1
|
Tian D, Yan HJ, Huang H, Zuo YJ, Liu MZ, Zhao J, Wu B, Shi LZ, Chen JY. Machine Learning-Based Prognostic Model for Patients After Lung Transplantation. JAMA Netw Open 2023; 6:e2312022. [PMID: 37145595 PMCID: PMC10163387 DOI: 10.1001/jamanetworkopen.2023.12022] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/21/2022] [Accepted: 03/23/2023] [Indexed: 05/06/2023] Open
Abstract
Importance Although numerous prognostic factors have been found for patients after lung transplantation (LTx) over the years, an accurate prognostic tool for LTx recipients remains unavailable. Objective To develop and validate a prognostic model for predicting overall survival in patients after LTx using random survival forests (RSF), a machine learning algorithm. Design, Setting, and Participants This retrospective prognostic study included patients who underwent LTx between January 2017 and December 2020. The LTx recipients were randomly assigned to training and test sets in accordance with a ratio of 7:3. Feature selection was performed using variable importance with bootstrapping resampling. The prognostic model was fitted using the RSF algorithm, and a Cox regression model was set as a benchmark. The integrated area under the curve (iAUC) and integrated Brier score (iBS) were applied to assess model performance in the test set. Data were analyzed from January 2017 to December 2019. Main Outcomes And Measures Overall survival in patients after LTx. Results A total of 504 patients were eligible for this study, consisting of 353 patients in the training set (mean [SD] age, 55.03 [12.78] years; 235 [66.6%] male patients) and 151 patients in the test set (mean [SD] age, 56.79 [10.95] years; 99 [65.6%] male patients). According to the variable importance of each factor, 16 were selected for the final RSF model, and postoperative extracorporeal membrane oxygenation time was identified as the most valuable factor. The RSF model had excellent performance with an iAUC of 0.879 (95% CI, 0.832-0.921) and an iBS of 0.130 (95% CI, 0.106-0.154). The Cox regression model fitted by the same modeling factors to the RSF model was significantly inferior to the RSF model with an iAUC of 0.658 (95% CI, 0.572-0.747; P < .001) and an iBS of 0.205 (95% CI, 0.176-0.233; P < .001). According to the RSF model predictions, the patients after LTx were stratified into 2 prognostic groups displaying significant difference, with mean overall survival of 52.91 months (95% CI, 48.51-57.32) and 14.83 months (95% CI, 9.44-20.22; log-rank P < .001), respectively. Conclusions and relevance In this prognostic study, the findings first demonstrated that RSF could provide more accurate overall survival prediction and remarkable prognostic stratification than the Cox regression model for patients after LTx.
Collapse
Affiliation(s)
- Dong Tian
- Department of Thoracic Surgery, West China Hospital, Sichuan University, Chengdu, China
- Wuxi Lung Transplant Center, Wuxi People’s Hospital affiliated to Nanjing Medical University, Wuxi, China
| | - Hao-Ji Yan
- Department of General Thoracic Surgery, Juntendo University School of Medicine, Tokyo, Japan
| | - Heng Huang
- Department of Thoracic Surgery, West China Hospital, Sichuan University, Chengdu, China
| | - Yu-Jie Zuo
- Department of Clinical Medicine, North Sichuan Medical College, Nanchong, China
| | - Ming-Zhao Liu
- Wuxi Lung Transplant Center, Wuxi People’s Hospital affiliated to Nanjing Medical University, Wuxi, China
| | - Jin Zhao
- Wuxi Lung Transplant Center, Wuxi People’s Hospital affiliated to Nanjing Medical University, Wuxi, China
| | - Bo Wu
- Wuxi Lung Transplant Center, Wuxi People’s Hospital affiliated to Nanjing Medical University, Wuxi, China
| | - Ling-Zhi Shi
- Wuxi Lung Transplant Center, Wuxi People’s Hospital affiliated to Nanjing Medical University, Wuxi, China
| | - Jing-Yu Chen
- Wuxi Lung Transplant Center, Wuxi People’s Hospital affiliated to Nanjing Medical University, Wuxi, China
| |
Collapse
|
2
|
Connor AA, Huang HJ, Mobley CM, Graviss EA, Nguyen DT, Goodarzi A, Saharia A, Yau S, Hobeika MJ, Suarez EE, Moaddab M, Brombosz EW, Moore LW, Yi SG, Gaber AO, Ghobrial RM. Progress in Combined Liver-lung Transplantation at a Single Center. Transplant Direct 2023; 9:e1482. [PMID: 37096152 PMCID: PMC10121433 DOI: 10.1097/txd.0000000000001482] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2023] [Accepted: 03/03/2023] [Indexed: 04/26/2023] Open
Abstract
