Predictors of shorter- and longer-term mortality after COVID-19 presentation among dialysis patients: parallel use of machine learning models in Latin and North American countries
Tóm tắt
We developed machine learning models to understand the predictors of shorter-, intermediate-, and longer-term mortality among hemodialysis (HD) patients affected by COVID-19 in four countries in the Americas. We used data from adult HD patients treated at regional institutions of a global provider in Latin America (LatAm) and North America who contracted COVID-19 in 2020 before SARS-CoV-2 vaccines were available. Using 93 commonly captured variables, we developed machine learning models that predicted the likelihood of death overall, as well as during 0–14, 15–30, > 30 days after COVID-19 presentation and identified the importance of predictors. XGBoost models were built in parallel using the same programming with a 60%:20%:20% random split for training, validation, & testing data for the datasets from LatAm (Argentina, Columbia, Ecuador) and North America (United States) countries. Among HD patients with COVID-19, 28.8% (1,001/3,473) died in LatAm and 20.5% (4,426/21,624) died in North America. Mortality occurred earlier in LatAm versus North America; 15.0% and 7.3% of patients died within 0–14 days, 7.9% and 4.6% of patients died within 15–30 days, and 5.9% and 8.6% of patients died > 30 days after COVID-19 presentation, respectively. Area under curve ranged from 0.73 to 0.83 across prediction models in both regions. Top predictors of death after COVID-19 consistently included older age, longer vintage, markers of poor nutrition and more inflammation in both regions at all timepoints. Unique patient attributes (higher BMI, male sex) were top predictors of mortality during 0–14 and 15–30 days after COVID-19, yet not mortality > 30 days after presentation. Findings showed distinct profiles of mortality in COVID-19 in LatAm and North America throughout 2020. Mortality rate was higher within 0–14 and 15–30 days after COVID-19 in LatAm, while mortality rate was higher in North America > 30 days after presentation. Nonetheless, a remarkable proportion of HD patients died > 30 days after COVID-19 presentation in both regions. We were able to develop a series of suitable prognostic prediction models and establish the top predictors of death in COVID-19 during shorter-, intermediate-, and longer-term follow up periods.
Tài liệu tham khảo
citation_journal_title=Nephrol Dial Transplant; citation_title=Impact of first-wave COronaVIrus disease 2019 infection in patients on haemoDIALysis in Alsace: the observational COVIDIAL study; citation_author=N Keller, F Chantrel, T Krummel, D Bazin-Kara, AL Faller, C Muller, T Nussbaumer, M Ismer, A Benmoussa, M Brahim-Bouna; citation_volume=35; citation_issue=8; citation_publication_date=2020; citation_pages=1338-1411; citation_doi=10.1093/ndt/gfaa170; citation_id=CR1
citation_journal_title=Kidney Med; citation_title=COVID-19 in Patients Undergoing Hemodialysis: Prevalence and Asymptomatic Screening During a Period of High Community Prevalence in a Large Paris Center; citation_author=C Creput, C Fumeron, D Toledano, M Diaconita, H Izzedine; citation_volume=2; citation_issue=6; citation_publication_date=2020; citation_pages=716-723 e711; citation_doi=10.1016/j.xkme.2020.09.001; citation_id=CR2
citation_journal_title=Clin Kidney J; citation_title=Risk prediction of COVID-19 incidence and mortality in a large multi-national hemodialysis cohort: implications for management of the pandemic in outpatient hemodialysis settings; citation_author=M Haarhaus, C Santos, M Haase, P MotaVeiga, C Lucas, F Macario; citation_volume=14; citation_issue=3; citation_publication_date=2021; citation_pages=805-813; citation_doi=10.1093/ckj/sfab037; citation_id=CR3
citation_journal_title=Am J Kidney Dis; citation_title=COVID-19 Among US Dialysis Patients: Risk Factors and Outcomes From a National Dialysis Provider; citation_author=CM Hsu, DE Weiner, G Aweh, DC Miskulin, HJ Manley, C Stewart, V Ladik, J Hosford, EC Lacson, DS Johnson; citation_volume=77; citation_issue=5; citation_publication_date=2021; citation_pages=748-756 e741; citation_doi=10.1053/j.ajkd.2021.01.003; citation_id=CR4
Neumann ME. Latest data show 305 dialysis patient deaths due to COVID-19 in the US. Nephrology News & Issues 2020, (Accessed 22 Apr 2020)
https://www.healio.com/nephrology/infection-control/news/online/%7B3a263aa9-ad59-4c3f-aab7-07b8395508e5%7D/latest-data-show-305-dialysis-patient-deaths-due-to-covid-19-in-the-us
.
