OPTN/SRTR 2016 Annual Data Report: Heart

Colvin, Monica; Smith, Jodi M.; Hadley, N.; Skeans, M. A.; Carrico, Robert J.; Uccellini, K.; Lehman, Rebecca R.; Robinson, A. M.; Israni, Ajay K.; Snyder, Jon J.; Kasiske, Bertram L.

doi:10.1111/ajt.14561

Cited by 150 publications

(137 citation statements)

References 0 publications

Supporting

Mentioning

134

Contrasting

Unclassified

Order By: Relevance

“…However, this approach may not capture the varied causes of death in a small but heterogeneous population. Graft failure is the most common cause of death following pediatric HTx, while other common causes include cardiovascular and cerebrovascular disease, infection, and respiratory disease . Variation in causes of death may be difficult to adequately describe with a ML model, especially when focusing on the limited population of pediatric HTx recipients.…”

Section: Discussionmentioning

confidence: 99%

Prediction of mortality following pediatric heart transplant using machine learning algorithms

Miller

Tumin

Cooper

et al. 2019

Pediatric Transplantation

View full text Add to dashboard Cite

Background Optimizing transplant candidates’ priority for donor organs depends on the accurate assessment of post‐transplant outcomes. Due to the complexity of transplantation and the wide range of possible serious complications, recipient outcomes are difficult to predict accurately using conventional multivariable regression. Therefore, we evaluated the utility of 3 ML algorithms for predicting mortality after pediatric HTx. Methods We identified patients <18 years of age receiving HTx in 2006‐2015 in the UNOS Registry database. Mortality within 1, 3, or 5 years was predicted using classification and regression trees, RFs, and ANN. Each model was trained using cross‐validation, then validated in a separate testing set. Model performance was primarily evaluated by the area under the receiver operating characteristic (AUC) curve. Results The training set included 2802 patients, whereas 700 were included in the testing set. RF achieved the best fit to the training data with AUCs of 0.74, 0.68, and 0.64 for 1‐, 3‐, and 5‐year mortality, respectively, and performed best in the testing data, with AUCs of 0.72, 0.61, and 0.60, respectively. Nevertheless, sensitivity was poor across models (training: 0.22‐0.58; testing: 0.07‐0.49). Discussion ML algorithms demonstrated fair predictive utility in both training and testing data, but the sensitivity of these algorithms was generally poor. With the registry missing data on many determinants of long‐term survival, the ability of ML methods to predict mortality after pediatric HTx may be fundamentally limited.

show abstract

Section: Discussionmentioning

confidence: 99%

Prediction of mortality following pediatric heart transplant using machine learning algorithms

Miller

Tumin

Cooper

et al. 2019

Pediatric Transplantation

View full text Add to dashboard Cite

show abstract

“…This survey analysis showed that more non-kidney transplant candidates (liver, heart, and lung) were willing to accept an HCV-positive organ compared to kidney transplant candidates, although this difference was not statistically significant (p = 0.05). This difference may indicate that the lack of a suitable alternative such as dialysis for the end-stage disease of these organs (although left ventricular assist devices are being used for heart failure) coupled with higher waitlist mortality rates may lead non-kidney transplant candidates toward pursuing HCV-positive organ transplantation more eagerly [2,3,31,32].…”

Section: Discussionmentioning

confidence: 99%

Use of Hepatitis C Positive Organs: Patient Attitudes in Urban Chicago

et al. 2018

View full text Add to dashboard Cite

Background: Hepatitis C virus (HCV)-infected organs are being transplanted in patients with and without HCV in the direct-acting antiviral era. Little is known about patient attitudes towards receiving an HCV-positive organ. Objectives: The aim of this study is to determine transplant candidates’ attitudes towards receiving HCV-positive organs. Methods: Adult solid organ transplant candidates were identified during a clinic visit or during outpatient hemodialysis from May to December 2017. Willing participants completed a survey. Descriptive analysis including mean and median for continuous variables and frequencies for categorical variables were calculated by the appropriate statistical method and compared across willing, unsure, and unwilling patients and between willing and unsure/unwilling patients. Results: Fifty patients were surveyed with median age 54.5 years (range 32–77). Eighty-eight percent were awaiting kidney transplant, and 12% were awaiting other organs. Median waitlist time was 39.8 months (range 1.7–203 months). Most patients (90%) had prior knowledge of HCV, but only 60% knew it was curable. Forty-six percent were willing, 30% were unsure, and 24% were unwilling to receive an HCV-positive organ. Those willing to accept an HCV-positive organ were significantly older, Caucasian, had shorter waitlist times, and had greater physician trust than those that were unsure/unwilling. Similar worries, such as HCV incurability, insurance coverage, fears over the organ not working, and post-transplant death, were expressed in both the willing and unsure/unwilling patients. Conclusions: The availability of HCV-positive organs may expand the donor pool and decrease waitlist times and mortality. These data highlight the need for patient education towards use of these organs.

show abstract

“…1 Of all HF patients, an estimated 150 000-200 000 have advanced (stage D) HF refractory to medical therapy. 3 As a result, durable ventricular assist device (VAD) therapy has been increasingly utilized, and nearly 18 000 continuous-flow VADs (CF-VADs) are implanted annually. 3 As a result, durable ventricular assist device (VAD) therapy has been increasingly utilized, and nearly 18 000 continuous-flow VADs (CF-VADs) are implanted annually.…”

Section: Introductionmentioning

confidence: 99%

Accuracy of Doppler blood pressure measurement in continuous‐flow left ventricular assist device patients

Beckman

Welch

et al. 2019

ESC Heart Failure

View full text Add to dashboard Cite

Aims Accurate blood pressure (BP) measurement in continuous‐flow ventricular assist device (CF‐VAD) patients is imperative to reduce stroke risk. This study assesses the accuracy of the Doppler opening pressure method compared with the gold standard arterial line method in CF‐VAD patients. Methods and results In a longitudinal cohort of HeartMate II and HVAD patients, arterial line BP and simultaneously measured Doppler opening pressure were obtained. Overall correlation, agreement between Doppler opening pressure and arterial line mean vs. systolic pressure, and the effect of arterial pulsatility on the accuracy of Doppler opening pressure were analysed. A total of 1933 pairs of Doppler opening pressure and arterial line pressure readings within 1 min of each other were identified in 154 patients (20% women, mean age 55 ± 15, 50% HeartMate II and 50% HVAD). Doppler opening pressure had good correlation with invasive mean arterial pressure (r = 0.742, P < 0.0001) and more closely approximated mean than systolic BP (mean error 2.4 vs. −8.4 mmHg). Arterial pulsatility did not have a clinically significant effect on the accuracy of the Doppler opening pressure method. Conclusions Doppler opening pressure should be the standard non‐invasive method of BP measurement in CF‐VAD patients.

show abstract

OPTN/SRTR 2016 Annual Data Report: Heart

Cited by 150 publications

References 0 publications

Prediction of mortality following pediatric heart transplant using machine learning algorithms

Prediction of mortality following pediatric heart transplant using machine learning algorithms

Use of Hepatitis C Positive Organs: Patient Attitudes in Urban Chicago

Accuracy of Doppler blood pressure measurement in continuous‐flow left ventricular assist device patients

Contact Info

Product

Resources

About