Creation of a Quantitative Recipient Risk Index for Mortality Prediction After Cardiac Transplantation (IMPACT)

Survival machine learning methods for mortality prediction after heart transplantation in the contemporary era

Although prediction models for heart transplantation outcomes have been developed previously, a comprehensive benchmarking of survival machine learning methods for mortality prognosis in the most contemporary era of heart transplants following the 2018 donor heart allocation policy change is warranted. This study assessed seven statistical and machine learning algorithms-Lasso, Ridge, Elastic Net, Cox Gradient Boost, Extreme Gradient Boost Linear, Extreme Gradient Boost Tree, and Random Survival Forests in a post-policy cohort of 7,160 adult heart-only transplant recipients in the Scientific Registry of Transplant Recipients (SRTR) database who received their first transplant on or after October 18, 2018. A cross-validation framework was designed in mlr. Model performance was also compared in a seasonally-matched pre-policy cohort. In the post-policy cohort, Random Survival Forests and Cox Gradient Boost had the highest performances with C-indices of 0.628 and 0.627. The relative importance of some predictive variables differed between the pre-policy and post-policy cohorts, such as the absence of ECMO in the post-policy cohort. Survival machine learning models provide reasonable prediction of 1-year posttransplant mortality outcomes and continual updating of prediction models is warranted in the contemporary era.

Fifteen-year experience of direct bridge with venoarterial extracorporeal membrane oxygenation to heart transplantation

Objective

The study objective was to evaluate outcomes of patients directly bridged with venoarterial extracorporeal membrane oxygenation to heart transplantation.

Methods

A single-center retrospective study was performed on 1152 adult patients undergoing isolated cardiac transplantation between January 2007 and December 2021. Among these, patients bridged with an extracorporeal membrane oxygenation to transplantation (extracorporeal membrane oxygenation group, n = 317) were compared with standard cohorts of patients (no extracorporeal membrane oxygenation group, n = 835). A period analysis (Era 1, 2007-2013, vs Era 2, 2014-2021) was performed.

Results

Median duration of extracorporeal membrane oxygenation support before transplantation in the extracorporeal membrane oxygenation group was 8 days. Recipients of extracorporeal membrane oxygenation group were younger, with a better renal function and a shorter time on the waiting list. They were allocated to younger donors, with a longer ischemic time. The extracorporeal membrane oxygenation group and no extracorporeal membrane oxygenation group showed similar 1-year and 9-year survivals: 79.2% versus 79.4%, P = .98, and 56.2% versus 53.9%, P = .59, respectively. Period analysis in the extracorporeal membrane oxygenation group showed improved 1- and 9-year survivals in Era 2 compared with Era 1: 82.7% versus 71.1%, P = .021 and 60.4% versus 50.5%, P = .031, respectively. Era 2 was characterized by a higher rate of patients maintained on extracorporeal membrane oxygenation support after transplantation (92% vs 48%, P < .001), inserted mainly by peripheral cannulation (99.51% vs 57%, P < .001), for a shorter median duration after transplantation (5 vs 6 days, P = .033).

Conclusions

Extracorporeal membrane oxygenation as a direct bridge to heart transplantation shows similar outcomes to standard cohorts of patients. In the extracorporeal membrane oxygenation group, the waiting list time is shorter due to the emergency allocation system, and recipients have no evidence of organ dysfunction at the time of transplantation.

Donation After Circulatory Death Cardiac Recovery Technique: Single-Center Observational Outcomes

BACKGROUND

Recovery of hearts from donation after circulatory death donors has been performed either with direct procurement and perfusion (DPP) using the TransMedics Organ Care System or with normothermic regional perfusion (NRP) with subsequent cold storage. It remains unclear which of these 2 strategies yields optimal posttransplant outcomes.

METHODS

All heart transplant recipients from donors after circulatory death donors at the Vanderbilt University Medical Center (Nashville, TN) were reviewed (February 2020 to January 2023). Recipients were stratified into an NRP or DPP cohort. All DPP recoveries were performed using the TransMedics Organ Care System. The key outcome was severe primary graft dysfunction at 24 hours, defined by the need for postoperative extracorporeal membrane oxygenation.

RESULTS

A total of 118 hearts were transplanted (NRP, 87; DPP, 31). Donors recovered using NRP were younger (25 years [interquartile range {IQR}, 21-31 years] vs 31 years [IQR, 24-37 years]; P = .008) and had shorter distance traveled (292 miles [158-516 miles] vs 449 miles [IQR, 248-635 miles]; P = .02). Recipient preoperative risk factors were similar between the groups. There was no difference in the incidence of severe primary graft dysfunction at 24 hours (NRP, 5.8%; and DPP, 12.9%; P = .24). However, ejection fraction at 7 days after transplantation was higher in the NRP group (65% [IQR, 60%-65%] vs 60% [IQR, 60%-68%]; P = .005). There was no difference in inotrope scores at 24 hours (P = 1.00) or 72 hours (P = .87) or in 30-day (NRP, 95% vs DPP, 97%; P = .75) and 1-year (NRP, 94% vs DPP, 86%; P = .19) survival.

CONCLUSIONS

NRP and DPP strategies for recovery of cardiac allografts yield comparable early allograft outcomes. Future studies are needed to confirm these findings in larger prospective cohorts.

The IMPACT Score: Does Sex Matter?

OBJECTIVE

The Index for Mortality Prediction After Cardiac Transplantation (IMPACT) score is a quantitative risk index that predicts 1-year mortality risk, derived from United Network for Organ Sharing data in which women are underrepresented. The validity of the IMPACT score in 1-year mortality risk after OHT in women is unknown. The objective of this study was to assess differences in score performance by sex. We hypothesized that the IMPACT score is a poor predictor of 1-year mortality risk after orthotopic heart transplantation (OHT) in women.

DESIGN

In this external validation study, demographic and clinical characteristics were compared by sex. The IMPACT score was calculated and regression models were constructed for the entire sample and stratified by sex. Model discrimination was assessed with the area under the receiver operating characteristic curve, and calibration was assessed graphically.

PARTICIPANTS

Patients 18 years and older who were first-time single OHT recipients from the International Society for Heart and Lung Transplantation registry from 2009 to 2018.

MEASUREMENTS AND MAIN RESULTS

For 1-year mortality, the area under the receiver operating characteristic curve (95% confidence interval) for the full sample was 0.59 (0.57-0.60): 0.58 (0.55-0.61) for women and 0.59 (0.58-0.61) for men. The 1-year mortality was 9.4% in the overall cohort, with no difference in mortality by sex (9.0% v 9.6% women v men, p = 0.22).

CONCLUSIONS

The IMPACT score exhibited poor discrimination and calibration in the International Society for Heart and Lung Transplantation 2009-2019 cohort, overall and by sex. There was no difference in 1-year mortality between women and men.

Recipient functional status impacts on short and long-term intestinal transplant outcomes in United States adults

BACKGROUND

Recipient functional status prior to transplantation has been found to impact post-transplant outcomes in heart, liver and kidney transplants. However, information on how functional status, before and after transplant impacts post-transplant survival outcomes is lacking.

AIM

To investigate the impact of recipient functional status on short and long term intestinal transplant outcomes in United States adults.

METHODS

We conducted a retrospective cohort study on 1254 adults who underwent first-time intestinal transplantation from 2005 to 2022. The primary outcome was mortality. Using the Karnofsky Performance Status, functional impairment was categorized as severe, moderate and normal. Analyses were conducted using Kaplan-Meier curves and multivariable Cox regression.

RESULTS

The median age was 41 years, majority (53.4%) were women. Severe impairment was present in 28.3% of recipients. The median survival time was 906.6 days. The median survival time was 1331 and 560 days for patients with normal and severe functional impairment respectively. Recipients with severe impairment had a 56% higher risk of mortality at one year [Hazard ratio (HR) = 1.56; 95%CI: 1.23-1.98; P < 0.001] and 58% at five years (HR = 1.58; 95%CI: 1.24-2.00; P < 0.001) compared to patients with no functional impairment. Recipients with worse functional status after transplant also had poor survival outcomes.

CONCLUSION

Pre- and post-transplant recipient functional status is an important prognostic indicator for short- and long-term intestinal transplant outcomes.

The Utility of the Vasoactive-Inotropic Score and Its Nomogram in Guiding Postoperative Management in Heart Transplant Recipients

Background

In the early postoperative stage after heart transplantation, there is a lack of predictive tools to guide postoperative management. Whether the vasoactive-inotropic score (VIS) can aid this prediction is not well illustrated.