citation_journal_title=CMAJ; citation_title=COVID-19 in patients undergoing long-term dialysis in Ontario; citation_author=L Taji, D Thomas, MJ Oliver, J Ip, Y Tang, A Yeung, R Cooper, AA House, P McFarlane, PG Blake; citation_volume=193; citation_issue=8; citation_publication_date=2021; citation_pages=E278-E284; citation_doi=10.1503/cmaj.202601; citation_id=CR6
citation_journal_title=J Nephrol; citation_title=Exposure to novel coronavirus in patients on renal replacement therapy during the exponential phase of COVID-19 pandemic: survey of the Italian Society of Nephrology; citation_author=G Quintaliani, G Reboldi, A Napoli, M Nordio, A Limido, F Aucella, P Messa, G Brunori; citation_volume=33; citation_issue=4; citation_publication_date=2020; citation_pages=725-736; citation_doi=10.1007/s40620-020-00794-1; citation_id=CR7
citation_journal_title=Kidney Int; citation_title=Results from the ERA-EDTA Registry indicate a high mortality due to COVID-19 in dialysis patients and kidney transplant recipients across Europe; citation_author=KJ Jager, A Kramer, NC Chesnaye, C Couchoud, JE Sanchez-Alvarez, L Garneata, F Collart, MH Hemmelder, P Ambuhl, J Kerschbaum; citation_volume=98; citation_issue=6; citation_publication_date=2020; citation_pages=1540-1548; citation_doi=10.1016/j.kint.2020.09.006; citation_id=CR8
citation_journal_title=Kidney Med; citation_title=Worldwide Early Impact of COVID-19 on Dialysis Patients and Staff and Lessons Learned: A DOPPS Roundtable Discussion; citation_author=BM Robinson, M Guedes, M Alghonaim, A Cases, I Dasgupta, L Gan, SH Jacobson, T Kanjanabuch, YL Kim, W Kleophas; citation_volume=3; citation_issue=4; citation_publication_date=2021; citation_pages=619-634; citation_doi=10.1016/j.xkme.2021.03.006; citation_id=CR9
United States Renal Data System. 2021 USRDS Annual Data Report: Epidemiology of kidney disease in the United States. In: National Institutes of Health, National Institute of Diabetes and Digestive and Kidney Diseases. Bethesda; 2021.
Dialysis COVID-19 Vaccination Data Dashboard. Centers for Disease Control and Prevention: National Healthcare Safety Network (Accessed 15 Nov 2021):
https://www.cdc.gov/nhsn/covid19/dial-vaccination-dashboard.html
.
Coronavirus Resource Center: Understanding Vaccination Progress by Country. Johns Hopkins University School of Medicine (Accessed 15 Nov 2021):
https://coronavirus.jhu.edu/vaccines/international
.
citation_journal_title=JAMA Netw Open; citation_title=Immunogenicity rates after SARS-CoV-2 vaccination in people with end-stage kidney disease: a systematic review and meta-analysis; citation_author=JJ Chen, TH Lee, YC Tian, CC Lee, PC Fan, CH Chang; citation_volume=4; citation_issue=10; citation_publication_date=2021; citation_pages=e2131749; citation_doi=10.1001/jamanetworkopen.2021.31749; citation_id=CR13
citation_journal_title=Clin J Am Soc Nephrol; citation_title=Humoral Response to mRNA versus an Adenovirus Vector-Based SARS-CoV-2 Vaccine in Dialysis Patients; citation_author=JG Mulhern, A Fadia, R Patel, LH Ficociello, J Willetts, IA Dahne-Steuber, MC Pollan, C Mullon, J DeLisi, C Johnson; citation_volume=16; citation_issue=11; citation_publication_date=2021; citation_pages=1720-1722; citation_doi=10.2215/CJN.06450521; citation_id=CR14
citation_journal_title=Kidney Int Rep; citation_title=COVID-19 vaccination acceptance and hesitancy in dialysis staff: first results from New York City; citation_author=GM Pamplona, T Sullivan, P Kotanko; citation_volume=6; citation_issue=4; citation_publication_date=2021; citation_pages=1192-1193; citation_doi=10.1016/j.ekir.2021.02.001; citation_id=CR15
citation_journal_title=Kidney Int; citation_title=Reasons for COVID-19 vaccination hesitancy in hemodialysis patients; citation_author=S Bhandari; citation_volume=100; citation_issue=3; citation_publication_date=2021; citation_pages=702; citation_doi=10.1016/j.kint.2021.07.003; citation_id=CR16
citation_journal_title=J Nephrol; citation_title=EuCliD (European Clinical Database): a database comparing different realities; citation_author=D Marcelli, J Kirchgessner, C Amato, H Steil, A Mitteregger, V Moscardo, C Carioni, G Orlandini, E Gatti; citation_volume=14; citation_issue=Suppl 4; citation_publication_date=2001; citation_pages=S94-100; citation_id=CR17
Chaudhuri S, Lasky R, Jiao Y, Larkin J, Monaghan C, Winter A, Neri L, Kotanko P, Hymes J, Lee S, et al. Trajectories of clinical and laboratory characteristics associated with COVID-19 in hemodialysis patients by survival. Hemodial Int. 2022;26(1):94–107.
