A machine learning model for prediction of 30-day primary graft failure after heart transplantation
(2023) In Heliyon 9(3).- Abstract
Background: Primary graft failure (PGF) remains the most common cause of short-term mortality after heart transplantation. The main objective was to develop and validate a risk model for prediction of short-term mortality due to PGF after heart transplantation using the ISHLT Heart Transplant Registry. Methods: We developed a non-linear artificial neural networks (ANN) model to evaluate the association between recipient-donor variables and post-transplant PGF. Patients in the ISHLT registry were randomly divided into derivation and an independent internal validation cohort. The primary endpoint was PGF defined as death within 30 days due to Graft failure or Cardiovascular causes or retransplant within 30 days for causes other than... (More)
Background: Primary graft failure (PGF) remains the most common cause of short-term mortality after heart transplantation. The main objective was to develop and validate a risk model for prediction of short-term mortality due to PGF after heart transplantation using the ISHLT Heart Transplant Registry. Methods: We developed a non-linear artificial neural networks (ANN) model to evaluate the association between recipient-donor variables and post-transplant PGF. Patients in the ISHLT registry were randomly divided into derivation and an independent internal validation cohort. The primary endpoint was PGF defined as death within 30 days due to Graft failure or Cardiovascular causes or retransplant within 30 days for causes other than rejection. Results: Among 64,964 adult recipients transplanted between 1994 and 2013, mean age was 51 years and 22% were female. The incidence of PGF up to 30 days was 3.7%. The ANN model selected 33 of 77 risk variables as relevant for PGF prediction. The C-index in the test cohort was 0.70 (95% CI: 0.68-0.71). The risk variables which most influenced the PGF were underlying HF diagnosis, ischemia time and sex, while renal function had a lower influence. Conclusion: An ANN model to predict primary graft dysfunction was derived and independently validated. The good discrimination of the ANN model likely results from its flexibility to model potentially non-linear relationships and interactions. Whether this model with improved discrimination can assist in clinical decisions at the time of transplant should be tested.
(Less)
- author
- Linse, Björn LU ; Ohlsson, Mattias LU ; Stehlik, Joseph ; Lund, Lars H. ; Andersson, Bodil LU and Nilsson, Johan LU
- organization
-
- Computational Biology and Biological Physics - Has been reorganised
- eSSENCE: The e-Science Collaboration
- Artificial Intelligence in CardioThoracic Sciences (AICTS) (research group)
- Hepato-Pancreato-Biliary Surgery (research group)
- Surgery (Lund)
- Thoracic Surgery
- Heparin bindning protein in cardiothoracic surgery (research group)
- Artificial Intelligence and Bioinformatics in Cardiothoracic Sciences (AIBCTS) (research group)
- Heart and Lung transplantation (research group)
- publishing date
- 2023-03
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Artificial neural network, Heart transplantation, Prediction, Primary graft failure
- in
- Heliyon
- volume
- 9
- issue
- 3
- article number
- e14282
- publisher
- Elsevier
- external identifiers
-
- scopus:85149794947
- pmid:36938431
- ISSN
- 2405-8440
- DOI
- 10.1016/j.heliyon.2023.e14282
- language
- English
- LU publication?
- yes
- id
- d3441484-5141-4c13-8bdd-b25b4475999d
- date added to LUP
- 2023-06-09 13:15:35
- date last changed
- 2024-06-15 03:51:03
@article{d3441484-5141-4c13-8bdd-b25b4475999d, abstract = {{<p>Background: Primary graft failure (PGF) remains the most common cause of short-term mortality after heart transplantation. The main objective was to develop and validate a risk model for prediction of short-term mortality due to PGF after heart transplantation using the ISHLT Heart Transplant Registry. Methods: We developed a non-linear artificial neural networks (ANN) model to evaluate the association between recipient-donor variables and post-transplant PGF. Patients in the ISHLT registry were randomly divided into derivation and an independent internal validation cohort. The primary endpoint was PGF defined as death within 30 days due to Graft failure or Cardiovascular causes or retransplant within 30 days for causes other than rejection. Results: Among 64,964 adult recipients transplanted between 1994 and 2013, mean age was 51 years and 22% were female. The incidence of PGF up to 30 days was 3.7%. The ANN model selected 33 of 77 risk variables as relevant for PGF prediction. The C-index in the test cohort was 0.70 (95% CI: 0.68-0.71). The risk variables which most influenced the PGF were underlying HF diagnosis, ischemia time and sex, while renal function had a lower influence. Conclusion: An ANN model to predict primary graft dysfunction was derived and independently validated. The good discrimination of the ANN model likely results from its flexibility to model potentially non-linear relationships and interactions. Whether this model with improved discrimination can assist in clinical decisions at the time of transplant should be tested.</p>}}, author = {{Linse, Björn and Ohlsson, Mattias and Stehlik, Joseph and Lund, Lars H. and Andersson, Bodil and Nilsson, Johan}}, issn = {{2405-8440}}, keywords = {{Artificial neural network; Heart transplantation; Prediction; Primary graft failure}}, language = {{eng}}, number = {{3}}, publisher = {{Elsevier}}, series = {{Heliyon}}, title = {{A machine learning model for prediction of 30-day primary graft failure after heart transplantation}}, url = {{http://dx.doi.org/10.1016/j.heliyon.2023.e14282}}, doi = {{10.1016/j.heliyon.2023.e14282}}, volume = {{9}}, year = {{2023}}, }