Methods

In total, 325 adult patients who underwent heart transplantation at our center between January 2015 and December 2018 were included. The maximum VIS (VISmax) within 24 h postoperatively was calculated. The Kaplan-Meier method was used for survival analysis. A logistic regression model was established to determine independent risk factors and to develop a nomogram for a composite severe adverse outcome combining early mortality and morbidity.

Results

VISmax was significantly associated with extensive early outcomes such as early death, renal injury, cardiac reoperation and mechanical circulatory support in a grade-dependent manner, and also predicted 90-day and 1-year survival (p < 0.05). A VIS-based nomogram for the severe adverse outcome was developed that included VISmax, preoperative advanced heart failure treatment, hemoglobin and serum creatinine. The nomogram was well calibrated (Hosmer-Lemeshow p = 0.424) with moderate to strong discrimination (C-index = 0.745) and good clinical utility.

Conclusion

VISmax is a valuable prognostic index in heart transplantation. In the early post-transplant stage, this VIS-based nomogram can easily aid intensive care clinicians in inferring recipient status and guiding postoperative management.

Importance of Transplant Era on Post-Heart Transplant Predictive Models: A UNOS Cohort Analysis

BACKGROUND

The application of posttransplant predictive models is limited by their poor statistical performance. Neglecting the dynamic evolution of demographics and medical practice over time may be a key issue.

OBJECTIVES

Our objective was to develop and validate era-specific predictive models to assess whether these models could improve risk stratification compared to non-era-specific models.

METHODS

We analyzed the United Network for Organ Sharing (UNOS) database including first noncombined heart transplantations (2001-2018, divided into four transplant eras: 2001-2005, 2006-2010, 2011-2015, 2016-2018). The endpoint was death or retransplantation during the 1st-year posttransplant. We analyzed the dynamic evolution of major predictive variables over time and developed era-specific models using logistic regression. We then performed a multiparametric evaluation of the statistical performance of era-specific models and compared them to non-era-specific models in 1000 bootstrap samples (derivation set, 2/3; test set, 1/3).

RESULTS

A total of 34 738 patients were included, 3670 patients (10.5%) met the composite endpoint. We found a significant impact of transplant era on baseline characteristics of donors and recipients, medical practice, and posttransplant predictive models, including significant interaction between transplant year and major predictive variables (total serum bilirubin, recipient age, recipient diabetes, previous cardiac surgery). Although the discrimination of all models remained low, era-specific models significantly outperformed the statistical performance of non-era-specific models in most samples, particularly concerning discrimination and calibration.

CONCLUSIONS

Era-specific models achieved better statistical performance than non-era-specific models. A regular update of predictive models may be considered if they were to be applied for clinical decision-making and allograft allocation.

Outcomes in Heart Transplant Recipients by Bridge to Transplant Strategy When Using the SherpaPak Cardiac Transport System

The last several years have seen a rise in use of mechanical circulatory support (MCS) to bridge heart transplant recipients. A controlled hypothermic organ preservation system, the SherpaPak Cardiac Transport System (SCTS), was introduced in 2018 and has grown in utilization with reports of improved posttransplant outcomes. The Global Utilization And Registry Database for Improved heArt preservatioN (GUARDIAN)-Heart registry is an international, multicenter registry assessing outcomes after transplant using the SCTS. This analysis examines outcomes in recipients bridged with various MCS devices in the GUARDIAN-Heart Registry. A total of 422 recipients with donor hearts transported using SCTS were included and identified. Durable ventricular assist devices (VADs) were used exclusively in 179 recipients, temporary VADs or intra-aortic balloon pump (IABP) in 197, and extracorporeal membrane oxygenation (ECMO) in 14 recipients. Average ischemic times were over 3.5 hours in all cohorts. Severe primary graft dysfunction (PGD) posttransplant increased across groups (4.5% VAD, 5.1% temporary support, 21.4% ECMO), whereas intensive care unit (ICU) length of stay (18.2 days) and total hospital stay (39.4 days) was longer in the ECMO cohort than the VAD and IABP groups. A comparison of outcomes of MCS bridging in SCTS versus traditional ice revealed significantly lower rates of both moderate/severe right ventricular (RV) dysfunction and severe PGD in the SCTS cohort; however, upon propensity matching only the reductions in moderate/severe RV dysfunction were statistically significant. Use of SCTS in transplant recipients with various bridging strategies results in excellent outcomes.

Early Outcomes in Patients With LVAD Undergoing Heart Transplant via Use of the SherpaPak Cardiac Transport System

BACKGROUND

Heart transplant (HT) in recipients with left ventricular assist devices (LVADs) is associated with poor early post-HT outcomes, including primary graft dysfunction (PGD). As complicated heart explants in recipients with LVADs may produce longer ischemic times, innovations in donor heart preservation may yield improved post-HT outcomes. The SherpaPak Cardiac Transport System is an organ preservation technology that maintains donor heart temperatures between 4 °C and 8 °C, which may minimize ischemic and cold-induced graft injuries. This analysis sought to identify whether the use of SherpaPak versus traditional cold storage was associated with differential outcomes among patients with durable LVAD undergoing HT.

METHODS

Global Utilization and Registry Database for Improved Heart Preservation-Heart (NCT04141605) is a multicenter registry assessing post-HT outcomes comparing 2 methods of donor heart preservation: SherpaPak versus traditional cold storage. A retrospective review of all patients with durable LVAD who underwent HT was performed. Outcomes assessed included rates of PGD, post-HT mechanical circulatory support use, and 30-day and 1-year survival.

RESULTS

SherpaPak (n=149) and traditional cold storage (n=178) patients had similar baseline characteristics. SherpaPak use was associated with reduced PGD (adjusted odds ratio, 0.56 [95% CI, 0.32-0.99]; P=0.045) and severe PGD (adjusted odds ratio, 0.31 [95% CI, 0.13-0.75]; P=0.009), despite an increased total ischemic time in the SherpaPak group. Propensity matched analysis also noted a trend toward reduced intensive care unit (SherpaPak 7.5±6.4 days versus traditional cold storage 11.3±18.8 days; P=0.09) and hospital (SherpaPak 20.5±11.9 days versus traditional cold storage 28.7±37.0 days; P=0.06) lengths of stay. The 30-day and 1-year survival was similar between groups.

CONCLUSIONS

SherpaPak use was associated with improved early post-HT outcomes among patients with LVAD undergoing HT. This innovation in preservation technology may be an option for HT candidates at increased risk for PGD.

REGISTRATION

URL: https://www.clinicaltrials.gov; Unique identifier: NCT04141605.

Artificial Intelligence Approaches for Predicting the Risks of Durable Mechanical Circulatory Support Therapy and Cardiac Transplantation

Background: The use of AI-driven technologies in probing big data to generate better risk prediction models has been an ongoing and expanding area of investigation. The AI-driven models may perform better as compared to linear models; however, more investigations are needed in this area to refine their predictability and applicability to the field of durable MCS and cardiac transplantation. Methods: A literature review was carried out using Google Scholar/PubMed from 2000 to 2023. Results: This review defines the knowledge gaps and describes different AI-driven approaches that may be used to further our understanding. Conclusions: The limitations of current models are due to missing data, data imbalances, and the uneven distribution of variables in the datasets from which the models are derived. There is an urgent need for predictive models that can integrate a large number of clinical variables from multicenter data to account for the variability in patient characteristics that influence patient selection, outcomes, and survival for both durable MCS and HT; this may be fulfilled by AI-driven risk prediction models.

Prognosis after heart transplant in patients with hypertrophic and restrictive cardiomyopathy. A nationwide registry analysis

INTRODUCTION AND OBJECTIVES

Posttransplant outcomes among recipients with a diagnosis of hypertrophic cardiomyopathy (HCM) or restrictive cardiomyopathy (RCM) remain controversial.

METHODS

Retrospective analysis of a nationwide registry of first-time recipients undergoing isolated heart transplant between 1984 and 2021. One-year and 5-year mortality in recipients with HCM and RCM were compared with those with dilated cardiomyopathy (DCM).

RESULTS

We included 3703 patients (3112 DCM; 331 HCM; 260 RCM) with a median follow-up of 5.0 [3.1-5.0] years. Compared with DCM, the adjusted 1-year mortality risk was: HCM: HR, 1.38; 95%CI, 1.07-1.78; P=.01, RCM: HR, 1.48; 95%CI, 1.14-1.93; P=.003. The adjusted 5-year mortality risk was: HCM: HR, 1.17; 95%CI, 0.93-1.47; P=.18; RCM: HR, 1.52; 95%CI, 1.22-1.89; P<.001. Over the last 20 years, the RCM group showed significant improvement in 1-year survival (adjusted R2=0.95) and 5-year survival (R2=0.88); the HCM group showed enhanced the 5-year survival (R2=0.59), but the 1-year survival remained stable (R2=0.16).

