构建计算模型以预测急性心肌梗死及心肌梗死后综合征的重症监护病房患者的一年死亡率。
Building Computational Models to Predict One-Year Mortality in ICU Patients with Acute Myocardial Infarction and Post Myocardial Infarction Syndrome.
作者信息
Barrett Laura A, Payrovnaziri Seyedeh Neelufar, Bian Jiang, He Zhe
机构信息
School of Information, Florida State University, Tallahassee, Florida, USA.
Department of Health Outcomes and Biomedical Informatics, University of Florida, Gainesville, Florida, USA.
出版信息
AMIA Jt Summits Transl Sci Proc. 2019 May 6;2019:407-416. eCollection 2019.
Abstract
Heart disease remains the leading cause of death in the United States. Compared with risk assessment guidelines that require manual calculation of scores, machine learning-based prediction for disease outcomes such as mortality can be utilized to save time and improve prediction accuracy. This study built and evaluated various machine learning models to predict one-year mortality in patients diagnosed with acute myocardial infarction or post myocardial infarction syndrome in the MIMIC-III database. The results of the best performing shallow prediction models were compared to a deep feedforward neural network (Deep FNN) with back propagation. We included a cohort of 5436 admissions. Six datasets were developed and compared. The models applying Logistic Model Trees (LMT) and Simple Logistic algorithms to the combined dataset resulted in the highest prediction accuracy at 85.12% and the highest AUC at .901. In addition, other factors were observed to have an impact on outcomes as well.
摘要
心脏病仍然是美国的主要死因。与需要手动计算分数的风险评估指南相比，基于机器学习的疾病预后预测（如死亡率预测）可用于节省时间并提高预测准确性。本研究构建并评估了各种机器学习模型，以预测MIMIC-III数据库中诊断为急性心肌梗死或心肌梗死后综合征患者的一年死亡率。将表现最佳的浅层预测模型的结果与具有反向传播的深度前馈神经网络（Deep FNN）进行了比较。我们纳入了5436例入院病例。开发并比较了六个数据集。将逻辑模型树（LMT）和简单逻辑算法应用于合并数据集的模型，预测准确率最高，为85.12%，AUC最高，为0.901。此外，还观察到其他因素也会对预后产生影响。
相似文献
1
Building Computational Models to Predict One-Year Mortality in ICU Patients with Acute Myocardial Infarction and Post Myocardial Infarction Syndrome.构建计算模型以预测急性心肌梗死及心肌梗死后综合征的重症监护病房患者的一年死亡率。
AMIA Jt Summits Transl Sci Proc. 2019 May 6;2019:407-416. eCollection 2019.
2
Enhancing Prediction Models for One-Year Mortality in Patients with Acute Myocardial Infarction and Post Myocardial Infarction Syndrome.增强急性心肌梗死和心肌梗死后综合征患者一年死亡率的预测模型
Stud Health Technol Inform. 2019 Aug 21;264:273-277. doi: 10.3233/SHTI190226.
3
Interpretable machine learning for 28-day all-cause in-hospital mortality prediction in critically ill patients with heart failure combined with hypertension: A retrospective cohort study based on medical information mart for intensive care database-IV and eICU databases.用于预测心力衰竭合并高血压重症患者28天全因院内死亡率的可解释机器学习：一项基于重症监护医学信息集市数据库-IV和电子重症监护病房数据库的回顾性队列研究
Front Cardiovasc Med. 2022 Oct 12;9:994359. doi: 10.3389/fcvm.2022.994359. eCollection 2022.
4
Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): a modelling study of pooled datasets.基于机器学习的急性冠状动脉综合征后不良事件预测（PRAISE）：汇总数据集的建模研究。
Lancet. 2021 Jan 16;397(10270):199-207. doi: 10.1016/S0140-6736(20)32519-8.
5
Support vector machine deep mining of electronic medical records to predict the prognosis of severe acute myocardial infarction.支持向量机对电子病历进行深度挖掘以预测急性ST段抬高型心肌梗死的预后
Front Physiol. 2022 Sep 29;13:991990. doi: 10.3389/fphys.2022.991990. eCollection 2022.
