Caregiver‐reported outcomes of pediatric transplantation: Changes and predictors at 6 months post‐transplant

(1) Background: Post-transplant lymphoproliferative disease (PTLD) is a significant complication of solid organ transplantation (SOT). However, there is lack of consensus in PTLD management. Our aim was to establish a present benchmark for comparison between international centers and between various organ transplant systems and modalities; (2) Methods: A cross-sectional questionnaire of relevant PTLD practices in pediatric transplantation was sent to multidisciplinary teams from 17 European center members of ERN TransplantChild to evaluate the centers’ approach strategies for diagnosis and treatment and how current practices impact a cross-sectional series of PTLD cases; (3) Results: A total of 34 SOT programs from 13 European centers participated. The decision to start preemptive treatment and its guidance was based on both EBV viremia monitoring plus additional laboratory methods and clinical assessment (61%). Among treatment modalities the most common initial practice at diagnosis was to reduce the immunosuppression (61%). A total of 126 PTLD cases were reported during the period 2012–2016. According to their histopathological classification, monomorphic lesions were the most frequent (46%). Graft rejection after PTLD remission was 33%. Of the total cases diagnosed with PTLD, 88% survived; (4) Conclusions: There is still no consensus on prevention and treatment of PTLD, which implies the need to generate evidence. This might successively allow the development of clinical guidelines.

Download Full-text

Machine learning–based prediction of health outcomes in pediatric organ transplantation recipients

JAMIA Open ◽

10.1093/jamiaopen/ooab008 ◽

2021 ◽

Vol 4 (1) ◽

Author(s):

Michael O Killian ◽

Seyedeh Neelufar Payrovnaziri ◽

Dipankar Gupta ◽

Dev Desai ◽

Zhe He

Keyword(s):

Machine Learning ◽

Health Outcomes ◽

Outcomes Research ◽

Characteristic Curve ◽

Organ Transplant ◽

Support Vector ◽

Solid Organ ◽

Post Transplant ◽

Transplant Outcomes ◽

Pediatric Transplantation

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.

Download Full-text