CONCLUSIONS

Both RCM and HCM were linked to a less favorable early posttransplant prognosis compared with DCM. However, at the 5-year mark, this unfavorable difference was evident only for RCM. Notably, a substantial temporal enhancement in both early and late mortality was observed for RCM, while for HCM, this improvement was mainly evident in late mortality.

Development and validation of mortality prediction models for heart transplantation using nutrition-related indicators: a single-center study from China

Objective

We sought to develop and validate a mortality prediction model for heart transplantation (HT) using nutrition-related indicators, which clinicians could use to identify patients at high risk of death after HT.

Method

The model was developed for and validated in adult participants in China who received HT between 1 January 2015 and 31 December 2020. 428 subjects were enrolled in the study and randomly divided into derivation and validation cohorts at a ratio of 7:3. The likelihood-ratio test based on Akaike information was used to select indicators and develop the prediction model. The performance of models was assessed and validated by area under the curve (AUC), C-index, calibration curves, net reclassification index, and integrated discrimination improvement.

Result

The mean (SD) age was 48.67 (12.33) years and mean (SD) nutritional risk index (NRI) was 100.47 (11.89) in the derivation cohort. Mortality after HT developed in 66 of 299 patients in the derivation cohort and 28 of 129 in the validation cohort. Age, NRI, serum creatine, and triglyceride were included in the full model. The AUC of this model was 0.76 and the C statistics was 0.72 (95% CI, 0.67-0.78) in the derivation cohort and 0.71 (95% CI, 0.62-0.81) in the validation cohort. The multivariable model improved integrated discrimination compared with the reduced model that included age and NRI (6.9%; 95% CI, 1.8%-15.1%) and the model which only included variable NRI (14.7%; 95% CI, 7.4%-26.2%) in the derivation cohort. Compared with the model that only included variable NRI, the full model improved categorical net reclassification index both in the derivation cohort (41.8%; 95% CI, 9.9%-58.8%) and validation cohort (60.7%; 95% CI, 9.0%-100.5%).

Conclusion

The proposed model was able to predict mortality after HT and estimate individualized risk of postoperative death. Clinicians could use this model to identify patients at high risk of postoperative death before HT surgery, which would help with targeted preventative therapy to reduce the mortality risk.

Non-inferior outcomes in lower urgency patients transplanted with extended criteria donor hearts

BACKGROUND

Recent work has suggested that outcomes among heart transplant patients listed at the lower-urgency (United Network for Organ Sharing Status 4 or 6) status may not be significantly impacted by donor comorbidities. The purpose of this study was to investigate outcomes of extended criteria donors (ECD) in lower versus higher urgency patients undergoing heart transplantation.

METHODS

The United Network for Organ Sharing (UNOS) database was queried for all adult patients undergoing heart transplantation from October 18, 2018 through December 31, 2021. Patients were stratified by degree of urgency (higher urgency: UNOS 1 or 2 vs lower urgency: UNOS 4 or 6) and receipt of ECD hearts, as defined by donor hearts failing to meet established acceptable use criteria. Outcomes were compared using propensity score matched cohorts.

RESULTS

Among 9,160 patients included, 2,320 (25.4%) were low urgency. ECD hearts were used in 35.5% of higher urgency (HU) patients and 39.2% of lower urgency (LU) patients. While ECD hearts had an impact on survival among high-urgency patients (p < 0.01), there was no difference in 1- and 2-year survival (p > 0.05) found among low urgency patients receiving ECD versus standard hearts. Neither ECDs nor individual ECD criteria were independently associated with mortality in low urgency patients (p > 0.05).

CONCLUSIONS

Post-transplant outcomes among low urgency patients are not adversely affected by receipt of ECD vs. standard hearts. Expanding the available donor pool by optimizing use of ECDs in this population may increase transplant frequency, decrease waitlist morbidity, and improve postoperative outcomes for the transplant community at large.

Predictors of Survival After Heart Transplant in the New Allocation System: A UNOS Database Analysis

Clinical predictors of posttransplant graft loss since the United Network for Organ Sharing (UNOS) heart allocation system change have not been well characterized. Single organ adult heart transplants from the UNOS database were identified (n = 10,252) and divided into a test cohort (n = 6,869, 67%) and validation cohort (n = 3,383, 33%). A Cox regression analysis was performed on the test cohort to identify recipient and donor risk factors for posttransplant graft loss. Based on the risk factors, a score (max 16) was developed to classify patients in the validation cohort into risk groups of low (≤1), mid (2-3), high (≥4) risk. Recipient factors of advanced age, Black race, recipient blood group O, diabetes, etiology of heart failure, renal dysfunction, elevated bilirubin, redo-transplantation, elevated pulmonary artery pressure, transplant with a durable ventricular assist device, or transplant on extracorporeal membrane oxygenation (ECMO) or ventilator were associated with more posttransplant graft loss. Donor factors of ischemic time and donor age were also associated with outcomes. One year graft survival for the low-, mid-, high-risk groups was 94%, 91%, and 85%, respectively. In conclusion, easily obtainable clinical characteristics at time of heart transplant can predict posttransplant outcomes in the current era.

Association between early postoperative hypoalbuminaemia and outcome after orthotopic heart transplantation

OBJECTIVES

In patients undergoing heart transplantation (HTX), preoperative liver impairment and consecutive hypoalbuminaemia are associated with increased mortality. The role of early postoperative hypoalbuminaemia after HTX is unclear. This study investigated the association between early postoperative hypoalbuminaemia and 1-year mortality as well as 'days alive and out of hospital' (DAOH) after HTX.

METHODS

This retrospective cohort study included patients who underwent HTX at the University Hospital Duesseldorf, Germany, between 2010 and 2022. The main exposure was serum albumin concentration at intensive care unit (ICU) arrival. The primary endpoints were mortality and DAOH within 1 year after surgery. Receiver operating characteristic (ROC) curve analysis was performed and logistic and quantile regression models with adjustment for 13 a priori defined clinical risk factors were conducted.

RESULTS

Out of 241 patients screened, 229 were included in the analysis (mean age 55 ± 11 years, 73% male). ROC analysis showed moderate discrimination for 1-year mortality by postoperative serum albumin after HTX [AUC = 0.74; 95% confidence interval (CI): 0.66-0.83]. The cutoff for serum albumin at ICU arrival was 3.0 g/dl. According to multivariate logistic and quantile regression, there were independent associations between hypoalbuminaemia and mortality/DAOH [odds ratio of 4.76 (95% CI: 1.94-11.67) and regression coefficient of -46.97 (95% CI: -83.81 to -10.13)].

CONCLUSIONS

Postoperative hypoalbuminaemia <3.0 g/dl is associated with 1-year mortality and reduced DAOH after HTX and therefore might be used for early postoperative risk re-assessment in clinical practice.

Risk factors for 1-year allograft loss in pediatric heart transplant patients using machine learning: An analysis of the pediatric heart transplant society database

BACKGROUND

Pediatric heart transplant patients are at greatest risk of allograft loss in the first year. We assessed whether machine learning could improve 1-year risk assessment using the Pediatric Heart Transplant Society database.

METHODS

Patients transplanted from 2010 to 2019 were included. The primary outcome was 1-year graft loss free survival. We developed a prediction model using cross-validation, by comparing Cox regression, gradient boosting, and random forests. The modeling strategy with the best discrimination and calibration was applied to fit a final prediction model. We used Shapley additive explanation (SHAP) values to perform variable selection and to estimate effect sizes and importance of individual variables when interpreting the final prediction model.

RESULTS

Cumulative incidence of graft loss or mortality was 7.6%. Random forests had favorable discrimination and calibration compared to Cox proportional hazards with a C-statistic (95% confidence interval [CI]) of 0.74 (0.72, 0.76) versus 0.71 (0.69, 0.73), and closer alignment between predicted and observed risk. SHAP values computed using the final prediction model indicated that the diagnosis of congenital heart disease (CHD) increased 1 year predicted risk of graft loss by 1.7 (i.e., from 7.6% to 9.3%), need for mechanical circulatory support increased predicted risk by 2, and single ventricle CHD increased predicted risk by 1.9. These three predictors, respectively, were also estimated to be the most important among the 15 predictors in the final model.

CONCLUSIONS

Risk prediction models used to facilitate patient selection for pediatric heart transplant can be improved without loss of interpretability using machine learning.

Survival analysis for pediatric heart transplant patients using a novel machine learning algorithm: A UNOS analysis

BACKGROUND

Impact of pretransplantation risk factors on mortality in the first year after heart transplantation remains largely unknown. Using machine learning algorithms, we selected clinically relevant identifiers that could predict 1-year mortality after pediatric heart transplantation.