6
Development and validation of an artificial neural network algorithm to predict mortality and admission to hospital for heart failure after myocardial infarction: a nationwide population-based study.开发和验证一种用于预测心肌梗死后心力衰竭患者死亡率和住院的人工神经网络算法：一项全国范围内基于人群的研究。
Lancet Digit Health. 2022 Jan;4(1):e37-e45. doi: 10.1016/S2589-7500(21)00228-4.
7
Clinical Feature-Based Machine Learning Model for 1-Year Mortality Risk Prediction of ST-Segment Elevation Myocardial Infarction in Patients with Hyperuricemia: A Retrospective Study.基于临床特征的机器学习模型对伴有高尿酸血症的 ST 段抬高型心肌梗死患者 1 年死亡风险的预测：一项回顾性研究。
Comput Math Methods Med. 2021 Jul 5;2021:7252280. doi: 10.1155/2021/7252280. eCollection 2021.
8
Predicting 30-day mortality after ST elevation myocardial infarction: Machine learning- based random forest and its external validation using two independent nationwide datasets.预测 ST 段抬高型心肌梗死 30 天后的死亡率：基于机器学习的随机森林及其使用两个独立的全国性数据集进行的外部验证。
J Cardiol. 2021 Nov;78(5):439-446. doi: 10.1016/j.jjcc.2021.06.002. Epub 2021 Jun 19.
9
Use of Machine Learning Models to Predict Death After Acute Myocardial Infarction.利用机器学习模型预测急性心肌梗死后的死亡。
JAMA Cardiol. 2021 Jun 1;6(6):633-641. doi: 10.1001/jamacardio.2021.0122.
10
In-hospital mortality risk stratification of Asian ACS patients with artificial intelligence algorithm.基于人工智能算法的亚洲 ACS 患者院内死亡风险分层。
PLoS One. 2022 Dec 12;17(12):e0278944. doi: 10.1371/journal.pone.0278944. eCollection 2022.
引用本文的文献
1
Explainable machine learning for predicting ICU mortality in myocardial infarction patients using pseudo-dynamic data.利用伪动态数据进行可解释的机器学习以预测心肌梗死患者的重症监护病房死亡率
Sci Rep. 2025 Jul 31;15(1):27887. doi: 10.1038/s41598-025-13299-3.
2
Machine learning prediction of mortality in Acute Myocardial Infarction.机器学习预测急性心肌梗死患者的死亡率。
BMC Med Inform Decis Mak. 2023 Apr 18;23(1):70. doi: 10.1186/s12911-023-02168-6.
3
Novel architecture for gated recurrent unit autoencoder trained on time series from electronic health records enables detection of ICU patient subgroups.基于电子健康记录时间序列训练的门控循环单元自动编码器的新型架构可用于检测 ICU 患者亚组。
Sci Rep. 2023 Mar 11;13(1):4053. doi: 10.1038/s41598-023-30986-1.
4
Prediction of All-Cause Mortality Based on Stress/Rest Myocardial Perfusion Imaging (MPI) Using Deep Learning: A Comparison between Image and Frequency Spectra as Input.基于深度学习的应力/静息心肌灌注成像（MPI）预测全因死亡率：图像与频谱作为输入的比较
J Pers Med. 2022 Jul 5;12(7):1105. doi: 10.3390/jpm12071105.
5
Intraoperative Hypotension Prediction Model Based on Systematic Feature Engineering and Machine Learning.基于系统特征工程和机器学习的术中低血压预测模型。
Sensors (Basel). 2022 Apr 19;22(9):3108. doi: 10.3390/s22093108.
6
Machine learning approaches to predict the 1-year-after-initial-AMI survival of elderly patients.机器学习方法预测老年首发心肌梗死患者 1 年后的生存情况。
BMC Med Inform Decis Mak. 2022 Apr 29;22(1):115. doi: 10.1186/s12911-022-01854-1.
7
Application of machine learning to predict the occurrence of arrhythmia after acute myocardial infarction.机器学习在预测急性心肌梗死后心律失常发生中的应用。
BMC Med Inform Decis Mak. 2021 Nov 2;21(1):301. doi: 10.1186/s12911-021-01667-8.
