Limits...
The International Heart Transplant Survival Algorithm (IHTSA): a new model to improve organ sharing and survival.

Nilsson J, Ohlsson M, Höglund P, Ekmehag B, Koul B, Andersson B - PLoS ONE (2015)

Bottom Line: The IHTSA model showed superior or similar discrimination in all of the cohorts.We show that the IHTSA model can be used to predict both short-term and long-term mortality with high accuracy globally.The model also estimates the expected benefit to the individual patient.

View Article: PubMed Central - PubMed

Affiliation: Department of Clinical Sciences Lund, Cardiothoracic Surgery, Lund University and Skåne University Hospital, Lund, Sweden.

ABSTRACT

Background: Heart transplantation is life saving for patients with end-stage heart disease. However, a number of factors influence how well recipients and donor organs tolerate this procedure. The main objective of this study was to develop and validate a flexible risk model for prediction of survival after heart transplantation using the largest transplant registry in the world.

Methods and findings: We developed a flexible, non-linear artificial neural networks model (IHTSA) and classification and regression tree to comprehensively evaluate the impact of recipient-donor variables on survival over time. We analyzed 56,625 heart-transplanted adult patients, corresponding to 294,719 patient-years. We compared the discrimination power with three existing scoring models, donor risk index (DRI), risk-stratification score (RSS) and index for mortality prediction after cardiac transplantation (IMPACT). The accuracy of the model was excellent (C-index 0.600 [95% CI: 0.595-0.604]) with predicted versus actual 1-year, 5-year and 10-year survival rates of 83.7% versus 82.6%, 71.4%-70.8%, and 54.8%-54.3% in the derivation cohort; 83.7% versus 82.8%, 71.5%-71.1%, and 54.9%-53.8% in the internal validation cohort; and 84.5% versus 84.4%, 72.9%-75.6%, and 57.5%-57.5% in the external validation cohort. The IHTSA model showed superior or similar discrimination in all of the cohorts. The receiver operating characteristic area under the curve to predict one-year mortality was for the IHTSA: 0.650 (95% CI: 0.640-0.655), DRI 0.56 (95% CI: 0.56-0.57), RSS 0.61 (95% CI: 0.60-0.61), and IMPACT 0.61 (0.61-0.62), respectively. The decision-tree showed that recipients matched to a donor younger than 38 years had additional expected median survival time of 2.8 years. Furthermore, the number of suitable donors could be increased by up to 22%.

Conclusions: We show that the IHTSA model can be used to predict both short-term and long-term mortality with high accuracy globally. The model also estimates the expected benefit to the individual patient.

Show MeSH

Related in: MedlinePlus

Validation of the IHTSA variable decision tree.This graph illustrates the difference in observed cumulative mortality for patients belonging to leaf nodes 16, 23, 24, and 127 in the decision tree. The line color corresponds to the leaf node color in Fig. 5. The solid lines show the observed cumulative mortality for transplanted patients in the derivation cohort and dashed lines show the observed cumulative mortality for transplanted patients in the internal validation cohort (estimated with Kaplan-Meier failure function).
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4356583&req=5

pone.0118644.g006: Validation of the IHTSA variable decision tree.This graph illustrates the difference in observed cumulative mortality for patients belonging to leaf nodes 16, 23, 24, and 127 in the decision tree. The line color corresponds to the leaf node color in Fig. 5. The solid lines show the observed cumulative mortality for transplanted patients in the derivation cohort and dashed lines show the observed cumulative mortality for transplanted patients in the internal validation cohort (estimated with Kaplan-Meier failure function).

Mentions: Of the 43 top-ranked variables included in the IHTSA model, only seven remained in the pruned decision tree. As illustrated in Fig. 5, the top-ranked variable, donor age, split the age at 38 years. Recipients matched to a donor younger than 38 years had an additional expected median survival time of 2.8 years. The relative importance of the donor age was 46%, followed by recipient age (18%), diagnosis (15%), donor cause of death (10%), previous transplant (6%), donor gender (3%), diabetes (1.4%), and treatment with mechanical ventilator prior to transplantation (0.5%). Duration of ischemia, body size and blood group were found to be of minor importance. Patients who had a previous transplant and those in need of a mechanical ventilator had the worse prognosis irrespectively of the age of the donor or recipient. The CART analysis identified three cut-offs for donor age—25 year, 38 years, and 50 years—but only one cut-off for recipient age, 57 years. The decision tree was validated by estimating the Kaplan Meier survival for the patients belonging to leaf node 16, 23, 24, and 127. As illustrated in Fig. 6, there was no significantly difference in survival for the DC and IVC in the four groups (p = 0.759, p = 0.861, p = 0.612, p = 0.214, log-rank test), and the trend was concordant with the decision tree.