METHODS

Data were obtained from the United Network for Organ Sharing Database for years 2010-2020 for patients 0-17 years receiving their first heart transplant (N = 4150). Features were selected using subject experts and literature review. Scikit-Learn, Scikit-Survival, and Tensorflow were used. A train:test split of 70:30 was used. N-repeated k-fold validation was performed (N = 5, k = 5). Seven models were tested, Hyperparameter tuning performed using Bayesian optimization and the concordance index (C-index) was used for model assessment.

RESULTS

A C-index above 0.6 for test data was considered acceptable for survival analysis models. C-indices obtained were 0.60 (Cox proportional hazards), 0.61 (Cox with elastic net), 0.64 (gradient boosting), 0.64 (support vector machine), 0.68 (random forest), 0.66 (component gradient boosting), and 0.54 (survival trees). Machine learning models show an improvement over the traditional Cox proportional hazards model, with random forest performing the best on the test set. Analysis of the feature importance for the gradient boosted model found that the top 5 features were the most recent serum total bilirubin, the travel distance from the transplant center, the patient body mass index, the deceased donor terminal Serum glutamic pyruvic transaminase/Alanine transaminase (SGPT/ALT), and the donor PCO2.

CONCLUSIONS

Combination of machine learning and expert-based methodology of selecting predictors of survival for pediatric heart transplantation provides a reasonable prediction of 1- and 3-year survival outcomes. SHapley Additive exPlanations can be an effective tool for modeling and visualizing nonlinear interactions.

Short stature is a risk factor for heart transplant morbidity and mortality

BACKGROUND

Short stature is associated with mortality after cardiac surgery and may increase size mismatch risk among transplant recipients. Yet, stature's impact on heart transplant outcomes is not well-characterized.

METHODS

The Scientific Registry of Transplant Recipients was queried for data on all adult heart transplants in the United States from 2000 to 2022. Recipients were stratified into five cohorts by sex-corrected stature. Morbidity was assessed with Kruskal-Wallis and chi-squared tests. Mortality was analyzed using Kaplan-Meier estimation. Risk factors for mortality were assessed with multivariable Cox regression.

RESULTS

Among 43,420 transplant recipients, 5321 (12.2%) had short stature (females >4'11″ & ≤5'1″; males >5'4″ & ≤5'7″) and 765 (1.8%) had very short stature (females ≤4'11″; males ≤5'4″). Very short stature patients had higher waitlist status (1A and 1), more congenital heart disease, and received more oversized donor hearts than other cohorts (all p < 0.05). Very short stature patients had decreased 30-day, 1-, 5-, and 10-year survival (94.6%, 84.3%, 69.3% and 52.5%, respectively, all p < 0.001), but less acute rejection (p = 0.005) and comparable stroke rates (p = 0.107). On multivariable regression adjusting for congenital heart disease and oversized donor hearts, very short and short stature were associated with 10-year mortality (hazard ratios: 1.40 and 1.12, respectively, both p < 0.005).

CONCLUSIONS

Short stature confers increased mortality risk for heart transplant recipients and merits inclusion in prognostic models.

Heart transplantation as a rescue strategy for patients with refractory electrical storm

AIMS

Heart transplantation (HT) can be proposed as a therapeutic strategy for patients with severe refractory electrical storm (ES). Data in the literature are scarce and based on case reports. We aimed at determining the characteristics and survival of patients transplanted for refractory ES.

METHODS AND RESULTS

Patients registered on HT waiting list during the following days after ES and eventually transplanted, from 2010 to 2021, were retrospectively included in 11 French centres. The primary endpoint was in-hospital mortality. Forty-five patients were included [82% men; 55.0 (47.8-59.3) years old; 42.2% and 26.7% non-ischaemic dilated or ischaemic cardiomyopathies, respectively]. Among them, 42 (93.3%) received amiodarone, 29 received (64.4%) beta blockers, 19 (42.2%) required deep sedation, 22 had (48.9%) mechanical circulatory support, and 9 (20.0%) had radiofrequency catheter ablation. Twenty-two patients (62%) were in cardiogenic shock. Inscription on wait list and transplantation occurred 3.0 (1.0-5.0) days and 9.0 (4.0-14.0) days after ES onset, respectively. After transplantation, 20 patients (44.4%) needed immediate haemodynamic support by extracorporeal membrane oxygenation (ECMO). In-hospital mortality rate was 28.9%. Predictors of in-hospital mortality were serum creatinine/urea levels, need for immediate post-operative ECMO support, post-operative complications, and surgical re-interventions. One-year survival was 68.9%.

CONCLUSION

Electrical storm is a rare indication of HT but may be lifesaving in those patients presenting intractable arrhythmias despite usual care. Most patients can be safely discharged from hospital, although post-operative mortality remains substantial in this context of emergency transplantation. Larger studies are warranted to precisely determine those patients at higher risk of in-hospital mortality.

Heart Transplantation in High-Risk Recipients Employing Donor Marginal Grafts Preserved With Ex-Vivo Perfusion

Extending selection criteria to face donor organ shortage in heart transplantation (HTx) may increase the risk of mortality. Ex-vivo normothermic perfusion (EVP) limits ischemic time allowing assessment of graft function. We investigated the outcome of HTx in 80 high-risk recipients transplanted with marginal donor and EVP-preserved grafts, from 2016 to 2021. The recipients median age was 57 years (range, 13-75), with chronic renal failure in 61%, impaired liver function in 11% and previous cardiac surgery in 90%; 80% were mechanically supported. Median RADIAL score was 3. Mean graft ischemic time was 118 ± 25 min, "out-of-body" time 420 ± 66 min and median cardiopulmonary bypass (CPB) time 228 min (126-416). In-hospital mortality was 11% and ≥moderate primary graft dysfunction 16%. At univariable analysis, CPB time and high central venous pressure were risk factors for mortality. Actuarial survival at 1 and 3 years was 83% ± 4%, and 72% ± 7%, with a median follow-up of 16 months (range 2-43). Recipient and donor ages, pre-HTx extracorporeal life support and intra-aortic balloon pump were risk factors for late mortality. In conclusion, the use of EVP allows extension of the graft pool by recruitment of marginal donors to successfully perform HTx even in high-risk recipients.

Prediction of Outcomes After Heart Transplantation in Pediatric Patients Using National Registry Data: Evaluation of Machine Learning Approaches

BACKGROUND

The prediction of posttransplant health outcomes for pediatric heart transplantation is critical for risk stratification and high-quality posttransplant care.

OBJECTIVE

The purpose of this study was to examine the use of machine learning (ML) models to predict rejection and mortality for pediatric heart transplant recipients.

METHODS

Various ML models were used to predict rejection and mortality at 1, 3, and 5 years after transplantation in pediatric heart transplant recipients using United Network for Organ Sharing data from 1987 to 2019. The variables used for predicting posttransplant outcomes included donor and recipient as well as medical and social factors. We evaluated 7 ML models-extreme gradient boosting (XGBoost), logistic regression, support vector machine, random forest (RF), stochastic gradient descent, multilayer perceptron, and adaptive boosting (AdaBoost)-as well as a deep learning model with 2 hidden layers with 100 neurons and a rectified linear unit (ReLU) activation function followed by batch normalization for each and a classification head with a softmax activation function. We used 10-fold cross-validation to evaluate model performance. Shapley additive explanations (SHAP) values were calculated to estimate the importance of each variable for prediction.

RESULTS

RF and AdaBoost models were the best-performing algorithms for different prediction windows across outcomes. RF outperformed other ML algorithms in predicting 5 of the 6 outcomes (area under the receiver operating characteristic curve [AUROC] 0.664 and 0.706 for 1-year and 3-year rejection, respectively, and AUROC 0.697, 0.758, and 0.763 for 1-year, 3-year, and 5-year mortality, respectively). AdaBoost achieved the best performance for prediction of 5-year rejection (AUROC 0.705).

CONCLUSIONS

This study demonstrates the comparative utility of ML approaches for modeling posttransplant health outcomes using registry data. ML approaches can identify unique risk factors and their complex relationship with outcomes, thereby identifying patients considered to be at risk and informing the transplant community about the potential of these innovative approaches to improve pediatric care after heart transplantation. Future studies are required to translate the information derived from prediction models to optimize counseling, clinical care, and decision-making within pediatric organ transplant centers.

The Ability of Comorbidity Indices to Predict Mortality After Heart Transplantation: A Validation of the Danish Comorbidity Index for Acute Myocardial Infarction, Charlson Comorbidity Index, and Elixhauser Comorbidity Index

Advanced heart failure patients often have comorbidities of prognostic importance. However, whether total pretransplantation comorbidity burden predicts mortality in patients treated with heart transplantation (HTx) is unknown. We used population-based hospital and prescription data to examine the ability of the Danish Comorbidity Index for Acute Myocardial Infarction (DANCAMI), DANCAMI restricted to noncardiovascular diseases, Charlson Comorbidity Index, and Elixhauser Comorbidity Index to predict 30-d, 1-y, 5-y, and 10-y all-cause and cardiovascular mortality after HTx.

