Prediction of 1-year mortality after heart transplantation using machine learning approaches: A single-center study from China

被引:20
作者
Zhou, Ying [1 ]
Chen, Si [1 ]
Rao, Zhenqi [1 ]
Yang, Dong [2 ]
Liu, Xiang [2 ]
Dong, Nianguo [1 ]
Li, Fei [1 ]
机构
[1] Huazhong Univ Sci & Technol, Union Hosp, Dept Cardiovasc Surg, Tongji Med Coll, 1277 Jiefang Ave, Wuhan 430022, Peoples R China
[2] Guangzhou AID Cloud Technol, Dept Data Sci, Guangzhou, Guangdong, Peoples R China
基金
中国国家自然科学基金;
关键词
Heart transplantation; Risk-prediction model; Machine-learning approach; Shapley Additive exPlanations; GUIDELINES; DIAGNOSIS; ESC;
D O I
10.1016/j.ijcard.2021.07.024
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Background: Heart transplantation (HTx) remains the gold-standard treatment for end-stage heart failure. The aim of this study was to establish a risk-prediction model for assessing prognosis of HTx using machine-learning approach. Methods: Consecutive recipients of orthotopic HTx at our institute between January 1st, 2015 and December 31st, 2018 were included in this study. The primary outcome was 1-year mortality. Least absolute shrinkage and selection operator method was used to select variables and seven different machine-learning approaches were employed to develop the risk-prediction model. Bootstrap method was used for model validation. Shapley Additive exPlanations (SHAP) method was used for model interpretation. Results: 381 recipients were included with average age of 43.783 years old. Albumin, recipient age and left atrium diameter ranked top three most important variables that affected the 1-year mortality of HTx. Other important variables included red blood cell, hemoglobin, lymphocyte%, smoking history, use of lyophilized rhBNP, use of Levosimendan, hypertension, cardiac surgery history, malignancy and endotracheal intubation history. Random Forest (RF) model achieved the best area under curves (AUC) of 0.801 and gradient boosting machine (GBM) showed the best sensitivity of 0.271. SHAP method was introduced to display the RF model's predicting processes of "survival" or "death" in individual level. Conclusions: We established the risk-prediction model for postoperative prognosis of HTx patients by using machine learning method and demonstrated that the RF model performed the highest discrimination with the largest AUC when validated. This prediction model could help to recognize high-risk HTx recipients, provide personalized therapy plan and reduce organ wastage.
引用
收藏
页码:21 / 27
页数:7
相关论文
共 23 条
[1]   Machine learning helps predict long-term mortality and graft failure in patients undergoing heart transplant [J].
Agasthi, Pradyumna ;
Buras, Matthew R. ;
Smith, Sean D. ;
Golafshar, Michael A. ;
Mookadam, Farouk ;
Anand, Senthil ;
Rosenthal, Julie L. ;
Hardaway, Brian W. ;
DeValeria, Patrick ;
Arsanjani, Reza .
GENERAL THORACIC AND CARDIOVASCULAR SURGERY, 2020, 68 (12) :1369-1376
[3]  
Bastanlar Y, 2014, METHODS MOL BIOL, V1107, P105, DOI 10.1007/978-1-62703-748-8_7
[4]   Tobacco Smoking and Solid Organ Transplantation [J].
Corbett, Chris ;
Armstrong, Matthew J. ;
Neuberger, James .
TRANSPLANTATION, 2012, 94 (10) :979-987
[5]   Explainable Machine Learning Model for Predicting GI Bleed Mortality in the Intensive Care Unit [J].
Deshmukh, Farah ;
Merchant, Shamel S. .
AMERICAN JOURNAL OF GASTROENTEROLOGY, 2020, 115 (10) :1657-1668
[6]   Heart Transplantation An In-Depth Survival Analysis [J].
Hsich, Eileen M. ;
Blackstone, Eugene H. ;
Thuita, Lucy W. ;
McNamara, Dennis M. ;
Rogers, Joseph G. ;
Yancy, Clyde W. ;
Goldberg, Lee R. ;
Valapour, Maryam ;
Xu, Gang ;
Ishwaran, Hemant .
JACC-HEART FAILURE, 2020, 8 (07) :557-568
[7]   Variables of importance in the Scientific Registry of Transplant Recipients database predictive of heart transplant waitlist mortality [J].
Hsich, Eileen M. ;
Thuita, Lucy ;
McNamara, Dennis M. ;
Rogers, Joseph G. ;
Valapour, Maryam ;
Goldberg, Lee R. ;
Yancy, Clyde W. ;
Ackstone, Eugene H. B. ;
Ishwaran, Hemant .
AMERICAN JOURNAL OF TRANSPLANTATION, 2019, 19 (07) :2067-2076
[8]   COMPLETE CONVERGENCE AND THE LAW OF LARGE NUMBERS [J].
HSU, PL ;
ROBBINS, H .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 1947, 33 (02) :25-31
[9]  
Lundberg SM, 2017, ADV NEUR IN, V30
[10]  
Markus MT, 1998, PSYCHOMETRIKA, V63, P97