The International Heart Transplant Survival Algorithm (IHTSA): A New Model to Improve Organ Sharing and Survival

Abstract

BackgroundHeart 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 FindingsWe 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%.ConclusionsWe 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.

Prediction of mortality following pediatric heart transplant using machine learning algorithms

“…We tested three ML algorithms that have been recently used in HTx outcomes research: ANN, CART, and RF . ANNs are designed to mimic biological neural processing and consist of weighted connections between neurons.…”

“…ML has also been proposed to improve prediction of transplant outcomes. Recently, several studies have attempted to improve HTx outcome prediction using ML techniques in adults or combined pediatric and adult populations . Compared to regression‐based modeling approaches, ML algorithms can capture more complex interactions between characteristics, which may result in improved predictions of transplantation outcomes.…”

Role of Depression and Social Isolation at Time of Waitlisting for Survival 8 Years After Heart Transplantation

“…According to the registry of the International Society for Heart and Lung Transplantation (ISHLT), 1‐year survival amounted to 84.5%, and 5‐year survival to 72.5% in 2014,2 with about 10% lower survival rates reported in Europe 3. Several models have been developed to predict survival after HTx based on pretransplant assessments, taking into account up to 43 demographic and medical recipient and donor variables,4, 5, 6 yet excluding psychosocial patient characteristics. The importance of the latter variables has been acknowledged by the ISHLT listing criteria for HTx, which focus primarily on screening for lack of social support in an effort to reduce the risk of adverse outcomes (Class I recommendation, Level of Evidence C) 7…”

Impact of hyperlipidemia on alloimmunity

“…Nor do standard transplant models address preexisting or concomitant health conditions present in the human transplant population that might affect outcomes. Indeed, transplant patients typically suffer from preexisting health conditions that either result from or lead to systemic inflammation such as diabetes, obesity and atherosclerosis (4). Increased inflammation in the recipient could significantly impact responses to alloantigen, modify mechanisms of rejection and negatively impact long-term survival of the transplanted organ.…”