Combined liver-lung transplantation is an uncommon, although vital, procedure for patients with simultaneous end-stage lung and liver disease. The utility of lung-liver transplant has been questioned because of initial poor survival outcomes, particularly when compared with liver-alone transplant recipients. Methods A single-center, retrospective review of the medical records of 19 adult lung-liver transplant recipients was conducted, comparing early recipients (2009-2014) with a recent cohort (2015-2021). Patients were also compared with the center's single lung or liver transplant recipients. Results Recent lung-liver recipients were older (P = 0.004), had a higher body mass index (P = 0.03), and were less likely to have ascites (P = 0.02), reflecting changes in the etiologies of lung and liver disease. Liver cold ischemia time was longer in the modern cohort (P = 0.004), and patients had a longer posttransplant length of hospitalization (P = 0.048). Overall survival was not statistically different between the 2 eras studied (P = 0.61), although 1-y survival was higher in the more recent group (90.9% versus 62.5%). Overall survival after lung-liver transplant was equivalent to lung-alone recipients and was significantly lower than liver-alone recipients (5-y survival: 52%, 51%, and 75%, respectively). Lung-liver recipient mortality was primarily driven by deaths within 6 mo of transplant due to infection and sepsis. Graft failure was not significantly different (liver: P = 0.06; lung: P = 0.74). Conclusions The severity of illness in lung-liver recipients combined with the infrequency of the procedure supports its continued use. However, particular attention should be paid to patient selection, immunosuppression, and prophylaxis against infection to ensure proper utilization of scarce donor organs.
Collapse
Affiliation(s)
- Ashton A. Connor
- JC Walter Jr Transplant Center, Houston Methodist Hospital, Houston, TX
- Department of Surgery, Houston Methodist Hospital, Houston, TX
| | - Howard J. Huang
- JC Walter Jr Transplant Center, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Weill Cornell Medical College, New York, NY
| | - Constance M. Mobley
- JC Walter Jr Transplant Center, Houston Methodist Hospital, Houston, TX
- Department of Surgery, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Weill Cornell Medical College, New York, NY
| | - Edward A. Graviss
- Department of Surgery, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Weill Cornell Medical College, New York, NY
- Department of Pathology and Genomic Medicine, Houston Methodist Hospital, Houston, TX
| | - Duc T. Nguyen
- Department of Pathology and Genomic Medicine, Houston Methodist Hospital, Houston, TX
| | - Ahmad Goodarzi
- Department of Medicine, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Weill Cornell Medical College, New York, NY
| | - Ashish Saharia
- JC Walter Jr Transplant Center, Houston Methodist Hospital, Houston, TX
- Department of Surgery, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Weill Cornell Medical College, New York, NY
| | - Simon Yau
- Department of Medicine, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Weill Cornell Medical College, New York, NY
| | - Mark J. Hobeika
- JC Walter Jr Transplant Center, Houston Methodist Hospital, Houston, TX
- Department of Surgery, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Weill Cornell Medical College, New York, NY
| | - Erik E. Suarez
- Department of Medicine, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Weill Cornell Medical College, New York, NY
| | - Mozhgon Moaddab
- JC Walter Jr Transplant Center, Houston Methodist Hospital, Houston, TX
- Department of Pharmacy, Houston Methodist Hospital, Houston, TX
| | | | - Linda W. Moore
- Department of Surgery, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Weill Cornell Medical College, New York, NY
| | - Stephanie G. Yi
- JC Walter Jr Transplant Center, Houston Methodist Hospital, Houston, TX
- Department of Surgery, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Weill Cornell Medical College, New York, NY
| | - A. Osama Gaber
- JC Walter Jr Transplant Center, Houston Methodist Hospital, Houston, TX
- Department of Surgery, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Weill Cornell Medical College, New York, NY
| | - Rafik Mark Ghobrial
- JC Walter Jr Transplant Center, Houston Methodist Hospital, Houston, TX
