Variables of importance in the Scientific Registry of Transplant Recipients database predictive of heart transplant waitlist mortality

Abstract

The pre-listing variables essential for creating an accurate heart transplant allocation score based on survival are unknown. To identify these we studied mortality of adults on the active heart transplant waiting list in the Scientific Registry of Transplant Recipients database from January 1, 2004-August 31, 2015. There were 33,069 candidates awaiting heart transplantation: 7,681 UNOS Status 1A, 13,027 Status 1B, and 12,361 Status 2. During a median waitlist follow-up of 4.3 months, 5514 candidates died. Variables of importance for waitlist mortality were identified by machine learning using Random Survival Forests. Strong correlates predicting survival were estimated glomerular filtration rate (eGFR), serum albumin, extracorporeal membrane oxygenation, ventricular assist device, mechanical ventilation, peak oxygen capacity, hemodynamics, inotrope support, and type of heart disease with less predictive variables including antiarrhythmic agents, history of stroke, vascular disease, prior malignancy, and prior tobacco use.

Outcome of patients on heart transplant list treated with a continuous-flow left ventricular assist device: Insights from the TRans-Atlantic registry on VAd and TrAnsplant (TRAViATA)

“…Creatinine also emerged as a baseline variable associated with prognosis consistently with other studies, including an extensive analysis of UNOS patients that showed impaired renal function predicted waitlist mortality [9]. It remains unclear how to select patients with considerable renal impairment for CF-LVAD, as opposed to listing directly for a multi-organ transplant.…”

Machine Learning for Integrating Social Determinants in Cardiovascular Disease Prediction Models: A Systematic Review

“…Of the observational studies, data from cohort studies was the most frequent (34 studies), followed by data from electronic medical records (32 studies), surveys (14 studies) and data from open-access repositories of registry or national survey data (7 studies) (e.g. Scientific Registry of Transplant Recipients Registry 37 ). Most of the observational data were structured data (clearly defined data features), while 9 studies included unstructured data (e.g.…”

Statistical performance of 16 posttransplant risk scores in a contemporary cohort of heart transplant recipients

“…The UNOS Thoracic Committee recently decided to expand the collection of data to capture more prognostic markers in order to improve risk stratification. Second, important predictive variables like serum albumin were missing in about half of the cohort, limiting the sample size of the validation cohort for the score 36 . Third, several scores were developed 10‐20 years ago, when the posttransplant prognosis was less favorable and pretransplant ventricular assist devices less frequent than in the current period 4 .…”

“…Sixth, more complex statistical models may improve risk stratification. The analysis of complex interactions between predictive variables may improve risk stratification (eg, donor age and ischemic time) 36‐38 . However, different machine learning approaches failed to improve the discrimination ability of predictive models 35 .…”