Literature DB >> 33422146

Machine learning-based prediction models for accidental hypothermia patients.

Yohei Okada1,2,3, Tasuku Matsuyama4, Sachiko Morita5, Naoki Ehara6, Nobuhiro Miyamae7, Takaaki Jo8, Yasuyuki Sumida9, Nobunaga Okada4,10, Makoto Watanabe4, Masahiro Nozawa11, Ayumu Tsuruoka12, Yoshihiro Fujimoto13, Yoshiki Okumura14, Tetsuhisa Kitamura15, Ryoji Iiduka16, Shigeru Ohtsuru17.   

Abstract

BACKGROUND: Accidental hypothermia is a critical condition with high risks of fatal arrhythmia, multiple organ failure, and mortality; however, there is no established model to predict the mortality. The present study aimed to develop and validate machine learning-based models for predicting in-hospital mortality using easily available data at hospital admission among the patients with accidental hypothermia.
METHOD: This study was secondary analysis of multi-center retrospective cohort study (J-point registry) including patients with accidental hypothermia. Adult patients with body temperature 35.0 °C or less at emergency department were included. Prediction models for in-hospital mortality using machine learning (lasso, random forest, and gradient boosting tree) were made in development cohort from six hospitals, and the predictive performance were assessed in validation cohort from other six hospitals. As a reference, we compared the SOFA score and 5A score.
RESULTS: We included total 532 patients in the development cohort [N = 288, six hospitals, in-hospital mortality: 22.0% (64/288)], and the validation cohort [N = 244, six hospitals, in-hospital mortality 27.0% (66/244)]. The C-statistics [95% CI] of the models in validation cohorts were as follows: lasso 0.784 [0.717-0.851] , random forest 0.794[0.735-0.853], gradient boosting tree 0.780 [0.714-0.847], SOFA 0.787 [0.722-0.851], and 5A score 0.750[0.681-0.820]. The calibration plot showed that these models were well calibrated to observed in-hospital mortality. Decision curve analysis indicated that these models obtained clinical net-benefit.
CONCLUSION: This multi-center retrospective cohort study indicated that machine learning-based prediction models could accurately predict in-hospital mortality in validation cohort among the accidental hypothermia patients. These models might be able to support physicians and patient's decision-making. However, the applicability to clinical settings, and the actual clinical utility is still unclear; thus, further prospective study is warranted to evaluate the clinical usefulness.

Entities:  

Keywords:  Accidental hypothermia; Artificial intelligence; Gradient boosting tree; Lasso; Machine learning; Prediction; Random forest

Year:  2021        PMID: 33422146     DOI: 10.1186/s40560-021-00525-z

Source DB:  PubMed          Journal:  J Intensive Care        ISSN: 2052-0492


  32 in total

Review 1.  Accidental hypothermia.

Authors:  Douglas J A Brown; Hermann Brugger; Jeff Boyd; Peter Paal
Journal:  N Engl J Med       Date:  2012-11-15       Impact factor: 91.245

2.  Severe accidental hypothermia treated in an ICU: prognosis and outcome.

Authors:  T Vassal; B Benoit-Gonin; F Carrat; B Guidet; E Maury; G Offenstadt
Journal:  Chest       Date:  2001-12       Impact factor: 9.410

3.  Prediction of 30-Day All-Cause Readmissions in Patients Hospitalized for Heart Failure: Comparison of Machine Learning and Other Statistical Approaches.

Authors:  Jarrod D Frizzell; Li Liang; Phillip J Schulte; Clyde W Yancy; Paul A Heidenreich; Adrian F Hernandez; Deepak L Bhatt; Gregg C Fonarow; Warren K Laskey
Journal:  JAMA Cardiol       Date:  2017-02-01       Impact factor: 14.676

4.  Development and Validation of a Clinical Risk Score to Predict the Occurrence of Critical Illness in Hospitalized Patients With COVID-19.

Authors:  Wenhua Liang; Hengrui Liang; Limin Ou; Binfeng Chen; Ailan Chen; Caichen Li; Yimin Li; Weijie Guan; Ling Sang; Jiatao Lu; Yuanda Xu; Guoqiang Chen; Haiyan Guo; Jun Guo; Zisheng Chen; Yi Zhao; Shiyue Li; Nuofu Zhang; Nanshan Zhong; Jianxing He
Journal:  JAMA Intern Med       Date:  2020-08-01       Impact factor: 21.873

5.  Prediction and risk stratification of survival in accidental hypothermia requiring extracorporeal life support: An individual patient data meta-analysis.

Authors:  Richard S Saczkowski; Doug J A Brown; Riyad B Abu-Laban; Guy Fradet; Costas J Schulze; Nick D Kuzak
Journal:  Resuscitation       Date:  2018-03-23       Impact factor: 5.262

Review 6.  Hypothermia outcome prediction after extracorporeal life support for hypothermic cardiac arrest patients: The HOPE score.

Authors:  Mathieu Pasquier; Olivier Hugli; Peter Paal; Tomasz Darocha; Marc Blancher; Paul Husby; Tom Silfvast; Pierre-Nicolas Carron; Valentin Rousson
Journal:  Resuscitation       Date:  2018-03-02       Impact factor: 5.262

7.  The development and validation of a "5A" severity scale for predicting in-hospital mortality after accidental hypothermia from J-point registry data.

Authors:  Yohei Okada; Tasuku Matsuyama; Sachiko Morita; Naoki Ehara; Nobuhiro Miyamae; Takaaki Jo; Yasuyuki Sumida; Nobunaga Okada; Makoto Watanabe; Masahiro Nozawa; Ayumu Tsuruoka; Yoshihiro Fujimoto; Yoshiki Okumura; Tetsuhisa Kitamura; Shungo Yamamoto; Ryoji Iiduka; Kaoru Koike
Journal:  J Intensive Care       Date:  2019-05-03

8.  Derivation of a model to predict mortality in urban patients with accidental hypothermia: a retrospective observational study.

Authors:  Tatsuki Uemura; Akio Kimura; Wataru Matsuda; Ryo Sasaki; Kentaro Kobayashi
Journal:  Acute Med Surg       Date:  2019-12-25

9.  Comparison of Machine Learning Methods With Traditional Models for Use of Administrative Claims With Electronic Medical Records to Predict Heart Failure Outcomes.

Authors:  Rishi J Desai; Shirley V Wang; Muthiah Vaduganathan; Thomas Evers; Sebastian Schneeweiss
Journal:  JAMA Netw Open       Date:  2020-01-03

10.  Machine Learning-Based Prediction of Clinical Outcomes for Children During Emergency Department Triage.

Authors:  Tadahiro Goto; Carlos A Camargo; Mohammad Kamal Faridi; Robert J Freishtat; Kohei Hasegawa
Journal:  JAMA Netw Open       Date:  2019-01-04
View more
  1 in total

1.  External validation of 5A score model for predicting in-hospital mortality among the accidental hypothermia patients: JAAM-Hypothermia study 2018-2019 secondary analysis.

Authors:  Yohei Okada; Tasuku Matsuyama; Kei Hayashida; Shuhei Takauji; Jun Kanda; Shoji Yokobori
Journal:  J Intensive Care       Date:  2022-05-26
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.