A machine-learning approach to human ex vivo lung perfusion predicts transplantation outcomes and promotes organ utilization

Andrew T Sage; Laura L Donahoe; Alaa A Shamandy; S Hossein Mousavi; Bonnie T Chao; Xuanzi Zhou; Jerome Valero; Sharaniyaa Balachandran; Aadil Ali; Tereza Martinu; George Tomlinson; Lorenzo Del Sorbo; Jonathan C Yeung; Mingyao Liu; Marcelo Cypel; Bo Wang; Shaf Keshavjee

doi:10.1038/s41467-023-40468-7

A machine-learning approach to human ex vivo lung perfusion predicts transplantation outcomes and promotes organ utilization

Nat Commun. 2023 Aug 9;14(1):4810. doi: 10.1038/s41467-023-40468-7.

Authors

Andrew T Sage^{1

2

3

4}, Laura L Donahoe^{2

3}, Alaa A Shamandy^{5

6}, S Hossein Mousavi^{1

2}, Bonnie T Chao^{1

2}, Xuanzi Zhou^{1

2}, Jerome Valero^{1

2}, Sharaniyaa Balachandran², Aadil Ali^{1

2}, Tereza Martinu^{1

2

4}, George Tomlinson⁷, Lorenzo Del Sorbo^{1

8}, Jonathan C Yeung^{1

2

3}, Mingyao Liu^{1

2

3

4}, Marcelo Cypel^{1

2

3

4}, Bo Wang^{9

10

11

12}, Shaf Keshavjee^{13

14

15

16}

Affiliations

¹ Latner Thoracic Research Laboratories, Toronto General Hospital Research Institute, University Health Network, Toronto, ON, Canada.
² Toronto Lung Transplant Program, Ajmera Transplant Centre, University Health Network, Toronto, ON, Canada.
³ Department of Surgery, University of Toronto, Toronto, ON, Canada.
⁴ Institute of Medical Science, University of Toronto, Toronto, ON, Canada.
⁵ Department of Computer Science, University of Toronto, Toronto, ON, Canada.
⁶ Peter Munk Cardiac Centre, University Health Network, Toronto, ON, Canada.
⁷ Department of Medicine, University Health Network, Toronto, ON, Canada.
⁸ Interdepartmental Division of Critical Care Medicine, Medical and Surgical Intensive Care Unit, University Health Network, Toronto, ON, Canada.
⁹ Department of Computer Science, University of Toronto, Toronto, ON, Canada. bo.wang@uhnresearch.ca.
¹⁰ Peter Munk Cardiac Centre, University Health Network, Toronto, ON, Canada. bo.wang@uhnresearch.ca.
¹¹ Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, ON, Canada. bo.wang@uhnresearch.ca.
¹² Vector Institute, Toronto, ON, Canada. bo.wang@uhnresearch.ca.
¹³ Latner Thoracic Research Laboratories, Toronto General Hospital Research Institute, University Health Network, Toronto, ON, Canada. shaf.keshavjee@uhn.ca.
¹⁴ Toronto Lung Transplant Program, Ajmera Transplant Centre, University Health Network, Toronto, ON, Canada. shaf.keshavjee@uhn.ca.
¹⁵ Department of Surgery, University of Toronto, Toronto, ON, Canada. shaf.keshavjee@uhn.ca.
¹⁶ Institute of Medical Science, University of Toronto, Toronto, ON, Canada. shaf.keshavjee@uhn.ca.

Abstract

Ex vivo lung perfusion (EVLP) is a data-intensive platform used for the assessment of isolated lungs outside the body for transplantation; however, the integration of artificial intelligence to rapidly interpret the large constellation of clinical data generated during ex vivo assessment remains an unmet need. We developed a machine-learning model, termed InsighTx, to predict post-transplant outcomes using n = 725 EVLP cases. InsighTx model AUROC (area under the receiver operating characteristic curve) was 79 ± 3%, 75 ± 4%, and 85 ± 3% in training and independent test datasets, respectively. Excellent performance was observed in predicting unsuitable lungs for transplantation (AUROC: 90 ± 4%) and transplants with good outcomes (AUROC: 80 ± 4%). In a retrospective and blinded implementation study by EVLP specialists at our institution, InsighTx increased the likelihood of transplanting suitable donor lungs [odds ratio=13; 95% CI:4-45] and decreased the likelihood of transplanting unsuitable donor lungs [odds ratio=0.4; 95%CI:0.16-0.98]. Herein, we provide strong rationale for the adoption of machine-learning algorithms to optimize EVLP assessments and show that InsighTx could potentially lead to a safe increase in transplantation rates.

MeSH terms

Artificial Intelligence
Humans
Lung / surgery
Lung Transplantation*
Machine Learning
Perfusion
Retrospective Studies
Tissue Donors