Identifying Modifiable Predictors of Long-Term Survival in Liver Transplant Recipients With Diabetes Mellitus Using Machine Learning

被引:24
作者
Yasodhara, Angeline [1 ,2 ,3 ]
Dong, Victor [4 ]
Azhie, Amirhossein [5 ,6 ]
Goldenberg, Anna [1 ,2 ,3 ]
Bhat, Mamatha [5 ,6 ,7 ,8 ]
机构
[1] Univ Toronto, Dept Comp Sci, Toronto, ON, Canada
[2] SickKids Res Inst, Genet & Genome Biol, Toronto, ON, Canada
[3] Vector Inst, Toronto, ON, Canada
[4] Interdept Div Crit Care Med, Toronto, ON, Canada
[5] Univ Hlth Network, Multi Organ Transplant Program, 585 Univ Ave,11PMB-183, Toronto, ON, Canada
[6] Univ Hlth Network, Div Gastroenterol, 585 Univ Ave,11PMB-183, Toronto, ON, Canada
[7] Univ Hlth Network & Univ Toronto, Div Gastroenterol & Hepatol, Toronto, ON, Canada
[8] Univ Toronto, Div Gastroenterol, Toronto, ON, Canada
基金
加拿大健康研究院;
关键词
CHRONIC KIDNEY-DISEASE; NEGATIVE IMPACT; RISK-FACTORS; MORTALITY; IMMUNOSUPPRESSION;
D O I
10.1002/lt.25930
中图分类号
R57 [消化系及腹部疾病];
学科分类号
摘要
Diabetes mellitus (DM) significantly impacts long-term survival after liver transplantation (LT). We identified survival factors for LT recipients who had DM to inform preventive care using machine-learning analysis. We analyzed risk factors for mortality in patients from across the United States using the Scientific Registry of Transplant Recipients (SRTR). Patients had undergone LT from 1987 to 2019, with a follow-up of 6.47 years (standard deviation [SD] 5.95). Findings were validated on a cohort from the University Health Network (UHN) from 1989 to 2014 (follow-up 8.15 years [SD 5.67]). Analysis was conducted with Cox proportional hazards and gradient boosting survival. The training set included 84.67% SRTR data (n = 15,289 patients), and the test set included 15.33% SRTR patients (n = 2769) and data from UHN patients (n = 1290). We included 18,058 adults (12,108 [67.05%] men, average age 54.21 years [SD 9.98]) from the SRTR who had undergone LT and had complete data for investigated features. A total of 4634 patients had preexisting DM, and 3158 had post-LT DM. The UHN data consisted of 1290 LT recipients (910 [70.5%] men, average age 54.0 years [SD 10.4]). Increased serum creatinine and hypertension significantly impacted mortality with preexisting DM 1.36 (95% confidence interval [CI], 1.21-1.54) and 1.20 (95% CI, 1.06-1.35) times, respectively. Sirolimus use increased mortality 1.36 times (95% CI, 1.18-1.58) in nondiabetics and 1.33 times (95% CI, 1.09-1.63) in patients with preexisting DM. A similar effect was found in post-LT DM, although it was not statistically significant (1.38 times; 95% CI, 1.07-1.77; P = 0.07). Survival predictors generally achieved a 0.60 to 0.70 area under the receiver operating characteristic for 5-year mortality. LT recipients who have DM have a higher mortality risk than those without DM. Hypertension, decreased renal function, and sirolimus for maintenance immunosuppression compound this mortality risk. These predisposing factors must be intensively treated and modified to optimize long-term survival after transplant.
引用
收藏
页码:536 / 547
页数:12
相关论文
共 36 条
[1]  
[Anonymous], 2016, **DATA OBJECT**, DOI [10.5281/zenodo.51773, DOI 10.5281/ZENODO.51773]
[2]  
[Anonymous], 2019, **DATA OBJECT**, DOI [10.5281/zenodo.3352343, DOI 10.5281/ZENODO.3352343]
[3]  
[Anonymous], 2018, Scientific Registry of Transplant Recipients
[4]   The Impact of Preexisting and Post-transplant Diabetes Mellitus on Outcomes Following Liver Transplantation [J].
Aravinthan, Aloysious D. ;
Fateen, Waleed ;
Doyle, Adam C. ;
Venkatachalapathy, Suresh V. ;
Lssachar, Assaf ;
Galvin, Zita ;
Sapisochin, Gonzalo ;
Cattral, Mark S. ;
Ghanekar, Anand ;
McGilvray, Ian D. ;
Selzner, Markus ;
Grant, David R. ;
Selzner, Nazia ;
Lilly, Leslie B. ;
Renner, Eberhard L. ;
Bhat, Mamatha .
TRANSPLANTATION, 2019, 103 (12) :2523-2530
[5]  
Bergstra James, 2013, P MACHINE LEARNING R, V28, P115
[6]   New-Onset Diabetes and Preexisting Diabetes Are Associated With Comparable Reduction in Long-Term Survival After Liver Transplant: A Machine Learning Approach [J].
Bhat, Venkat ;
Tazari, Mahmood ;
Watt, Kymberly D. ;
Bhat, Mamatha .
MAYO CLINIC PROCEEDINGS, 2018, 93 (12) :1794-1802
[7]   Early Changes in Kidney Function Predict Long-Term Chronic Kidney Disease and Mortality in Patients After Liver Transplantation [J].
Cantarovich, Marcelo ;
Tchervenkov, Jean ;
Paraskevas, Steven ;
Ghali, Peter ;
Wong, Philip ;
Deschenes, Marc ;
Chaudhury, Prosanto ;
Hassanain, Mazen ;
Vrochides, Dionisios ;
Metrakos, Peter ;
Barkun, Jeffrey .
TRANSPLANTATION, 2011, 92 (12) :1358-1363
[8]   International Liver Transplantation Society Consensus Statement on Immunosuppression in Liver Transplant Recipients [J].
Charlton, Michael ;
Levitsky, Josh ;
Aqel, Bashar ;
O'Grady, John ;
Hemibach, Julie ;
Rinella, Mary ;
Fung, John ;
Ghabril, Marwan ;
Thomason, Ray ;
Burra, Patrizia ;
Little, Ester Coelho ;
Berenguer, Marina ;
Shaked, Abraham ;
Trotter, James ;
Roberts, John ;
Rodriguez-Davalos, Manuel ;
Rela, Mohamed ;
Pomfret, Elizabeth ;
Heyrend, Caroline ;
Gallegos-Orozco, Juan ;
Saliba, Faouzi .
TRANSPLANTATION, 2018, 102 (05) :727-743
[9]   XGBoost: A Scalable Tree Boosting System [J].
Chen, Tianqi ;
Guestrin, Carlos .
KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :785-794
[10]   GLUCOCORTICOID-INDUCED HYPERGLYCEMIA [J].
Clore, John N. ;
Thurby-Hay, Linda .
ENDOCRINE PRACTICE, 2009, 15 (05) :469-474