Predicting Long-Term Allograft Survival in Liver Transplant Recipients

Xiang Gao, Michael Cooper, Maryam Naghibzadeh, Amirhossein Azhie, Mamatha Bhat, Rahul Krishnan
Proceedings of the 9th Machine Learning for Healthcare Conference, PMLR 252, 2024.

Abstract

Liver allograft failure occurs in approximately 20% of liver transplant recipients within five years post-transplant, leading to mortality or the need for retransplantation. Providing an accurate and interpretable model for individualized risk estimation of graft failure is essential for improving post-transplant care. To this end, we introduce the Model for Allograft Survival (MAS), a simple linear risk score that outperforms other advanced survival models. Using longitudinal patient follow-up data from the United States (U.S.), we develop our models on 82,959 liver transplant recipients and conduct multi-site evaluations on 11 regions. Additionally, by testing on a separate non-U.S. cohort, we explore the out-of-distribution generalization performance of various models without additional fine-tuning, a crucial property for clinical deployment. We find that the most complex models are also the ones most vulnerable to distribution shifts despite achieving the best in-distribution performance. Our findings not only provide a strong risk score for predicting long-term graft failure but also suggest that the routine machine learning pipeline with only in-distribution held-out validation could create harmful consequences for patients at deployment.

Cite this Paper

BibTeX
@InProceedings{pmlr-v252-gao24a, title = {Predicting Long-Term Allograft Survival in Liver Transplant Recipients}, author = {Gao, Xiang and Cooper, Michael and Naghibzadeh, Maryam and Azhie, Amirhossein and Bhat, Mamatha and Krishnan, Rahul}, booktitle = {Proceedings of the 9th Machine Learning for Healthcare Conference}, year = {2024}, editor = {Deshpande, Kaivalya and Fiterau, Madalina and Joshi, Shalmali and Lipton, Zachary and Ranganath, Rajesh and Urteaga, Iñigo}, volume = {252}, series = {Proceedings of Machine Learning Research}, month = {16--17 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v252/main/assets/gao24a/gao24a.pdf}, url = {https://proceedings.mlr.press/v252/gao24a.html}, abstract = {Liver allograft failure occurs in approximately 20% of liver transplant recipients within five years post-transplant, leading to mortality or the need for retransplantation. Providing an accurate and interpretable model for individualized risk estimation of graft failure is essential for improving post-transplant care. To this end, we introduce the Model for Allograft Survival (MAS), a simple linear risk score that outperforms other advanced survival models. Using longitudinal patient follow-up data from the United States (U.S.), we develop our models on 82,959 liver transplant recipients and conduct multi-site evaluations on 11 regions. Additionally, by testing on a separate non-U.S. cohort, we explore the out-of-distribution generalization performance of various models without additional fine-tuning, a crucial property for clinical deployment. We find that the most complex models are also the ones most vulnerable to distribution shifts despite achieving the best in-distribution performance. Our findings not only provide a strong risk score for predicting long-term graft failure but also suggest that the routine machine learning pipeline with only in-distribution held-out validation could create harmful consequences for patients at deployment.} }
Endnote
%0 Conference Paper %T Predicting Long-Term Allograft Survival in Liver Transplant Recipients %A Xiang Gao %A Michael Cooper %A Maryam Naghibzadeh %A Amirhossein Azhie %A Mamatha Bhat %A Rahul Krishnan %B Proceedings of the 9th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2024 %E Kaivalya Deshpande %E Madalina Fiterau %E Shalmali Joshi %E Zachary Lipton %E Rajesh Ranganath %E Iñigo Urteaga %F pmlr-v252-gao24a %I PMLR %U https://proceedings.mlr.press/v252/gao24a.html %V 252 %X Liver allograft failure occurs in approximately 20% of liver transplant recipients within five years post-transplant, leading to mortality or the need for retransplantation. Providing an accurate and interpretable model for individualized risk estimation of graft failure is essential for improving post-transplant care. To this end, we introduce the Model for Allograft Survival (MAS), a simple linear risk score that outperforms other advanced survival models. Using longitudinal patient follow-up data from the United States (U.S.), we develop our models on 82,959 liver transplant recipients and conduct multi-site evaluations on 11 regions. Additionally, by testing on a separate non-U.S. cohort, we explore the out-of-distribution generalization performance of various models without additional fine-tuning, a crucial property for clinical deployment. We find that the most complex models are also the ones most vulnerable to distribution shifts despite achieving the best in-distribution performance. Our findings not only provide a strong risk score for predicting long-term graft failure but also suggest that the routine machine learning pipeline with only in-distribution held-out validation could create harmful consequences for patients at deployment.
APA
Gao, X., Cooper, M., Naghibzadeh, M., Azhie, A., Bhat, M. & Krishnan, R.. (2024). Predicting Long-Term Allograft Survival in Liver Transplant Recipients. Proceedings of the 9th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 252 Available from https://proceedings.mlr.press/v252/gao24a.html.

Related Material