Machine Learning Approach to Predict In-Hospital Mortality in Patients Admitted for Peripheral Artery Disease in the United States

被引:18
作者
Zhang, Donglan [2 ]
Li, Yike [1 ]
Kalbaugh, Corey Andrew [3 ]
Shi, Lu [3 ]
Divers, Jasmin [2 ]
Islam, Shahidul [2 ]
Annex, Brian H. [4 ,5 ]
机构
[1] Vanderbilt Univ, Med Ctr, Bill Wilkerson Ctr, Dept Otolaryngol Head & Neck Surg, 1161 21st Ave South,S2211 Med Ctr North, Nashville, TN 37232 USA
[2] NYU, Dept Fdn Med, Div Hlth Serv Res, Long Isl Sch Med, Mineola, NY USA
[3] Clemson Univ, Dept Publ Hlth Sci, Clemson, SC USA
[4] Med Coll Georgia, Dept Med, Augusta, GA 30912 USA
[5] Med Coll Georgia, Vasc Biol Ctr, Augusta, GA 30912 USA
来源
JOURNAL OF THE AMERICAN HEART ASSOCIATION | 2022年 / 11卷 / 20期
关键词
big data; diabetes; hospital mortality; machine learning; peripheral artery disease; precision medicine; AMPUTATION; RISK; PREVALENCE; TRENDS; RATES;
D O I
10.1161/JAHA.122.026987
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Background Peripheral artery disease (PAD) affects >10 million people in the United States. PAD is associated with poor outcomes, including premature death. Machine learning (ML) has been increasingly used on big data to predict clinical outcomes. This study aims to develop ML models to predict in-hospital mortality in patients hospitalized for PAD based on a national database. Methods and Results Inpatient hospitalization data were obtained from the 2016 to 2019 National Inpatient Sample. A total of 150 921 inpatients were identified with a primary diagnosis of PAD and PAD-related procedures using codes of the International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) and International Classification of Diseases, Tenth Revision, Procedure Coding System (ICD-10-PCS). Four ML models, including logistic regression, random forest, light gradient boosting, and extreme gradient boosting models, were trained to predict the risk of in-hospital death based on a selection of variables, including patient characteristics, comorbidities, procedures, and hospital-related factors. In-hospital mortality occurred in 1.8% of patients. The performance of the 4 models was comparable, with the area under the receiver operating characteristic curve ranging from 0.83 to 0.85, sensitivity of 77% to 82%, and specificity of 72% to 75%. These results suggest adequate predictability for clinical decision-making. In all 4 models, the total number of diagnoses and procedures, age, endovascular revascularization procedure, congestive heart failure, diabetes, and diabetes with complications were critical predictors of in-hospital mortality. Conclusions This study demonstrates the feasibility of ML in predicting in-hospital mortality in patients with a primary PAD diagnosis. Findings highlight the potential of ML models in identifying high-risk patients for poor outcomes and guiding personalized intervention.
引用
收藏
页数:30
相关论文
共 50 条
[41]   Risk indices that predict in-hospital mortality of elderly patients [J].
Dulger, Dilek ;
Albuz, Ozgur .
TURKISH JOURNAL OF MEDICAL SCIENCES, 2020, 50 (04) :969-977
[42]   Development of Comorbidity Index for in-hospital mortality for patients who underwent coronary artery revascularization [J].
Li, Renxi ;
Huddleston, Stephen .
JOURNAL OF CARDIOVASCULAR SURGERY, 2023, 64 (06) :678-685
[43]   Trends in surgical volume and in-hospital mortality among United States cirrhosis hospitalizations [J].
Tessiatore, Kristen M. ;
Mahmud, Nadim .
ANNALS OF GASTROENTEROLOGY, 2021, 34 (01) :85-+
[44]   Supervised machine learning including environmental factors to predict in-hospital outcomes in acute heart failure patients [J].
Sibilia, Benjamin ;
Toupin, Solenn ;
Bouali, Nabil ;
Brette, Jean-Baptiste ;
Ramonatxo, Arthur ;
Schurtz, Guillaume ;
Hamzi, Kenza ;
Trimaille, Antonin ;
Gall, Emmanuel ;
Piliero, Nicolas ;
Unger, Alexandre ;
Andrieu, Stephane ;
Goncalves, Trecy ;
Picard, Fabien ;
Roule, Vincent ;
Roubille, Francois ;
Houssany-Pissot, Sonia ;
Bouchot, Oceane ;
Aboyans, Victor ;
Vasram, Reza Rossanaly ;
Bochaton, Thomas ;
Logeart, Damien ;
Solal, Alain Cohen ;
Cartailler, Jerome ;
Mebazaa, Alexandre ;
Dillinger, Jean-Guillaume ;
Henry, Patrick ;
Pezel, Theo ;
Investigators ADDICT ICCU study .
EUROPEAN HEART JOURNAL - DIGITAL HEALTH, 2024, 6 (02) :190-199
[45]   The use of machine learning for the identification of peripheral artery disease and future mortality risk [J].
Ross, Elsie Gyang ;
Shah, Nigam H. ;
Dalman, Ronald L. ;
Nead, Kevin T. ;
Cooke, John P. ;
Leeper, Nicholas J. .
JOURNAL OF VASCULAR SURGERY, 2016, 64 (05) :1515-+
[46]   Personalized treatment for coronary artery disease patients: a machine learning approach [J].
Dimitris Bertsimas ;
Agni Orfanoudaki ;
Rory B. Weiner .
Health Care Management Science, 2020, 23 :482-506
[47]   Personalized treatment for coronary artery disease patients: a machine learning approach [J].
Bertsimas, Dimitris ;
Orfanoudaki, Agni ;
Weiner, Rory B. .
HEALTH CARE MANAGEMENT SCIENCE, 2020, 23 (04) :482-506
[48]   Decreasing Hospitalization and In-hospital Mortality Related to Cholangitis in the United States [J].
Jamal, M. Mazen ;
Yamini, David ;
Singson, Zarema ;
Samarasena, Jason ;
Hashemzadeh, Mehrtash ;
Vega, Kenneth J. .
JOURNAL OF CLINICAL GASTROENTEROLOGY, 2011, 45 (10) :E92-E96
[49]   Comparative mortality according to peripheral artery disease and coronary heart disease/stroke in the United States [J].
Matsushita, Kunihiro ;
Gao, Yumin ;
Sang, Yingying ;
Ballew, Shoshana H. ;
Salameh, Maya ;
Allison, Matthew ;
Selvin, Elizabeth ;
Coresh, Josef .
ATHEROSCLEROSIS, 2022, 354 :57-62
[50]   Accuracy of Machine Learning Models to Predict In-hospital Cardiac Arrest A Systematic Review [J].
Moffat, Laura M. ;
Xu, Dongjuan .
CLINICAL NURSE SPECIALIST, 2022, 36 (01) :29-44