Skip to main content

Advertisement

SpringerLink
Log in

Machine learning helps predict long-term mortality and graft failure in patients undergoing heart transplant

  • Original Article
  • Published:
General Thoracic and Cardiovascular Surgery Aims and scope Submit manuscript

Abstract

Objective

We aimed to develop a risk prediction model using a machine learning to predict survival and graft failure (GF) 5 years after orthotopic heart transplant (OHT).

Methods

Using the International Society of Heart and Lung Transplant (ISHLT) registry data, we analyzed 15,236 patients who underwent OHT from January 2005 to December 2009. 342 variables were extracted and used to develop a risk prediction model utilizing a gradient-boosted machine (GBM) model to predict the risk of GF and mortality 5 years after hospital discharge. After excluding variables missing at least 50% of the observations and variables with near zero variance, 87 variables were included in the GBM model. Ten fold cross-validation repeated 5 times was used to estimate the model’s external performance and optimize the hyperparameters simultaneously. Area under the receiver operator characteristic curve (AUC) for the GBM model was calculated for survival and GF 5 years post-OHT.

Results

The median duration of follow-up was 5 years. The mortality and GF 5 years post-OHT were 27.3% (n = 4161) and 28.1% (n = 4276), respectively. The AUC to predict 5-year mortality and GF is 0.717 (95% CI 0.696–0.737) and 0.716 (95% CI 0.696–0.736), respectively. Length of stay, recipient and donor age, recipient and donor body mass index, and ischemic time had the highest relative influence in predicting 5-year mortality and graft failure.

Conclusion

The GBM model has a good accuracy to predict 5-year mortality and graft failure post-OHT.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

References

  1. Wilhelm MJ. Long-term outcome following heart transplantation: current perspective. J Thorac Dis. 2015;7(3):549–51.

    PubMed  PubMed Central  Google Scholar 

  2. Chambers DC, Yusen RD, Cherikh WS, Goldfarb SB, Kucheryavaya AY, Khusch K, et al. The registry of the International Society for Heart and Lung Transplantation: thirty-fourth adult lung and heart-lung transplantation report—2017; focus theme: allograft ischemic time. J Heart Lung Transplant. 2017;36(10):1047–59.

    Article  Google Scholar 

  3. Fayek S, Quintini C, Chavin K, Marsh C. The current state of liver transplantation in the United States: perspective from American Society of Transplant Surgeons (ASTS) Scientific Studies Committee and endorsed by ASTS Council. Am J Transplant. 2016;16(11):3093–104.

    Article  CAS  Google Scholar 

  4. United Network for Organ Sharing. Facts about transplantation in the United States. Richmond, VA: UNOS. 1992;1:42.

    Google Scholar 

  5. Lund LH, Edwards LB, Kucheryavaya AY, Benden C, Dipchand AI, Goldfarb S, et al. The Registry of the International Society for Heart and Lung Transplantation: thirty-second official adult heart transplantation report–2015; focus theme: early graft failure. J Heart Lung Transplant. 2015;34(10):1244–54.

    Article  Google Scholar 

  6. Weiss ES, Allen JG, Arnaoutakis GJ, George TJ, Russell SD, Shah AS, et al. Creation of a quantitative recipient risk index for mortality prediction after cardiac transplantation (IMPACT). Ann Thorac Surg. 2011;92(3):914–21.

    Article  Google Scholar 

  7. Nilsson J, Ohlsson M, Höglund P, Ekmehag B, Koul B, Andersson B. The International Heart Transplant Survival Algorithm (IHTSA): a new model to improve organ sharing and survival. PLoS ONE. 2015;10(3):e0118644.

    Article  Google Scholar 

  8. Cruz JA, Wishart DS. Applications of machine learning in cancer prediction and prognosis. Cancer Inform. 2007;2:59–77.

    PubMed  PubMed Central  Google Scholar 

  9. Friedman J. Stochastic gradient boosting. Department of Statistics. San Francisco: Stanford University, Technical Report; 1999.

    Google Scholar 

  10. Friedman J. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001;29:1189–232.

    Article  Google Scholar 

  11. Kuhn M. Building predictive models in R using the caret package. J Stat Softw. 2008;28:1–26.

    Article  Google Scholar 

  12. Greenwell B, Boehmke B, Cunningham J, Developers G (2018) Generalized Boosted Regression Models. R Package Version 21. 4.

  13. DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44:837–45.

    Article  CAS  Google Scholar 

  14. Robin X, Turck N, Hainard A, et al. pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinformatics. 2011;12:77.

    Article  Google Scholar 

  15. Weiss ES, Allen JG, Kilic A, Russell SD, Baumgartner WA, Conte JV, et al. Development of a quantitative donor risk index to predict short-term mortality in orthotopic heart transplantation. J Heart Lung Transplant. 2012;31(3):266–73.

    Article  Google Scholar 

  16. Smits JM, De Pauw M, de Vries E, Rahmel A, Meiser B, Laufer G, et al. Donor scoring system for heart transplantation and the impact on patient survival. J Heart Lung Transplant. 2012;31(4):387–97.