Methods

We identified all adult Danish patients with incident HTx from the Scandiatransplant Database between March 1, 1995, and December 31, 2018 (n = 563). We calculated Harrell's C-Statistics to examine discriminatory performance.

Results

The C-Statistic for predicting 1-y all-cause mortality after HTx was 0.58 (95% confidence interval [CI], 0.50-0.65) for a baseline model including age and sex. Adding comorbidity score to the baseline model did not increase the C-Statistics for DANCAMI (0.58; 95% CI, 0.50-0.65), DANCAMI restricted to noncardiovascular diseases (0.57; 95% CI, 0.50-0.64), Charlson Comorbidity Index (0.59; 95% CI, 0.51-0.66), or Elixhauser Comorbidity Index (0.58; 95% CI, 0.51-0.65). The results for 30-d, 5-y, and 10-y all-cause and cardiovascular mortality were consistent.

Conclusions

After accounting for patient age and sex, none of the commonly used comorbidity indices added predictive value to short- or long-term all-cause or cardiovascular mortality after HTx.

Direct Extracorporeal Membrane Oxygenation Bridged Heart Transplantation: The Importance of Multi-Organ Failure

Background and Objectives

Recently, approximately 40% of all heart transplantation (HTx) in South Korea are performed using the direct extracorporeal membrane oxygenation (ECMO) bridging method. We conducted a study to examine the clinical outcome of direct ECMO-bridged HTx and to investigate the impact of multi-organ failure (MOF).

Methods

From June 2014 to September 2022, a total of 96 adult patients who underwent isolated HTx at a single tertiary hospital were included in the study. The patients were sub-grouped into ECMO (n=48) and non-ECMO group (n=48), and the ECMO group was subdivided into awake (n=22) and non-awake (n=26) groups based on mechanical ventilator (MV) dependency. Baseline characteristics, 30-day, and 1-year mortality were analyzed retrospectively.

Results

The 1-year survival rate was significantly lower in the ECMO group (72.9% vs. 95.8%, p=0.002). There was a significant difference in the 30-day survival rate between the awake and non-awake ECMO groups (81.8% vs. 65.4%, p=0.032). In the univariate analysis of logistic regression for 1-year mortality, the odds ratio was 8.5 for ECMO bridged HTx compared to the non-ECMO group, 12.3 in patients who required MV (p=0.003), and 23 with additional hemodialysis (p<0.001).

Conclusions

Patients who required MV in ECMO bridged HTx showed higher preoperative MOF rates and early mortality than those extubated. When considering ECMO bridged HTx, the severity of MOF should be thoroughly investigated, and careful patient selection is necessary.

JM, Shickel B, Rashidi P, Bihorac A, Ahmed MM, Mardini MT. Artificial intelligence guidance of advanced heart failure therapies: A systematic scoping review

Introduction

Artificial intelligence can recognize complex patterns in large datasets. It is a promising technology to advance heart failure practice, as many decisions rely on expert opinions in the absence of high-quality data-driven evidence.

Methods

We searched Embase, Web of Science, and PubMed databases for articles containing "artificial intelligence," "machine learning," or "deep learning" and any of the phrases "heart transplantation," "ventricular assist device," or "cardiogenic shock" from inception until August 2022. We only included original research addressing post heart transplantation (HTx) or mechanical circulatory support (MCS) clinical care. Review and data extraction were performed in accordance with PRISMA-Scr guidelines.

Results

Of 584 unique publications detected, 31 met the inclusion criteria. The majority focused on outcome prediction post HTx (n = 13) and post durable MCS (n = 7), as well as post HTx and MCS management (n = 7, n = 3, respectively). One study addressed temporary mechanical circulatory support. Most studies advocated for rapid integration of AI into clinical practice, acknowledging potential improvements in management guidance and reliability of outcomes prediction. There was a notable paucity of external data validation and integration of multiple data modalities.

Conclusion

Our review showed mounting innovation in AI application in management of MCS and HTx, with the largest evidence showing improved mortality outcome prediction.

Postoperative high-sensitivity troponin T predicts 1-year mortality and days alive and out of hospital after orthotopic heart transplantation

BACKGROUND

Orthotopic heart transplantation (HTX) is the gold standard to treat end-stage heart failure. Numerous risk stratification tools have been developed in the past years. However, their clinical utility is limited by their poor discriminative ability. High sensitivity troponin T (hsTnT) is the most specific biomarker to detect myocardial cell injury. However, its prognostic relevance after HTX is not fully elucidated. Thus, this study evaluated the predictive value of postoperative hsTnT for 1-year survival and days alive and out of hospital (DAOH) after HTX.

METHODS

This retrospective cohort study included patients who underwent HTX at the University Hospital Duesseldorf, Germany between 2011 and 2021. The main exposure was hsTnT concentration at 48 h after HTX. The primary endpoints were mortality and DAOH within 1 year after surgery. Receiver operating characteristic (ROC) curve analysis, logistic regression model and linear regression with adjustment for risk index for mortality prediction after cardiac transplantation (IMPACT) were performed.

RESULTS

Out of 231 patients screened, 212 were included into analysis (mean age 55 ± 11 years, 73% male). One-year mortality was 19.7% (40 patients) and median DAOH was 298 days (229-322). ROC analysis revealed strongest discrimination for mortality by hsTnT at 48 h after HTX [AUC = 0.79 95% CI 0.71-0.87]. According to Youden Index, the cutoff for hsTnT at 48 h and mortality was 1640 ng/l. After adjustment for IMPACT score multivariate logistic and linear regression showed independent associations between hsTnT and mortality/DAOH with odds ratio of 8.10 [95%CI 2.99-21.89] and unstandardized regression coefficient of -1.54 [95%CI -2.02 to -1.06], respectively.

CONCLUSION

Postoperative hsTnT might be suitable as an early prognostic marker after HTX and is independently associated with 1-year mortality and poor DAOH.

Left ventricular assist device bridging to heart transplantation: Comparison of temporary versus durable support

BACKGROUND

Since the revision of the United States heart allocation system, increasing use of mechanical circulatory support has been observed as a means to support acutely ill patients. We sought to compare outcomes between patients bridged to orthotopic heart transplantation (OHT) with either temporary (t-LVAD) or durable left ventricular assist devises (d-LVAD) under the revised system.

METHODS

The United States Organ Network database was queried to identify all adult OHT recipients who were bridged to transplant with either an isolated t-LVAD or d-LVAD from 10/18/2018 to 9/30/2020. The primary outcome was 1-year post-transplant survival. Predictors of mortality were also modeled, and national trends of LVAD bridging were examined across the study period.

RESULTS

About 1,734 OHT recipients were analyzed, 1,580 (91.1%) bridged with d-LVAD and 154 (8.9%) bridged with t-LVAD. At transplant, the t-LVAD cohort had higher total bilirubin levels and greater prevalence of pre-transplant intravenous inotrope usage and mechanical ventilation. Median waitlist time was also shorter for t-LVAD. At 1 year, there was a non-significant trend of increased survival in the t-LVAD cohort (94.8% vs 90.1%; p = 0.06). After risk adjustment, d-LVAD was associated with a 4-fold hazards for 1-year mortality (hazard ratio 3.96, 95% confidence interval 1.42-11.03; p = 0.009). From 2018 to 2021, t-LVAD bridging increased, though d-LVAD remained a more common bridging strategy.

CONCLUSIONS

Since the 2018 allocation change, there has been a steady increase in t-LVAD usage as a bridge to OHT. Overall, patients bridged with these devices appear to have least equivalent 1-year survival compared to those bridged with d-LVAD.

Clinical course of arrhythmogenic right ventricular cardiomyopathy with end-stage heart failure and outcome after heart transplantation

BACKGROUND

Few data exist on the characteristics and outcomes of patients with arrhythmogenic right ventricular cardiomyopathy and advanced heart failure who undergo heart transplantation.

AIM

To explore the pretransplant course and outcomes of patients with arrhythmogenic right ventricular cardiomyopathy after heart transplantation.

METHODS

This observational retrospective monocentric study included all consecutive patients with arrhythmogenic right ventricular cardiomyopathy who underwent heart transplantation during a 13-year period (2006-2019) at Pitié-Salpêtrière University Hospital (Paris).