citation_title=XGBoost: A Scalable Tree Boosting System; citation_inbook_title=Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; citation_publication_date=2016; citation_pages=785-794; citation_id=CR19; citation_author=T Chen; citation_author=C Guestrin; citation_publisher=Association for Computing Machinery
citation_journal_title=PLoS One; citation_title=The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets; citation_author=T Saito, M Rehmsmeier; citation_volume=10; citation_issue=3; citation_publication_date=2015; citation_pages=e0118432; citation_doi=10.1371/journal.pone.0118432; citation_id=CR20
Shapley LS. A Value for n-Person Games. In: Kuhn HW, Tucker AW, Eds., Contributions to the Theory of Games II. Annals of Mathematics Studies, Princeton University Press, Princeton 1953, 28:307–317.
citation_journal_title=J Knowl Inf Syst; citation_title=Explaining prediction models and individual predictions with feature contributions; citation_author=E Štrumbelj, I Kononenko; citation_volume=41; citation_publication_date=2013; citation_pages=647-665; citation_doi=10.1007/s10115-013-0679-x; citation_id=CR22
citation_title=A Unified Approach to Interpreting Model Predictions; citation_inbook_title=Advances in Neural Information Processing Systems 30. Curran Associates, Inc; citation_publication_date=2017; citation_pages=4765-4774; citation_id=CR23; citation_author=S Lundberg; citation_author=SI Lee
citation_journal_title=Nat Mach Intell; citation_title=From local explanations to global understanding with explainable AI for trees; citation_author=SM Lundberg, G Erion, H Chen, A DeGrave, JM Prutkin, B Nair, R Katz, J Himmelfarb, N Bansal, SI Lee; citation_volume=2; citation_issue=1; citation_publication_date=2020; citation_pages=56-67; citation_doi=10.1038/s42256-019-0138-9; citation_id=CR24
citation_journal_title=Semin Dial; citation_title=Artificial intelligence enabled applications in kidney disease; citation_author=S Chaudhuri, A Long, H Zhang, C Monaghan, JW Larkin, P Kotanko, S Kalaskar, JP Kooman, FM Sande, FW Maddux; citation_volume=34; citation_issue=1; citation_publication_date=2021; citation_pages=5-16; citation_doi=10.1111/sdi.12915; citation_id=CR25
Lugon JR, Neves P, Pio-Abreu A, do Nascimento MM, Sesso R; Investigators C-H-B. Evaluation of central venous catheter and other risk factors for mortality in chronic hemodialysis patients with COVID-19 in Brazil. Int Urol Nephrol. 2022;54(1):193–9.
citation_journal_title=JAMA Netw Open; citation_title=COVID-19 risk factors and mortality outcomes among medicare patients receiving long-term dialysis; citation_author=S Salerno, JM Messana, GW Gremel, C Dahlerus, RA Hirth, P Han, JH Segal, T Xu, D Shaffer, A Jiao; citation_volume=4; citation_issue=11; citation_publication_date=2021; citation_pages=e2135379-e2135379; citation_doi=10.1001/jamanetworkopen.2021.35379; citation_id=CR27
citation_journal_title=Comput Methods Programs Biomed; citation_title=Prediction of death status on the course of treatment in SARS-COV-2 patients with deep learning and machine learning methods; citation_author=M Kivrak, E Guldogan, C Colak; citation_volume=201; citation_publication_date=2021; citation_pages=105951; citation_doi=10.1016/j.cmpb.2021.105951; citation_id=CR28
Pettit RW, Fullem R, Cheng C, Amos CI. Artificial intelligence, machine learning, and deep learning for clinical outcome prediction. Emerg Top Life Sci. 2021;5(6):729–45.
Monaghan CK, Larkin JW, Chaudhuri S, Han H, Jiao Y, Bermudez KM, Weinhandl ED, Dahne-Steuber IA, Belmonte K, Neri L et al. Machine Learning for Prediction of Hemodialysis Patients with an Undetected SARS-CoV-2 Infection. Kidney360 2021:
https://doi.org/10.34067/KID.0003802020
.