The International Heart Transplant Survival Algorithm (IHTSA): a new model to improve organ sharing and survival.

Nilsson J, Ohlsson M, Höglund P, Ekmehag B, Koul B, Andersson B - PLoS ONE (2015)

Validation of the IHTSA variable decision tree.This graph illustrates the difference in observed cumulative mortality for patients belonging to leaf nodes 16, 23, 24, and 127 in the decision tree. The line color corresponds to the leaf node color in Fig. 5. The solid lines show the observed cumulative mortality for transplanted patients in the derivation cohort and dashed lines show the observed cumulative mortality for transplanted patients in the internal validation cohort (estimated with Kaplan-Meier failure function).
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4356583&req=5

pone.0118644.g006: Validation of the IHTSA variable decision tree.This graph illustrates the difference in observed cumulative mortality for patients belonging to leaf nodes 16, 23, 24, and 127 in the decision tree. The line color corresponds to the leaf node color in Fig. 5. The solid lines show the observed cumulative mortality for transplanted patients in the derivation cohort and dashed lines show the observed cumulative mortality for transplanted patients in the internal validation cohort (estimated with Kaplan-Meier failure function).
Mentions: Of the 43 top-ranked variables included in the IHTSA model, only seven remained in the pruned decision tree. As illustrated in Fig. 5, the top-ranked variable, donor age, split the age at 38 years. Recipients matched to a donor younger than 38 years had an additional expected median survival time of 2.8 years. The relative importance of the donor age was 46%, followed by recipient age (18%), diagnosis (15%), donor cause of death (10%), previous transplant (6%), donor gender (3%), diabetes (1.4%), and treatment with mechanical ventilator prior to transplantation (0.5%). Duration of ischemia, body size and blood group were found to be of minor importance. Patients who had a previous transplant and those in need of a mechanical ventilator had the worse prognosis irrespectively of the age of the donor or recipient. The CART analysis identified three cut-offs for donor age—25 year, 38 years, and 50 years—but only one cut-off for recipient age, 57 years. The decision tree was validated by estimating the Kaplan Meier survival for the patients belonging to leaf node 16, 23, 24, and 127. As illustrated in Fig. 6, there was no significantly difference in survival for the DC and IVC in the four groups (p = 0.759, p = 0.861, p = 0.612, p = 0.214, log-rank test), and the trend was concordant with the decision tree.

Bottom Line: The IHTSA model showed superior or similar discrimination in all of the cohorts.We show that the IHTSA model can be used to predict both short-term and long-term mortality with high accuracy globally.The model also estimates the expected benefit to the individual patient.

View Article: PubMed Central - PubMed

Affiliation: Department of Clinical Sciences Lund, Cardiothoracic Surgery, Lund University and Skåne University Hospital, Lund, Sweden.

ABSTRACT

Background: Heart transplantation is life saving for patients with end-stage heart disease. However, a number of factors influence how well recipients and donor organs tolerate this procedure. The main objective of this study was to develop and validate a flexible risk model for prediction of survival after heart transplantation using the largest transplant registry in the world.

Methods and findings: We developed a flexible, non-linear artificial neural networks model (IHTSA) and classification and regression tree to comprehensively evaluate the impact of recipient-donor variables on survival over time. We analyzed 56,625 heart-transplanted adult patients, corresponding to 294,719 patient-years. We compared the discrimination power with three existing scoring models, donor risk index (DRI), risk-stratification score (RSS) and index for mortality prediction after cardiac transplantation (IMPACT). The accuracy of the model was excellent (C-index 0.600 [95% CI: 0.595-0.604]) with predicted versus actual 1-year, 5-year and 10-year survival rates of 83.7% versus 82.6%, 71.4%-70.8%, and 54.8%-54.3% in the derivation cohort; 83.7% versus 82.8%, 71.5%-71.1%, and 54.9%-53.8% in the internal validation cohort; and 84.5% versus 84.4%, 72.9%-75.6%, and 57.5%-57.5% in the external validation cohort. The IHTSA model showed superior or similar discrimination in all of the cohorts. The receiver operating characteristic area under the curve to predict one-year mortality was for the IHTSA: 0.650 (95% CI: 0.640-0.655), DRI 0.56 (95% CI: 0.56-0.57), RSS 0.61 (95% CI: 0.60-0.61), and IMPACT 0.61 (0.61-0.62), respectively. The decision-tree showed that recipients matched to a donor younger than 38 years had additional expected median survival time of 2.8 years. Furthermore, the number of suitable donors could be increased by up to 22%.

Conclusions: We show that the IHTSA model can be used to predict both short-term and long-term mortality with high accuracy globally. The model also estimates the expected benefit to the individual patient.

Show MeSH
Related in: MedlinePlus