RESULTS

A total of 23 patients with arrhythmogenic right ventricular cardiomyopathy underwent heart transplantation between 2006 and 2019. The median time from diagnosis to heart transplantation was 9 years, and the median age at transplantation was 50 years. At diagnosis, half of the patients had left ventricular dysfunction, 59% had extensive T-wave inversion and 43% had a history of sustained ventricular tachycardia. Only five patients were involved in intensive sport activity. Indications for heart transplantation were end-stage biventricular dysfunction in 13 patients, end-stage right ventricular heart failure in seven and electrical storm in three. Only three patients had pulmonary hypertension, and half of the patients had atrial arrhythmias. The survival rate 1 year after heart transplantation was 74% (95% confidence interval 53-88%). Eight patients experienced primary graft dysfunction needing extracorporeal membrane oxygenation.

CONCLUSIONS

Patients with arrhythmogenic right ventricular cardiomyopathy who eventually needed heart transplantation mostly exhibited extended disease with biventricular dysfunction at diagnosis. Intensive sport activity did not seem to be a major determinant. Advanced heart failure usually occurred late in the course of the disease. Primary graft dysfunction after heart transplantation was frequent, and should be anticipated. Additional data are needed to identify the optimal timing for heart transplantation and predictors of end-stage heart failure in patients with arrhythmogenic right ventricular cardiomyopathy.

The Clinical Outcomes of Marginal Donor Hearts: A Single Center Experience

BACKGROUND AND OBJECTIVES

Although the shortage of donor is a common problem worldwide, a significant portion of unutilized hearts are classified as marginal donor (MD) hearts. However, research on the correlation between the MD and the prognosis of heart transplantation (HTx) is lacking. This study was conducted to investigate the clinical impact of MD in HTx.

METHODS

Consecutive 73 HTxs during 2014 and 2021 in a tertiary hospital were analyzed. MD was defined as follows; a donor age >55 years, left ventricular ejection fraction <50%, cold ischemic time >240 minutes, or significant cardiac structural problems. Preoperative characteristics and postoperative hemodynamic data, primary graft dysfunction (PGD), and the survival rate were analyzed. Risk stratification by Index for Mortality Prediction after Cardiac Transplantation (IMPACT) score was performed to examine the outcomes according to the recipient state. Each group was sub-divided into 2 risk groups according to the IMPACT score (low <10 vs. high ≥10).

RESULTS

A total of 32 (43.8%) patients received an organ from MDs. Extracorporeal membrane oxygenation was more frequent in the non-MD group (34.4% vs. 70.7, p=0.007) There was no significant difference in PGD, 30-day mortality and long-term survival between groups. In the subgroup analysis, early outcomes did not differ between low- and high-risk groups. However, the long-term survival was better in the low-risk group (p=0.01).

CONCLUSIONS

The outcomes of MD group were not significantly different from non-MD group. Particularly, in low-risk recipient, the MD group showed excellent early and long-term outcomes. These results suggest the usability of selected MD hearts without increasing adverse events.

Machine learning-based prediction of mortality after heart transplantation in adults with congenital heart disease: A UNOS database analysis

BACKGROUND

Machine learning (ML) is increasingly being applied in Cardiology to predict outcomes and assist in clinical decision-making. We sought to develop and validate an ML model for the prediction of mortality after heart transplantation (HT) in adults with congenital heart disease (ACHD).

METHODS

The United Network for Organ Sharing (UNOS) database was queried from 2000 to 2020 for ACHD patients who underwent isolated HT. The study cohort was randomly split into derivation (70%) and validation (30%) datasets that were used to train and test a CatBoost ML model. Feature selection was performed using SHapley Additive exPlanations (SHAP). Recipient, donor, procedural, and post-transplant characteristics were tested for their ability to predict mortality. We additionally used SHAP for explainability analysis, as well as individualized mortality risk assessment.

RESULTS

The study cohort included 1033 recipients (median age 34 years, 61% male). At 1 year after HT, there were 205 deaths (19.9%). Out of a total of 49 variables, 10 were selected as highly predictive of 1-year mortality and were used to train the ML model. Area under the curve (AUC) and predictive accuracy for the 1-year ML model were .80 and 75.2%, respectively, and .69 and 74.2% for the 3-year model, respectively. Based on SHAP analysis, hemodialysis of the recipient post-HT had overall the strongest relative impact on 1-year mortality after HΤ, followed by recipient-estimated glomerular filtration rate, age and ischemic time.

CONCLUSIONS

ML models showed satisfactory predictive accuracy of mortality after HT in ACHD and allowed for individualized mortality risk assessment.

Donor heart selection: Evidence-based guidelines for providers

The proposed donor heart selection guidelines provide evidence-based and expert-consensus recommendations for the selection of donor hearts following brain death. These recommendations were compiled by an international panel of experts based on an extensive literature review.

Enhanced survival prediction using explainable artificial intelligence in heart transplantation

The most limiting factor in heart transplantation is the lack of donor organs. With enhanced prediction of outcome, it may be possible to increase the life-years from the organs that become available. Applications of machine learning to tabular data, typical of clinical decision support, pose the practical question of interpretation, which has technical and potential ethical implications. In particular, there is an issue of principle about the predictability of complex data and whether this is inherent in the data or strongly dependent on the choice of machine learning model, leading to the so-called accuracy-interpretability trade-off. We model 1-year mortality in heart transplantation data with a self-explaining neural network, which is benchmarked against a deep learning model on the same development data, in an external validation study with two data sets: (1) UNOS transplants in 2017-2018 (n = 4750) for which the self-explaining and deep learning models are comparable in their AUROC 0.628 [0.602,0.654] cf. 0.635 [0.609,0.662] and (2) Scandinavian transplants during 1997-2018 (n = 2293), showing good calibration with AUROCs of 0.626 [0.588,0.665] and 0.634 [0.570, 0.698], respectively, with and without missing data (n = 982). This shows that for tabular data, predictive models can be transparent and capture important nonlinearities, retaining full predictive performance.

Hemodynamic markers of pulmonary vasculopathy for prediction of early right heart failure and mortality after heart transplantation

BACKGROUND

Elevated pulmonary vascular resistance (PVR) is broadly accepted as an imminent risk factor for mortality after heart transplantation (HTx). However, no current HTx recipient risk score includes PVR or other hemodynamic parameters. This study examined the utility of various hemodynamic parameters for risk stratification in a contemporary HTx population.

METHODS

Patients from seven German HTx centers undergoing HTx between 2011 and 2015 were included retrospectively. Established risk factors and complete hemodynamic datasets before HTx were analyzed. Outcome measures were overall all-cause mortality, 12-month mortality, and right heart failure (RHF) after HTx.

RESULTS

The final analysis included 333 patients (28% female) with a median age of 54 (IQR 46-60) years. The median mean pulmonary artery pressure was 30 (IQR 23-38) mm Hg, transpulmonary gradient 8 (IQR 5-10) mm Hg, and PVR 2.1 (IQR 1.5-2.9) Wood units. Overall mortality was 35.7%, 12-month mortality was 23.7%, and the incidence of early RHF was 22.8%, which was significantly associated with overall mortality (log-rank HR 4.11, 95% CI 2.47-6.84; log-rank p < .0001). Pulmonary arterial elastance (Ea) was associated with overall mortality (HR 1.74, 95% CI 1.25-2.30; p < .001) independent of other non-hemodynamic risk factors. Ea values below a calculated cutoff represented a significantly reduced mortality risk (HR 0.38, 95% CI 0.19-0.76; p < .0001). PVR with the established cutoff of 3.0 WU was not significant. Ea was also significantly associated with 12-month mortality and RHF.

CONCLUSIONS

Ea showed a strong impact on post-transplant mortality and RHF and should become part of the routine hemodynamic evaluation in HTx candidates.

Pre-operative Machine Learning for Heart Transplant Patients Bridged with Temporary Mechanical Circulatory Support

Background: Existing prediction models for post-transplant mortality in patients bridged to heart transplantation with temporary mechanical circulatory support (tMCS) perform poorly. A more reliable model would allow clinicians to provide better pre-operative risk assessment and develop more targeted therapies for high-risk patients. Methods: We identified adult patients in the United Network for Organ Sharing database undergoing isolated heart transplantation between 01/2009 and 12/2017 who were supported with tMCS at the time of transplant. We constructed a machine learning model using extreme gradient boosting (XGBoost) with a 70:30 train:test split to predict 1-year post-operative mortality. All pre-transplant variables available in the UNOS database were included to train the model. Shapley Additive Explanations was used to identify and interpret the most important features for XGBoost predictions. Results: A total of 1584 patients were included, with a median age of 56 (interquartile range: 46-62) and 74% male. Actual 1-year mortality was 12.1%. Out of 498 available variables, 43 were selected for the final model. The area under the receiver operator characteristics curve (AUC) for the XGBoost model was 0.71 (95% CI: 0.62-0.78). The most important variables predictive of 1-year mortality included recipient functional status, age, pulmonary capillary wedge pressure (PCWP), cardiac output, ECMO usage, and serum creatinine. Conclusions: An interpretable machine learning model trained on a large clinical database demonstrated good performance in predicting 1-year mortality for patients bridged to heart transplantation with tMCS. Machine learning may be used to enhance clinician judgement in the care of markedly high-risk transplant recipients.