8
Machine learning enhances the performance of short and long-term mortality prediction model in non-ST-segment elevation myocardial infarction.机器学习提高非 ST 段抬高型心肌梗死患者短期和长期死亡率预测模型的性能。
Sci Rep. 2021 Jun 18;11(1):12886. doi: 10.1038/s41598-021-92362-1.
9
Application of Machine Learning in Intensive Care Unit (ICU) Settings Using MIMIC Dataset: Systematic Review.使用MIMIC数据集的机器学习在重症监护病房（ICU）环境中的应用：系统评价。
Informatics (MDPI). 2021 Mar;8(1). doi: 10.3390/informatics8010016. Epub 2021 Mar 3.
10
Establishment of a prognostic model based on the Sequential Organ Failure Assessment score for patients with first-time acute myocardial infarction.基于序贯器官衰竭评估评分建立首次急性心肌梗死患者的预后模型。
J Int Med Res. 2021 May;49(5):3000605211011976. doi: 10.1177/03000605211011976.
本文引用的文献
1
Scalable and accurate deep learning with electronic health records.借助电子健康记录实现可扩展且准确的深度学习。
NPJ Digit Med. 2018 May 8;1:18. doi: 10.1038/s41746-018-0029-1. eCollection 2018.
2
Predicting Mortality in Diabetic ICU Patients Using Machine Learning and Severity Indices.使用机器学习和严重程度指数预测糖尿病重症监护病房患者的死亡率
AMIA Jt Summits Transl Sci Proc. 2018 May 18;2017:310-319. eCollection 2018.
3
Artificial Intelligence in Cardiology.人工智能在心脏病学中的应用。
J Am Coll Cardiol. 2018 Jun 12;71(23):2668-2679. doi: 10.1016/j.jacc.2018.03.521.
4
Predicting Intensive Care Unit Readmission with Machine Learning Using Electronic Health Record Data.使用电子健康记录数据进行机器学习预测重症监护病房再入院。
Ann Am Thorac Soc. 2018 Jul;15(7):846-853. doi: 10.1513/AnnalsATS.201710-787OC.
5
Heart Disease and Stroke Statistics-2018 Update: A Report From the American Heart Association.《2018年心脏病和中风统计数据更新：美国心脏协会报告》
Circulation. 2018 Mar 20;137(12):e67-e492. doi: 10.1161/CIR.0000000000000558. Epub 2018 Jan 31.
6
Development and Validation of Machine Learning Models for Prediction of 1-Year Mortality Utilizing Electronic Medical Record Data Available at the End of Hospitalization in Multicondition Patients: a Proof-of-Concept Study.利用多病种患者住院结束时可获取的电子病历数据开发和验证机器学习模型预测 1 年死亡率：概念验证研究。
J Gen Intern Med. 2018 Jun;33(6):921-928. doi: 10.1007/s11606-018-4316-y. Epub 2018 Jan 30.
7
Machine learning in cardiovascular medicine: are we there yet?机器学习在心血管医学中的应用：我们是否已经实现？
Heart. 2018 Jul;104(14):1156-1164. doi: 10.1136/heartjnl-2017-311198. Epub 2018 Jan 19.
8
Risk prediction model for in-hospital mortality in women with ST-elevation myocardial infarction: A machine learning approach.ST段抬高型心肌梗死女性患者院内死亡风险预测模型：一种机器学习方法。
Heart Lung. 2017 Nov-Dec;46(6):405-411. doi: 10.1016/j.hrtlng.2017.09.003. Epub 2017 Oct 6.
9
Predicting two-year survival versus non-survival after first myocardial infarction using machine learning and Swedish national register data.利用机器学习和瑞典国家登记数据预测首次心肌梗死后的两年生存率与非生存率。
BMC Med Inform Decis Mak. 2017 Jul 5;17(1):99. doi: 10.1186/s12911-017-0500-y.
10
Development of a novel score for the prediction of hospital mortality in patients with severe sepsis: the use of electronic healthcare records with LASSO regression.开发一种预测严重脓毒症患者医院死亡率的新评分：利用电子健康记录结合套索回归分析
Oncotarget. 2017 Jul 25;8(30):49637-49645. doi: 10.18632/oncotarget.17870.
Zotero 插件