Machine Learning Prediction Model of Waitlist Outcomes in Patients with Primary Sclerosing Cholangitis

Background. Liver transplantation is essential for many people with primary sclerosing cholangitis (PSC). People with PSC are less likely to receive a deceased donor liver transplant compared with other causes of chronic liver disease. This disparity may stem from the inaccuracy of the model for end...

Full description

Saved in:
Bibliographic Details
Main Authors: Xun Zhao, MD, Maryam Naghibzadeh, MD, Yingji Sun, MSc, Arya Rahmani, BSc, Leslie Lilly, MD, Nazia Selzner, MD, PhD, Cynthia Tsien, MD, MPH, Elmar Jaeckel, MD, Mary Pressley Vyas, Rahul Krishnan, PhD, Gideon Hirschfield, MD, PhD, MB, Mamatha Bhat, MD, PhD
Format: Article
Language:English
Published: Wolters Kluwer 2025-04-01
Series:Transplantation Direct
Online Access:http://journals.lww.com/transplantationdirect/fulltext/10.1097/TXD.0000000000001774
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850139805517611008
author Xun Zhao, MD
Maryam Naghibzadeh, MD
Yingji Sun, MSc
Arya Rahmani, BSc
Leslie Lilly, MD
Nazia Selzner, MD, PhD
Cynthia Tsien, MD, MPH
Elmar Jaeckel, MD
Mary Pressley Vyas
Rahul Krishnan, PhD
Gideon Hirschfield, MD, PhD, MB
Mamatha Bhat, MD, PhD
author_facet Xun Zhao, MD
Maryam Naghibzadeh, MD
Yingji Sun, MSc
Arya Rahmani, BSc
Leslie Lilly, MD
Nazia Selzner, MD, PhD
Cynthia Tsien, MD, MPH
Elmar Jaeckel, MD
Mary Pressley Vyas
Rahul Krishnan, PhD
Gideon Hirschfield, MD, PhD, MB
Mamatha Bhat, MD, PhD
author_sort Xun Zhao, MD
collection DOAJ
description Background. Liver transplantation is essential for many people with primary sclerosing cholangitis (PSC). People with PSC are less likely to receive a deceased donor liver transplant compared with other causes of chronic liver disease. This disparity may stem from the inaccuracy of the model for end-stage liver disease (MELD) in predicting waitlist mortality or dropout for PSC. The broad applicability of MELD across many causes comes at the expense of accuracy in prediction for certain causes that involve unique comorbidities. We aimed to develop a model that could more accurately predict dynamic changes in waitlist outcomes among patients with PSC while including complex clinical variables. Methods. We developed 3 machine learning architectures using data from 4666 patients with PSC in the Scientific Registry of Transplant Recipients (SRTR) and tested our models on our institutional data set of 144 patients at the University Health Network (UHN). We evaluated their time-dependent concordance index (C-index) for mortality prediction and compared it against MELD-sodium and MELD 3.0. Results. Random survival forest (RSF), a decision tree–based survival model, outperformed MELD-sodium and MELD 3.0 in both the SRTR and the UHN test data set using the same bloodwork variables and readily available demographic data. It achieved a C-index of 0.868 (SD 0.020) and 0.771 (SD 0.085) on the SRTR and UHN test data, respectively. Training a separate RSF model using the UHN data with PSC-specific achieved a C-index of 0.91. In addition to high MELD score, increased white blood cells, time on the waiting list, platelet count, presence of Autoimmune hepatitis-PSC overlap, aspartate aminotransferase, female sex, age, history of stricture dilation, and extremes of body weight were the top-ranked features predictive of the outcomes. Conclusions. Our RSF model offers more accurate waitlist outcome prediction in PSC. The significant performance improvement with the inclusion of PSC-specific variables highlights the importance of disease-specific variables for predicting trajectories of clinically distinct presentations.
format Article
id doaj-art-62df13c145474c16adaf9dafa4dc206f
institution OA Journals
issn 2373-8731
language English
publishDate 2025-04-01
publisher Wolters Kluwer
record_format Article
series Transplantation Direct
spelling doaj-art-62df13c145474c16adaf9dafa4dc206f2025-08-20T02:30:06ZengWolters KluwerTransplantation Direct2373-87312025-04-01114e177410.1097/TXD.0000000000001774202504000-00009Machine Learning Prediction Model of Waitlist Outcomes in Patients with Primary Sclerosing CholangitisXun Zhao, MD0Maryam Naghibzadeh, MD1Yingji Sun, MSc2Arya Rahmani, BSc3Leslie Lilly, MD4Nazia Selzner, MD, PhD5Cynthia Tsien, MD, MPH6Elmar Jaeckel, MD7Mary Pressley Vyas8Rahul Krishnan, PhD9Gideon Hirschfield, MD, PhD, MB10Mamatha Bhat, MD, PhD111 Ajmera Transplant Program, University Health Network, Toronto, ON, Canada.1 Ajmera Transplant Program, University Health Network, Toronto, ON, Canada.1 Ajmera Transplant Program, University Health Network, Toronto, ON, Canada.1 Ajmera Transplant Program, University Health Network, Toronto, ON, Canada.1 Ajmera Transplant Program, University Health Network, Toronto, ON, Canada.1 Ajmera Transplant Program, University Health Network, Toronto, ON, Canada.1 Ajmera Transplant Program, University Health Network, Toronto, ON, Canada.1 Ajmera Transplant Program, University Health