Michael O Killian1,2, Seyedeh Neelufar Payrovnaziri3, Dipankar Gupta4,5, Dev Desai6, Zhe He3. 1. College of Social Work, Florida State University, Florida, USA. 2. College of Medicine, Florida State University, Florida, USA. 3. School of Information, College of Communication and Information, Florida State University, Florida, USA. 4. Congenital Heart Center, Shands Children's Hospital, University of Florida, Florida, USA. 5. Department of Pediatrics, UF College of Medicine, Gainesville, Florida, USA. 6. University of Texas Southwestern School of Medicine, Texas, USA.
Abstract
OBJECTIVES: Prediction of post-transplant health outcomes and identification of key factors remain important issues for pediatric transplant teams and researchers. Outcomes research has generally relied on general linear modeling or similar techniques offering limited predictive validity. Thus far, data-driven modeling and machine learning (ML) approaches have had limited application and success in pediatric transplant outcomes research. The purpose of the current study was to examine ML models predicting post-transplant hospitalization in a sample of pediatric kidney, liver, and heart transplant recipients from a large solid organ transplant program. MATERIALS AND METHODS: Various logistic regression, naive Bayes, support vector machine, and deep learning (DL) methods were used to predict 1-, 3-, and 5-year post-transplant hospitalization using patient and administrative data from a large pediatric organ transplant center. RESULTS: DL models generally outperformed traditional ML models across organtypes and prediction windows with area under the receiver operating characteristic curve values ranging from 0.750 to 0.851. Shapley additive explanations (SHAP) were used to increase the interpretability of DL model results. Various medical, patient, and social variables were identified as salient predictors across organ types. DISCUSSION: Results demonstrate the utility of DL modeling for health outcome prediction with pediatric patients, and its use represents an important development in the prediction of post-transplant outcomes in pediatric transplantation compared to prior research. CONCLUSION: Results point to DL models as potentially useful tools in decision-support systems assisting physicians and transplant teams in identifying patients at a greater risk for poor post-transplant outcomes. Published by Oxford University Press on behalf of the American Medical Informatics Association 2020.
OBJECTIVES: Prediction of post-transplant health outcomes and identification of key factors remain important issues for pediatric transplant teams and researchers. Outcomes research has generally relied on general linear modeling or similar techniques offering limited predictive validity. Thus far, data-driven modeling and machine learning (ML) approaches have had limited application and success in pediatric transplant outcomes research. The purpose of the current study was to examine ML models predicting post-transplant hospitalization in a sample of pediatric kidney, liver, and heart transplant recipients from a large solid organ transplant program. MATERIALS AND METHODS: Various logistic regression, naive Bayes, support vector machine, and deep learning (DL) methods were used to predict 1-, 3-, and 5-year post-transplant hospitalization using patient and administrative data from a large pediatric organ transplant center. RESULTS: DL models generally outperformed traditional ML models across organtypes and prediction windows with area under the receiver operating characteristic curve values ranging from 0.750 to 0.851. Shapley additive explanations (SHAP) were used to increase the interpretability of DL model results. Various medical, patient, and social variables were identified as salient predictors across organ types. DISCUSSION: Results demonstrate the utility of DL modeling for health outcome prediction with pediatric patients, and its use represents an important development in the prediction of post-transplant outcomes in pediatric transplantation compared to prior research. CONCLUSION: Results point to DL models as potentially useful tools in decision-support systems assisting physicians and transplant teams in identifying patients at a greater risk for poor post-transplant outcomes. Published by Oxford University Press on behalf of the American Medical Informatics Association 2020.
Entities:
Keywords:
UNOS; machine learning; pediatric organ transplantation; united network for organ sharing
Authors: Iuliana D Bobanga; Beth A Vogt; Kenneth J Woodside; Devan R Cote; Katherine M Dell; Robert J Cunningham; Kelly A Noon; Edward M Barksdale; Vanessa R Humphreville; Edmund Q Sanchez; James A Schulak Journal: J Pediatr Surg Date: 2015-03-14 Impact factor: 2.545
Authors: D M Dickinson; T H Shearon; J O'Keefe; H-H Wong; C L Berg; J D Rosendale; F L Delmonico; R L Webb; R A Wolfe Journal: Am J Transplant Date: 2006 Impact factor: 8.086
Authors: Emily M Fredericks; John C Magee; Lisa Opipari-Arrigan; Victoria Shieck; Andrew Well; M James Lopez Journal: Pediatr Transplant Date: 2008-02-15
Authors: Eyal Shemesh; Benjamin L Shneider; Jill K Savitzky; Lindsay Arnott; Gabriel E Gondolesi; Nancy R Krieger; Nanda Kerkar; Margret S Magid; Margaret L Stuber; James Schmeidler; Rachel Yehuda; Sukru Emre Journal: Pediatrics Date: 2004-04 Impact factor: 7.124
Authors: Benjamin L Shou; Devina Chatterjee; Joseph W Russel; Alice L Zhou; Isabella S Florissi; Tabatha Lewis; Arjun Verma; Peyman Benharash; Chun Woo Choi Journal: J Cardiovasc Dev Dis Date: 2022-09-19