Utility of the IMPACT score for predicting heart transplant mortality. Analysis on a contemporary cohort of the Spanish Heart Transplant Registry

INTRODUCTION AND OBJECTIVES

The Index for Mortality Prediction After Cardiac Transplantation (IMPACT) score was derived and validated as a predictor of mortality after heart transplantation (HT). The primary objective of this work is to externally validate the IMPACT score in a contemporary Spanish cohort.

METHODS

Spanish Heart Transplant Registry data were used to identify adult (>16 years) HT patients between January 2000 and December 2015. Retransplantation, multiorgan transplantation and patients in whom at least one of the variables required to calculate the IMPACT score was missing were excluded from the analysis (N = 2,810).

RESULTS

Median value of the IMPACT score was 5 points (IQR: 3, 8). Overall 1-year survival rate was 79.1%. Kaplan-Meier 1-year survival rates by IMPACT score categories (0-2, 3-5, 6-9, 10-14, ≥ 15) were 84.4%, 81.5%, 79.3%, 77.3% and 58.5% respectively (Log-Rank test: p<0.001). Performance analysis showed a good calibration (Hosmer-Lemeshow chi-square for one year was 7.56; p = 0.47) and poor discrimination ability (AUC-ROC 0.59) of the IMPACT score as a predictive model.

CONCLUSIONS

In a contemporary Spanish cohort, the IMPACT score failed to accurately predict the risk of death after HT. This article is protected by copyright. All rights reserved.

Post Heart Transplantation Outcomes of Patients Supported on Biventricular Mechanical Support

With the implementation of the new heart transplant (HT) allocation system, patients requiring biventricular support systems have the highest priority, a shorter waitlist time, and a higher frequency of HT. However, the short-term and long-term outcomes of such patients are often disputed. Hence, we examined the outcomes of these patients who underwent HT before change in allocation scheme. Additionally, we compared post-HT outcomes of extracorporeal membrane oxygenation (ECMO) with other nondischargeable biventricular (BiVAD) supported patients. We identified adult ECMO or BiVAD supported HT recipients between 2000 and 2018 in the Scientific Registry of Transplant Recipients database. We compared survival with the Kaplan-Meier method. Using overlap propensity score weighting, we constructed Cox proportional hazards regression models to determine the risk-adjusted influence of BiVAD versus ECMO on survival. Of the 730 patients HT recipients; 528 (72.3%) and 202 (27.7%) were bridged with BiVAD and ECMO, respectively. For BiVAD versus ECMO patients, the 30-day, 1-year, 3-year, and 5-year mortality rates were 8.0% versus 14.4%, 16.3% versus 21.3%, 22.4% versus 25.3%, and 26.3% versus 25.7%, respectively. Risk-adjusted post-HT survival of BiVAD and ECMO patients at 30-day (HR 1.24 [95% CI, 0.68-2.27]; P = 0.4863), 1-year (HR 1.29 [95% CI, 0.80-2.09]; P = 0.3009), 3-year (HR 1.27 [95% CI, 0.83-1.94]; P = 0.2801), and 5-year (HR 1.35, 95% CI, 0.90-2.05; P = 0.1501) were similar. Around three-fourth of the ECMO or BiVAD supported patients were alive at 5-years post-HT. The short-term and long-term post-HT survivals of groups were comparable.

Durable Left Ventricular Assist Device as a Bridge to Heart Transplantation Under the New Donor Heart Allocation System

The new donor heart allocation system prioritizes candidates supported by temporary devices. However, waitlist and posttransplant outcomes in candidates with durable left ventricular assist device (LVAD) remain to be elucidated. The United Network for Organ Sharing database was queried for adults listed from October 2015 to March 2020 for a single-organ, first-time heart transplant (HTx) with a durable LVAD. Waitlist removal within 1 year because of death or clinical deterioration and HTx was analyzed using competing risks regression. Candidates who underwent HTx within 1 year of listing were identified for examination of post-HTx survival using the Kaplan-Meier method and Cox proportional hazards models. Compared with candidates listed under the old system (n = 2,122), candidates listed under the new system (n = 1,562) were slightly younger ( p = 0.04) but had higher body mass index ( p < 0.01). Those listed under the new system were significantly less likely to experience waitlist removal because of death or clinical deterioration (subhazard ratio [HR] 0.68, 95% CI 0.52-0.90) but were also less likely to undergo HTx (sub-HR 0.91, 95% CI 0.83-0.998). Those who survived to HTx were more likely to experience death or need for re-HTx within 1 year of HTx under the new system (adjusted HR 1.50, 95% CI 1.11-2.03). Candidates with durable LVAD experience favorable waitlist outcomes under the new allocation system, although those who undergo HTx may be at increased mortality risk. Thus, candidates with a durable LVAD should be carefully selected for HTx listing under the new allocation system.

Using Operative Reports to Predict Heart Transplantation Survival

Heart transplantation is a difficult procedure compared with other surgical operations, with a greater outcome uncertainty such as late rejection and death. We can model the success of heart transplants from predicting factors such as the age, sex, diagnosis, etc., of the donor and recipient. Although predictions can mitigate the uncertainty on the transplantation outcome, their accuracy is far from perfect. In this paper, we describe a new method to predict the outcome of a transplantation from textual operative reports instead of traditional tabular data. We carried out an experiment on 300 surgical reports to determine the survival rates at one year and five years. Using a truncated TF-IDF vectorization of the texts and logistic regression, we could reach a macro Fl of 59.1 %, respectively, 54.9% with a five-fold cross validation. While the size of the corpus is relatively small, our experiments show that the operative textual sources can discriminate the transplantation outcomes and could be a valuable additional input to existing prediction systems. Clinical Relevance- Heart transplantation involves a significant number of written reports including in the preoperative examinations and operative documentation. In this paper, we show that these written reports can predict the outcome of the transplantation at one and five years with macro 1s of 59.1 % and 54.9 %, respectively and complement existing prediction methods.

Early and Midterm Results of Orthotopic Heart Transplantation in Poland (2015-2019)

Orthotopic heart transplantation (OHT) has become one of the most expensive and resource-consuming treatment options for patients with end-stage heart failure. It is therefore useful to review clinical data, such as treatment duration after surgery and midterm follow-up in this group of patients. Contemporary epidemiologic data on early and midterm OHT follow-ups including patient demographics, hospitalization rates and related post-OHT morbidity, and mortality are scarce in Poland. The aim of the study was to determine early survival, hospitalization rates related to OHT and related morbidity, and mortality in Poland in the recent decade.

Validation of existing risk scores for mortality prediction after a heart transplant in a Chinese population

OBJECTIVES

The objectives of this study were to validate 3 existing heart transplant risk scores with a single-centre cohort in China and evaluate the efficacy of the 3 systems in predicting mortality.

METHODS

We retrospectively studied 428 patients from a single centre who underwent heart transplants from January 2015 to December 2019. All patients were scored using the Index for Mortality Prediction After Cardiac Transplantation (IMPACT) and the United Network for Organ Sharing (UNOS) and risk stratification scores (RSSs). We assessed the efficacy of the risk scores by comparing the observed and the predicted 1-year mortality. Binary logistic regression was used to evaluate the predictive accuracy of the 3 risk scores. Model discrimination was assessed by measuring the area under the receiver operating curves. Kaplan-Meier survival analyses were performed after the patients were divided into different risk groups.

RESULTS

Based on our cohort, the observed mortality was 6.54%, whereas the predicted mortality of the IMPACT and UNOS scores and the RSSs was 10.59%, 10.74% and 12.89%, respectively. Logistic regression analysis showed that the IMPACT [odds ratio (OR), 1.25; 95% confidence interval (CI), 1.15-1.36; P < 0.001], UNOS (OR, 1.68; 95% CI, 1.37-2.07; P < 0.001) and risk stratification (OR, 1.61; 95% CI, 1.30-2.00; P < 0.001) scores were predictive of 1-year mortality. The discriminative power was numerically higher for the IMPACT score [area under the curve (AUC) of 0.691)] than for the UNOS score (AUC 0.685) and the RSS (AUC 0.648).

CONCLUSIONS

We validated the IMPACT and UNOS scores and the RSSs as predictors of 1-year mortality after a heart transplant, but all 3 risk scores had unsatisfactory discriminative powers that overestimated the observed mortality for the Chinese cohort.