    Article  Google Scholar 

  17. Hong KN, Iribarne A, Worku B, Takayama H, Gelijns AC, Naka Y, et al. Who is the high-risk recipient? Predicting mortality after heart transplant using pretransplant donor and recipient risk factors. Ann Thorac Surg. 2011;92(2):520–7.

    Article  Google Scholar 

  18. Anyanwu AC, Rogers CA, Murday AJ. A simple approach to risk stratification in adult heart transplantation. Eur J Cardiothorac Surg. 1999;16(4):424–8.

    Article  CAS  Google Scholar 

  19. Biganzoli E, Boracchi P, Mariani L, Marubini E. Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach. Stat Med. 1998;17(10):1169–86.

    Article  CAS  Google Scholar 

  20. Lippmann RP, Shahian DM. Coronary artery bypass risk prediction using neural networks. Ann Thorac Surg. 1997;63(6):1635–43.

    Article  CAS  Google Scholar 

  21. Pedotti P, Mattucci DA, Gabbrielli F, Venettoni S, Costa AN, Taioli E. Analysis of the complex effect of donor’s age on survival of subjects who underwent heart transplantation. Transplantation. 2005;80(8):1026–32.

    Article  Google Scholar 

  22. Russo MJ, Chen JM, Sorabella RA, Martens TP, Garrido M, Davies RR, et al. The effect of ischemic time on survival after heart transplantation varies by donor age: an analysis of the United Network for Organ Sharing database. J Thorac Cardiovasc Surg. 2007;133(2):554–9.

    Article  Google Scholar 

  23. Russo MJ, Iribarne A, Hong KN, Ramlawi B, Chen JM, Takayama H, et al. Factors associated with primary graft failure after heart transplantation. Transplantation. 2010;90(4):444–50.

    Article  Google Scholar 

  24. Kilic A, Weiss ES, George TJ, Arnaoutakis GJ, Yuh DD, Shah AS, et al. What predicts long-term survival after heart transplantation? An analysis of 9,400 ten-year survivors. Ann Thorac Surg. 2012;93(3):699–704.

    Article  Google Scholar 

  25. Reichart B. Size matching in heart transplantation. J Heart Lung Transplant. 1992;11(4 Pt 2):S199–202.

    CAS  PubMed  Google Scholar 

  26. Zeier M, Döhler B, Opelz G, Ritz E. The effect of donor gender on graft survival. J Am Soc Nephrol. 2002;13(10):2570–6.

    Article  Google Scholar 

Download references

Funding

No funding was available for the current study.

Author information

Author notes

  1. Pradyumna Agasthi, Matthew R. Buras and Sean D. Smith equally contributed to the manuscript.

Authors and Affiliations

  1. Department of Cardiovascular Medicine, Mayo Clinic, 5777 E Mayo Blvd, Phoenix, AZ, 85054, USA

    Pradyumna Agasthi, Farouk Mookadam, Senthil Anand, Julie L. Rosenthal, Brian W. Hardaway & Reza Arsanjani

  2. Department of Internal Medicine, Mayo Clinic, Phoenix, AZ, USA

    Sean D. Smith

  3. Division of Biomedical Statistics and Informatics, Mayo Clinic, Scottsdale, AZ, USA

    Matthew R. Buras & Michael A. Golafshar

  4. Division of Cardiovascular and Thoracic Surgery, Mayo Clinic, Phoenix, AZ, USA

    Patrick DeValeria

Authors
  1. Pradyumna Agasthi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Matthew R. Buras
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sean D. Smith
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Michael A. Golafshar
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Farouk Mookadam
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Senthil Anand
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Julie L. Rosenthal
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Brian W. Hardaway
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Patrick DeValeria
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Reza Arsanjani
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

PA designed the study, extracted the data, drafted the initial manuscript, and critically reviewed the manuscript. SDS drafted the initial manuscript and critically reviewed the manuscript. SA extracted the data and critically reviewed the manuscript. MB analyzed the data, prepared the figures, and critically reviewed the manuscript. MAG analyzed the data, prepared the figures, and critically reviewed the manuscript. JLR critically reviewed the manuscript. BWH critically reviewed the manuscript. PD critically reviewed the manuscript. FM designed the study and critically reviewed the manuscript. RA designed the study and critically reviewed the manuscript. All authors have read and approved the final manuscript.

Corresponding author

Correspondence to Pradyumna Agasthi.

Ethics declarations

Conflict of interest

The authors have no conflict of interest to declare.

Ethical approval

The study complied with the Declaration of Helsinki and was approved by the local institutional review board. The committee waived the requirement for informed consent in consideration of the retrospective nature of the study and anonymous data analyses.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary data (DOCX 610 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Agasthi, P., Buras, M.R., Smith, S.D. et al. Machine learning helps predict long-term mortality and graft failure in patients undergoing heart transplant. Gen Thorac Cardiovasc Surg 68, 1369–1376 (2020). https://doi.org/10.1007/s11748-020-01375-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11748-020-01375-6

Keywords

Search

Navigation