- Department of Surgery, Houston Methodist Hospital, Houston, TX
- Department of Medicine, Weill Cornell Medical College, New York, NY
| |
Collapse
|
3
|
Brahmbhatt JM, Wai TH, Goss CH, Lease ED, Merlo CA, Kapnadak SG, Ramos KJ. The Lung Allocation Score and Other Available Models Lack Predictive Accuracy for Post-Lung Transplant Survival. J Heart Lung Transplant 2022; 41:1063-1074. [PMID: 35690561 PMCID: PMC9329266 DOI: 10.1016/j.healun.2022.05.008] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2021] [Revised: 04/29/2022] [Accepted: 05/12/2022] [Indexed: 11/26/2022] Open
Abstract
BACKGROUND Improved predictive models are needed in lung transplantation in the setting of a proposed allocation system that incorporates longer-term post-transplant survival in the United States. Allocation systems require accurate mortality predictions to justly allocate organs. METHODS Utilizing the United Network for Organ Sharing database (2005-2017), we fit models to predict 1-year mortality based on the Lung Allocation Score (LAS), the Chan, et al, 2019 model, a novel "clinician" model (a priori clinician selection of pre-transplant covariates), and two machine learning models (Least Absolute Shrinkage and Selection Operator; LASSO and Random Forests) for predicting 1-year and 3-year post-transplant mortality. We compared predictive accuracy among models. We evaluated the calibration of models by comparing average predicted probability vs observed outcome per decile. We repeated analyses fit for 3-year mortality, disease category, including donor covariates, and LAS era. RESULTS The area under the cure for all models was low, ranging from 0.55 to 0.62. All exhibited reasonable negative predictive values (0.87-0.90), but the positive predictive value for was poor (all <0.25). Evaluating LAS calibration found 1-year post-transplant estimates consistently overestimated risk of mortality, with greater differences in higher deciles. LASSO, Random Forests, and clinician models showed no improvement when evaluated by disease category or with the addition of donor covariates and performed worse for 3-year outcomes. CONCLUSIONS The LAS overestimated patients' risk of post-transplant death, thus underestimating transplant benefit in the sickest candidates. Novel models based on pre-transplant recipient covariates failed to improve prediction. There should be wariness in post-transplant survival predictions from available models.
Collapse
|
5
|
Ungerman E, Khoche S, Subramani S, Bartels S, Fritz AV, Martin AK, Subramanian H, Devarajan J, Knight J, Boisen ML, Gelzinis TA. The Year in Cardiothoracic Transplantation Anesthesia: Selected Highlights from 2019. J Cardiothorac Vasc Anesth 2020; 34:2889-2905. [PMID: 32782193 DOI: 10.1053/j.jvca.2020.06.026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/01/2020] [Accepted: 06/08/2020] [Indexed: 11/11/2022]
Abstract
The highlights in cardiothoracic transplantation focus on the recent research pertaining to heart and lung transplantation, including expansion of the donor pool, the optimization of donors and recipients, the use of mechanical support, the perioperative and long-term outcomes in these patient populations, and the use of transthoracic echocardiography to diagnose rejection.
Collapse
Affiliation(s)
- Elizabeth Ungerman
- Department of Anesthesiology and Perioperative Medicine, University of Pittsburgh, Pittsburgh, PA
| | - Swapnil Khoche
- Department of Anesthesiology, University of California San Diego, San Diego, CA
| | - Sudhakar Subramani
- Department of Anesthesiology, University of Iowa Hospitals and Clinics, Iowa City, IA
| | - Steven Bartels
- Anesthesiology Institute, Cleveland Clinic, Cleveland, OH
| | - Ashley Virginia Fritz
- Division of Cardiovascular and Thoracic Anesthesiology, Mayo Clinic Florida, Jacksonville, FL
| | - Archer Kilbourne Martin
- Division of Cardiovascular and Thoracic Anesthesiology, Mayo Clinic Florida, Jacksonville, FL
| | - Harikesh Subramanian
- Department of Anesthesiology and Perioperative Medicine, University of Pittsburgh, Pittsburgh, PA
| | | | - Joshua Knight
- Department of Anesthesiology and Perioperative Medicine, University of Pittsburgh, Pittsburgh, PA
| | - Michael L Boisen
- Department of Anesthesiology and Perioperative Medicine, University of Pittsburgh, Pittsburgh, PA
| | - Theresa A Gelzinis
- Department of Anesthesiology and Perioperative Medicine, University of Pittsburgh, Pittsburgh, PA.
| |
Collapse
|