Derivation and validation of the bridge to transplantation with left ventricular assist device score for 1 year mortality after heart transplantation. The BTT-LVAD score

BACKGROUND

To derive and validate a risk score that accurately predicts 1-year mortality after heart transplantation (HT) in patients bridged to transplant (BTT) with a left ventricular assist device (LVAD).

METHODS

The UNOS database was queried to identify patients BTT with an LVAD between 2008 and 2018. Patients with ⩾1-year follow up were randomly divided into derivation (70%) and validation (30%) cohorts. The primary endpoint was 1-year mortality. A simple additive risk score was developed based on the odds of 1-year mortality after HT. Risk groups were created, and survival was estimated and compared.

RESULTS

A total of 7759 patients were randomly assigned to derivation (n = 5431) and validation (n = 2328) cohorts. One-year post-transplant mortality was 9.8% (n = 760). A 33-point scoring was created from six recipient variables and two donor variables. Risk groups were classified as low (0-5), intermediate (6-10), and high (>10). In the validation cohort, the predicted 1-year mortality was significantly higher in the high-risk group than the intermediate and low-risk groups, 14.7% versus 9% versus 6.1% respectively (log-rank test: p < 0.0001).

CONCLUSION

The BTT-LVAD Score can serve as a clinical decision tool to guide therapeutic decisions in advanced heart failure patients.

Thirty-Year Trends in Graft Survival After Heart Transplant: Modeled Analyses of a Transplant Registry

BACKGROUND

Heart failure is an epidemic in the United States, and transplantation remains the most definitive therapy. We describe multidecade trends in posttransplant graft survival, adjusted for concurrent changes in the population, over the 30 years antecedent to the most recent heart allocation policy change.

METHODS

Scientific Registry of Transplant Recipients data were used to identify all primary adult heart recipients from 1989 to 2017. We described temporal changes in population characteristics (recipient and donor demographics and comorbidities, pretransplant interventions, clinical transplant measures, and providers). The primary outcome was graft survival, defined as freedom from all-cause death and graft failure, within 6 months posttransplant. Modified Poisson logistic regression estimated relative changes in risk of outcomes compared with 1989, with and without adjustment for changing population characteristics. We identified risk factors, quantified by associated risk ratios.

RESULTS

Among 56,488 primary adult heart recipients, we observed 5529 (9.8%) all-cause deaths and 1933 (3.4%) graft failure events within 6 months posttransplant. Prevalence of known recipient risk factors increased over time. Unadjusted modeling demonstrated a significant 30-year improvement in graft survival, averaging 2.6% per year (95% confidence interval, 2.4-2.9; P for trend < .001). After adjusting for population changes the 30-year trend remained significant and graft survival improved on average 3.0% per year (95% confidence interval, 2.6-3.3). Regression modeling identified multiple predictors of graft survival. Modeling 2 additional outcomes of 6-month mortality and 6-month graft failure produced similar results.

CONCLUSIONS

Short-term graft survival after heart transplantation has improved significantly leading up to the 2018 heart allocation policy change, despite concurrent increase in prevalence of higher risk population characteristics.

Extracorporeal Photopheresis With Low-Dose Immunosuppression in High-Risk Heart Transplant Patients-A Pilot Study

In severely ill patients undergoing urgent heart transplant (HTX), immunosuppression carries high risks of infection, malignancy, and death. Low-dose immunosuppressive protocols have higher rejection rates. We combined extracorporeal photopheresis (ECP), an established therapy for acute rejection, with reduced-intensity immunosuppression. Twenty-eight high-risk patients (13 with high risk of infection due to infection at the time of transplant, 7 bridging to transplant via extracorporeal membrane oxygenation, 8 with high risk of malignancy) were treated, without induction therapy. Prophylactic ECP for 6 months (24 procedures) was initiated immediately postoperatively. Immunosuppression consisted of low-dose tacrolimus (8–10 ng/ml, months 1–6; 5–8 ng/ml, >6 months) with delayed start; mycophenolate mofetil (MMF); and low maintenance steroid with delayed start (POD 7) and tapering in the first year. One-year survival was 88.5%. Three patients died from infection (POD 12, 51, 351), and one from recurrence of cancer (POD 400). Incidence of severe infection was 17.9% (n = 5, respiratory tract). Within the first year, antibody-mediated rejection was detected in one patient (3.6%) and acute cellular rejection in four (14.3%). ECP with reduced-intensity immunosuppression is safe and effective in avoiding allograft rejection in HTX recipients with risk of severe infection or cancer recurrence.

Heart Transplantation: A Bibliometric Review From 1990-2021

BACKGROUND

As the rapidly aging population and the rising incidence of end-stage heart failure (HF), extensive research has been conducted on heart transplantation (HTx). Bibliometrics harbors the function for describing the relationships of knowledge structures in different research fields and predicting the growth trend .

METHODS

The publications were searched and filtered based on the WOS core database. The target literature was visualized and analyzed by CiteSpace or VOSviewer .

RESULTS

In total, 19,998 published papers were obtained. There is a wave-like growth in HTx development. Most advanced research results are concentrated in a few developed countries, while the interactions with developing countries are still in infancy. The United States occupies a strong dominant position among active countries on HTx. Early research hotpots mostly focused on primary disease, survival risk factors, and complications. In recent years, the research frontiers have shifted steadily to clinical evaluation of immunosuppressants and diagnosis of acute rejection, cardiac re-injury with COVID-19, innovations in ventricular assist devices(VAD), and donation allocation strategies. The research directions of HTx are gradually shifting from observational studies to intervention research.

Galectin-3 as an independent prognostic factor after heart transplantation

BACKGROUND

Galectin-3 (GAL3) is linked to the prognosis of patients with heart failure and after heart transplantation (HTx). We assessed the prognostic role of GAL3 in a long-term follow-up after HTx.

METHODS

HTx patients (N = 121) were evaluated in a single-center, noninterventional, prospective, observational study. The median follow-up was 96 months (2,942 days, interquartile range (IQR) 2,408-3,264 days), and 40 patients died. GAL3 was measured before HTx, +10 days after HTx, and during the first posttransplant year. Survival analysis (all-cause mortality) was performed with adjustments for clinical and laboratory variables.

RESULTS

The median pretransplant GAL3 level was 18.0 μg/L (IQR 14.0-25.9), and higher values were associated with older age, worse kidney function, left ventricular assist device use before HTx, a higher IMPACT score and mortality. Increased pretransplant GAL3 predicted shorter survival time (HR 2.05, 95% CI 1.09-3.85, p<0.05). Similar prognostic power had GAL3 on the 10th posttransplant day (HR 2.03, 95% CI 1.08-3.82, p<0.05). GAL3 was an independent predictor of death after adjustment for clinical variables (age, infection, diabetes, smoking, IMPACT score, troponin).

CONCLUSIONS

GAL3 was significantly associated with all-cause mortality after adjusting for clinical and laboratory variables and may serve as an additional prognostic biomarker. This article is protected by copyright. All rights reserved.

Adult Combined Heart-Liver Transplantation: The United States Experience

Background: We aimed to review the indications and outcomes of adults undergoing combined heart-liver transplantation (CHLT) in the US using national registry data.

Methods: Adult (≥18 years) CHLT recipients in the United Network for Organ Sharing database were included (09/1987–09/2020; era 1 = 1989–2000, era 2 = 2001–2010, era 3 = 2011–2020). Survival analysis was conducted by means of Kaplan-Meier method, log-rank test, and Cox regression.

Results: We identified 369 adults receiving CHLT between 12/1989–08/2020. The number of adult CHLT recipients (R² = 0.75, p < 0.001) and centers performing CHLT (R² = 0.80, p < 0.001) have increased over the study period. The most common cardiac diagnosis in the first two eras was restrictive/infiltrative cardiomyopathy, while the most common in era 3 was congenital heart disease (p = 0.03). The 1-, 3-, and 5-years patient survival was 86.8, 80.1, and 77.9%, respectively. In multivariable analysis, recipient diabetes [adjusted hazard ratio (aHR) = 2.35, 95% CI: 1.23–4.48], CHLT between 1989-2000 compared with 2011–2020 (aHR = 5.00, 95% CI: 1.13–22.26), and sequential-liver first CHLT compared with sequential-heart first CHLT (aHR = 2.44, 95% CI: 1.15–5.18) were associated with increased risk of mortality. Higher left ventricular ejection fraction was associated with decreased risk of mortality (aHR = 0.96, 95% CI: 0.92–0.99).

Conclusion: CHLT is being increasingly performed with evolving indications. Excellent outcomes can be achieved with multidisciplinary patient and donor selection and surgical planning.