Literature DB >> 34511920

Optimized Machine Learning Models to Predict In-Hospital Mortality for Patients with ST-Segment Elevation Myocardial Infarction.

Jia Zhao1,2, Pengyu Zhao3, Chunjie Li2, Yonghong Hou3.   

Abstract

PURPOSE: This study aimed to optimize machine learning (ML) models for predicting in-hospital mortality in patients with ST-segment elevation acute myocardial infarction (STEMI). PATIENTS AND METHODS: A total of 5708 STEMI patients were enrolled and divided into two groups according to patients' hospital outcomes. Both groups were randomly split into a training set (75%) and a testing set (25%). Four ML models were trained with data, which applied random under-sampling (RUS). The performance of optimized ML models was evaluated with respect to accuracy, sensitivity, specificity, G-mean and AUC. Two sets of features in chronological order were considered: a full set that included all variables during hospitalization and a simplified set that only included variables prior to reperfusion therapy, and the performance of the prediction models trained with these two sets of features was compared.
RESULTS: For the comprehensive metric - G-mean, the models trained with RUS outperformed those without, 80.54% vs 23.31% on average in the full set and 75.72% vs 35.76% on average in the simplified set. For models trained with the full set, the SVM achieved the best performance with 85.62% accuracy, 84.21% sensitivity, 85.66% specificity, 84.93% G-mean and 0.919 AUC. For models trained with the simplified set, the SVM achieved 83.48% G-mean, which was comparable to the models trained using the full set. For the most critical metric - sensitivity, the SVM trained using the simplified set achieved 89.47%, which even exceed the SVM (84.21%), DT (81.58%) and RF (81.58%) trained using the full set.
CONCLUSION: Applying RUS can improve the performance of prediction models, and the models trained with simplified set, which only included variables prior to reperfusion therapy can accurately predict high-risk patients.
© 2021 Zhao et al.

Entities:  

Keywords:  STEMI; in-hospital mortality; optimized machine learning algorithm; prediction model; random under-sampling

Year:  2021        PMID: 34511920      PMCID: PMC8427294          DOI: 10.2147/TCRM.S321799

Source DB:  PubMed          Journal:  Ther Clin Risk Manag        ISSN: 1176-6336            Impact factor:   2.423


  20 in total

Review 1.  Applications of Support Vector Machine (SVM) Learning in Cancer Genomics.

Authors:  Shujun Huang; Nianguang Cai; Pedro Penzuti Pacheco; Shavira Narrandes; Yang Wang; Wayne Xu
Journal:  Cancer Genomics Proteomics       Date:  2018 Jan-Feb       Impact factor: 4.069

2.  Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network.

Authors:  Christopher M Haggerty; Brandon K Fornwalt; Sushravya Raghunath; Alvaro E Ulloa Cerna; Linyuan Jing; David P vanMaanen; Joshua Stough; Dustin N Hartzel; Joseph B Leader; H Lester Kirchner; Martin C Stumpe; Ashraf Hafez; Arun Nemani; Tanner Carbonati; Kipp W Johnson; Katelyn Young; Christopher W Good; John M Pfeifer; Aalpen A Patel; Brian P Delisle; Amro Alsaid; Dominik Beer
Journal:  Nat Med       Date:  2020-05-11       Impact factor: 53.440

3.  TIMI risk score for ST-elevation myocardial infarction: A convenient, bedside, clinical score for risk assessment at presentation: An intravenous nPA for treatment of infarcting myocardium early II trial substudy.

Authors:  D A Morrow; E M Antman; A Charlesworth; R Cairns; S A Murphy; J A de Lemos; R P Giugliano; C H McCabe; E Braunwald
Journal:  Circulation       Date:  2000-10-24       Impact factor: 29.690

Review 4.  Artificial intelligence in cardiology.

Authors:  Dipti Itchhaporia
Journal:  Trends Cardiovasc Med       Date:  2020-11-23       Impact factor: 6.677

5.  Coronary Catheterization and Percutaneous Coronary Intervention in China: 10-Year Results From the China PEACE-Retrospective CathPCI Study.

Authors:  Xin Zheng; Jeptha P Curtis; Shuang Hu; Yongfei Wang; Yuejin Yang; Frederick A Masoudi; John A Spertus; Xi Li; Jing Li; Kumar Dharmarajan; Nicholas S Downing; Harlan M Krumholz; Lixin Jiang
Journal:  JAMA Intern Med       Date:  2016-04       Impact factor: 21.873

6.  Whole blood transcriptome profile at hospital admission discriminates between patients with ST-segment elevation and non-ST-segment elevation acute myocardial infarction.

Authors:  Mattia Chiesa; Luca Piacentini; Elisa Bono; Valentina Milazzo; Jeness Campodonico; Giancarlo Marenzi; Gualtiero I Colombo
Journal:  Sci Rep       Date:  2020-05-26       Impact factor: 4.379

7.  Machine Learning to Predict the 1-Year Mortality Rate After Acute Anterior Myocardial Infarction in Chinese Patients.

Authors:  Yi-Ming Li; Li-Cheng Jiang; Jing-Jing He; Kai-Yu Jia; Yong Peng; Mao Chen
Journal:  Ther Clin Risk Manag       Date:  2020-01-09       Impact factor: 2.423

8.  High-sensitivity troponin I concentrations are a marker of an advanced hypertrophic response and adverse outcomes in patients with aortic stenosis.

Authors:  Calvin W L Chin; Anoop S V Shah; David A McAllister; S Joanna Cowell; Shirjel Alam; Jeremy P Langrish; Fiona E Strachan; Amanda L Hunter; Anna Maria Choy; Chim C Lang; Simon Walker; Nicholas A Boon; David E Newby; Nicholas L Mills; Marc R Dweck
Journal:  Eur Heart J       Date:  2014-05-14       Impact factor: 29.983

9.  Deep-learning-based risk stratification for mortality of patients with acute myocardial infarction.

Authors:  Joon-Myoung Kwon; Ki-Hyun Jeon; Hyue Mee Kim; Min Jeong Kim; Sungmin Lim; Kyung-Hee Kim; Pil Sang Song; Jinsik Park; Rak Kyeong Choi; Byung-Hee Oh
Journal:  PLoS One       Date:  2019-10-31       Impact factor: 3.240

10.  Machine learning-based prediction of acute coronary syndrome using only the pre-hospital 12-lead electrocardiogram.

Authors:  Salah Al-Zaiti; Lucas Besomi; Zeineb Bouzid; Ziad Faramand; Stephanie Frisch; Christian Martin-Gill; Richard Gregg; Samir Saba; Clifton Callaway; Ervin Sejdić
Journal:  Nat Commun       Date:  2020-08-07       Impact factor: 14.919

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.