Network, Toronto, ON, Canada.3 PSC Partners Seeking a Cure Canada, Toronto, ON, Canada.4 Department of Computer Science, University of Toronto, Toronto, ON, Canada.1 Ajmera Transplant Program, University Health Network, Toronto, ON, Canada.1 Ajmera Transplant Program, University Health Network, Toronto, ON, Canada.Background. Liver transplantation is essential for many people with primary sclerosing cholangitis (PSC). People with PSC are less likely to receive a deceased donor liver transplant compared with other causes of chronic liver disease. This disparity may stem from the inaccuracy of the model for end-stage liver disease (MELD) in predicting waitlist mortality or dropout for PSC. The broad applicability of MELD across many causes comes at the expense of accuracy in prediction for certain causes that involve unique comorbidities. We aimed to develop a model that could more accurately predict dynamic changes in waitlist outcomes among patients with PSC while including complex clinical variables. Methods. We developed 3 machine learning architectures using data from 4666 patients with PSC in the Scientific Registry of Transplant Recipients (SRTR) and tested our models on our institutional data set of 144 patients at the University Health Network (UHN). We evaluated their time-dependent concordance index (C-index) for mortality prediction and compared it against MELD-sodium and MELD 3.0. Results. Random survival forest (RSF), a decision tree–based survival model, outperformed MELD-sodium and MELD 3.0 in both the SRTR and the UHN test data set using the same bloodwork variables and readily available demographic data. It achieved a C-index of 0.868 (SD 0.020) and 0.771 (SD 0.085) on the SRTR and UHN test data, respectively. Training a separate RSF model using the UHN data with PSC-specific achieved a C-index of 0.91. In addition to high MELD score, increased white blood cells, time on the waiting list, platelet count, presence of Autoimmune hepatitis-PSC overlap, aspartate aminotransferase, female sex, age, history of stricture dilation, and extremes of body weight were the top-ranked features predictive of the outcomes. Conclusions. Our RSF model offers more accurate waitlist outcome prediction in PSC. The significant performance improvement with the inclusion of PSC-specific variables highlights the importance of disease-specific variables for predicting trajectories of clinically distinct presentations.http://journals.lww.com/transplantationdirect/fulltext/10.1097/TXD.0000000000001774
spellingShingle Xun Zhao, MD
Maryam Naghibzadeh, MD
Yingji Sun, MSc
Arya Rahmani, BSc
Leslie Lilly, MD
Nazia Selzner, MD, PhD
Cynthia Tsien, MD, MPH
Elmar Jaeckel, MD
Mary Pressley Vyas
Rahul Krishnan, PhD
Gideon Hirschfield, MD, PhD, MB
Mamatha Bhat, MD, PhD
Machine Learning Prediction Model of Waitlist Outcomes in Patients with Primary Sclerosing Cholangitis
Transplantation Direct
title Machine Learning Prediction Model of Waitlist Outcomes in Patients with Primary Sclerosing Cholangitis
title_full Machine Learning Prediction Model of Waitlist Outcomes in Patients with Primary Sclerosing Cholangitis
title_fullStr Machine Learning Prediction Model of Waitlist Outcomes in Patients with Primary Sclerosing Cholangitis
title_full_unstemmed Machine Learning Prediction Model of Waitlist Outcomes in Patients with Primary Sclerosing Cholangitis
title_short Machine Learning Prediction Model of Waitlist Outcomes in Patients with Primary Sclerosing Cholangitis
title_sort machine learning prediction model of waitlist outcomes in patients with primary sclerosing cholangitis
url http://journals.lww.com/transplantationdirect/fulltext/10.1097/TXD.0000000000001774
work_keys_str_mv AT xunzhaomd machinelearningpredictionmodelofwaitlistoutcomesinpatientswithprimarysclerosingcholangitis
AT maryamnaghibzadehmd machinelearningpredictionmodelofwaitlistoutcomesinpatientswithprimarysclerosingcholangitis
AT yingjisunmsc machinelearningpredictionmodelofwaitlistoutcomesinpatientswithprimarysclerosingcholangitis
AT aryarahmanibsc machinelearningpredictionmodelofwaitlistoutcomesinpatientswithprimarysclerosingcholangitis
AT leslielillymd machinelearningpredictionmodelofwaitlistoutcomesinpatientswithprimarysclerosingcholangitis
AT naziaselznermdphd machinelearningpredictionmodelofwaitlistoutcomesinpatientswithprimarysclerosingcholangitis
AT cynthiatsienmdmph machinelearningpredictionmodelofwaitlistoutcomesinpatientswithprimarysclerosingcholangitis
AT elmarjaeckelmd machinelearningpredictionmodelofwaitlistoutcomesinpatientswithprimarysclerosingcholangitis
AT marypressleyvyas machinelearningpredictionmodelofwaitlistoutcomesinpatientswithprimarysclerosingcholangitis
AT rahulkrishnanphd machinelearningpredictionmodelofwaitlistoutcomesinpatientswithprimarysclerosingcholangitis
AT gideonhirschfieldmdphdmb machinelearningpredictionmodelofwaitlistoutcomesinpatientswithprimarysclerosingcholangitis
AT mamathabhatmdphd machinelearningpredictionmodelofwaitlistoutcomesinpatientswithprimarysclerosingcholangitis