest algorithm trained with NEWS variables was superior to traditional NEWS for predicting one-day mortality in adult prehospital patients, although the risk of selection bias must be acknowledged. The inclusion of blood glucose in the model further improved its predictive performance.http://www.sciencedirect.com/science/article/pii/S2666520420300461Emergency medical servicesPrehospitalCardiac arrest preventionEarly warning scoreNational Early Warning ScoreNEWS |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jussi Pirneskoski Joonas Tamminen Antti Kallonen Jouni Nurmi Markku Kuisma Klaus T. Olkkola Sanna Hoppu |
spellingShingle |
Jussi Pirneskoski Joonas Tamminen Antti Kallonen Jouni Nurmi Markku Kuisma Klaus T. Olkkola Sanna Hoppu Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality: A retrospective study Resuscitation Plus Emergency medical services Prehospital Cardiac arrest prevention Early warning score National Early Warning Score NEWS |
author_facet |
Jussi Pirneskoski Joonas Tamminen Antti Kallonen Jouni Nurmi Markku Kuisma Klaus T. Olkkola Sanna Hoppu |
author_sort |
Jussi Pirneskoski |
title |
Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality: A retrospective study |
title_short |
Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality: A retrospective study |
title_full |
Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality: A retrospective study |
title_fullStr |
Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality: A retrospective study |
title_full_unstemmed |
Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality: A retrospective study |
title_sort |
random forest machine learning method outperforms prehospital national early warning score for predicting one-day mortality: a retrospective study |
publisher |
Elsevier |
series |
Resuscitation Plus |
issn |
2666-5204 |
publishDate |
2020-12-01 |
description |
Aim of the study: The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting short-term mortality. Thus, we aimed to compare the mortality prediction accuracy of NEWS and random forest machine learning using prehospital vital signs. Methods: In this retrospective study, all electronic ambulance mission reports between 2008 and 2015 in a single EMS system were collected. Adult patients (≥ 18 years) were included in the analysis. Random forest models with and without blood glucose were compared to the traditional NEWS for predicting one-day mortality. A ten-fold cross-validation method was applied to train and validate the random forest models. Results: A total of 26,458 patients were included in the study of whom 278 (1.0%) died within one day of ambulance mission. The area under the receiver operating characteristic curve for one-day mortality was 0.836 (95% CI, 0.810−0.860) for NEWS, 0.858 (95% CI, 0.832−0.883) for a random forest trained with NEWS variables only and 0.868 (0.843−0.892) for a random forest trained with NEWS variables and blood glucose. Conclusion: A random forest algorithm trained with NEWS variables was superior to traditional NEWS for predicting one-day mortality in adult prehospital patients, although the risk of selection bias must be acknowledged. The inclusion of blood glucose in the model further improved its predictive performance. |
topic |
Emergency medical services Prehospital Cardiac arrest prevention Early warning score National Early Warning Score NEWS |
url |
http://www.sciencedirect.com/science/article/pii/S2666520420300461 |
work_keys_str_mv |
AT jussipirneskoski randomforestmachinelearningmethodoutperformsprehospitalnationalearlywarningscoreforpredictingonedaymortalityaretrospectivestudy AT joonastamminen randomforestmachinelearningmethodoutperformsprehospitalnationalearlywarningscoreforpredictingonedaymortalityaretrospectivestudy AT anttikallonen randomforestmachinelearningmethodoutperformsprehospitalnationalearlywarningscoreforpredictingonedaymortalityaretrospectivestudy AT jouninurmi randomforestmachinelearningmethodoutperformsprehospitalnationalearlywarningscoreforpredictingonedaymortalityaretrospectivestudy AT markkukuisma randomforestmachinelearningmethodoutperformsprehospitalnationalearlywarningscoreforpredictingonedaymortalityaretrospectivestudy AT klaustolkkola randomforestmachinelearningmethodoutperformsprehospitalnationalearlywarningscoreforpredictingonedaymortalityaretrospectivestudy AT sannahoppu randomforestmachinelearningmethodoutperformsprehospitalnationalearlywarningscoreforpredictingonedaymortalityaretrospectivestudy |
_version_ |
1724213196942737408 |