Prediction of Outcomes after Heart Transplantation Using Machine Learning Techniques

Villela, Miguel Alvarez; Bravo, Claudio; Shah, Mahek; Patel, Snehal R.; Jorde, Ulrich P.; Stehlik, Josef; Castellanos, Arturo Rodríguez

doi:10.1016/j.healun.2020.01.658

Cited by 10 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML models have been applied in HT with promising results. 13,14 The previously published International Heart Transplant Survival Algorithm (IHTSA) was based on a flexible, nonlinear artificial neural network to predict survival after HT, included over 56 000 adult patients who underwent HT from 1994 to 2010 with a reported AUC .65 for 1-year survival. 25 The analysis identified recipient age, type of heart disease, history of prior transplantation, and mechanical ventilation before transplantation and donor age, cause of death, sex, and diabetes as important predictors of mortality.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

State‐of‐the‐art machine learning algorithms for the prediction of outcomes after contemporary heart transplantation: Results from the UNOS database

Kampaktsis

Tzani

Doulamis

et al. 2021

Clinical Transplantation

View full text Add to dashboard Cite

We sought to develop and validate machine learning (ML) models to increase the predictive accuracy of mortality after heart transplantation (HT). Methods and results:We included adult HT recipients from the United Network for Organ Sharing (UNOS) database between 2010 and 2018 using solely pre-transplant variables. The study cohort comprised 18 625 patients (53 ± 13 years, 73% males) and was randomly split into a derivation and a validation cohort with a 3:1 ratio. At 1-year after HT, there were 2334 (12.5%) deaths. Out of a total of 134 pre-transplant variables, 39 were selected as highly predictive of 1-year mortality via feature selection algorithm and were used to train five ML models. AUC for the prediction of 1-year survival was .689, .642, .649, .637, .526 for the Adaboost, Logistic Regression, Decision Tree, Support Vector Machine, and K-nearest neighbor models, respectively, whereas the Index for Mortality Prediction after Cardiac Transplantation (IMPACT) score had an AUC of .569. Local interpretable model-agnostic explanations (LIME) analysis was used in the best performing model to identify the relative impact of key predictors.ML models for 3-and 5-year survival as well as acute rejection were also developed in a secondary analysis and yielded AUCs of .629, .609, and .610 using 27, 31, and 91 selected variables respectively. Conclusion:Machine learning models showed good predictive accuracy of outcomes after heart transplantation.

show abstract

Section: Discussionmentioning

confidence: 99%

“…11,12 Recently, the application of ML algorithms to predict outcomes after HT has shown some promising results compared to traditionally derived risk scores. 13,14 However, further work is needed to determine the role of ML in the prediction of outcomes and risk stratification of HT patients.…”

Section: Introductionmentioning

confidence: 99%

State‐of‐the‐art machine learning algorithms for the prediction of outcomes after contemporary heart transplantation: Results from the UNOS database

Kampaktsis

Tzani

Doulamis

et al. 2021

Clinical Transplantation

View full text Add to dashboard Cite

show abstract

“…However, results from ML models in pediatric transplantation across kidney, liver, and heart recipients from one center were similarly suboptimal [14]. In adult populations, predictive validity with ML approaches has not achieved better results [25][26][27][28][29][30][31][32][33]. Many of these studies have focused only on mortality in adult HT, offering little insight for transplant teams managing instances of other important outcomes like rejection and hospitalization in the years following transplantation in pediatric patients.…”

Section: Discussionmentioning

confidence: 99%

“…Patient medical factors also included weight, a history of prior malignancies, and creatine levels. These medical factors have been similarly identi ed in prior research using machine-learning approaches in other transplant data, including adult populations [14,27,[31][32][33].…”

Section: Model Interpretationmentioning

confidence: 94%

Predicting health outcomes through machine learning in pediatric heart transplantation: Use of national data from the United Network for Organ Sharing

Killian

Tian

Xing

et al. 2022

Preprint

View full text Add to dashboard Cite

Background Prediction of post-transplant health outcomes for pediatric heart transplantation is critical for high quality post-transplant care. The purpose of the current study is to examine the use of machine learning models to predict late acute rejection, hospitalizations, and mortality for pediatric heart transplant recipients. Methods Various traditional machine learning and deep learning models were used to predict late acute rejection, hospitalizations, and mortality at 1-, 3-, and 5-years post-transplant in pediatric heart transplant recipients using the national United Network for Organ Sharing data. Variables predicting post-transplant outcomes included donor and recipient medical and social predictors. SHAP (SHapley Additive exPlanations) were calculated to estimate the importance of each variable for prediction and to increase the interpretability of modeling results. Results Logistic regression, random forest, and adaptive boosting models were the best performing algorithms for different prediction windows across outcomes. Based on the area under the receiver operating curve, models predicting rejection and mortality were found to be more accurate than those predicting hospitalizations. Conclusions Machine learning approaches can identify unique risk factors, their complex relationship with outcomes using prediction modeling, thereby aiding in identifying at-risk patients, providing a solid foundation for improved clinical care, risk stratification, and guiding decision-making within pediatric organ transplant centers. The current study demonstrates the value of machine learning approaches for modeling post-transplant health outcomes using patient-level data and informs the transplant community about the future potential of these innovative approaches to improve pediatric post-heart transplant care.

show abstract

“…Typical tasks that are performed with the models implemented with AutoML are classification tasks. For example, it was used in the health sector [28,30,31], the corporate sector [32], the environmental sector [33,34], the energy sector [35,36], and others [37][38][39]. There are many AutoML tools and solutions available today to help data scientists.…”

Section: Automated Machine Learningmentioning

confidence: 99%

Using a DEA–AutoML Approach to Track SDG Achievements

Singpai

2020

Sustainability

View full text Add to dashboard Cite

Each country needs to monitor progress on their Sustainable Development Goals (SDGs) to develop strategies that meet the expectations of the United Nations. Data envelope analysis (DEA) can help identify best practices for SDGs by setting goals to compete against. Automated machine learning (AutoML) simplifies machine learning for researchers who need less time and manpower to predict future situations. This work introduces an integrative method that integrates DEA and AutoML to assess and predict performance in SDGs. There are two experiments with different data properties in their interval and correlation to demonstrate the approach. Three prediction targets are set to measure performance in the regression, classification, and multi-target regression algorithms. The back-propagation neural network (BPNN) is used to validate the outputs of the AutoML. As a result, AutoML can outperform BPNN for regression and classification prediction problems. Low standard deviation (SD) data result in poor prediction performance for the BPNN, but does not have a significant impact on AutoML. Highly correlated data result in a higher accuracy, but does not significantly affect the R-squared values between the actual and predicted values. This integrative approach can accurately predict the projected outputs, which can be used as national goals to transform an inefficient country into an efficient country.

show abstract

Prediction of Outcomes after Heart Transplantation Using Machine Learning Techniques

Cited by 10 publications

References 0 publications

State‐of‐the‐art machine learning algorithms for the prediction of outcomes after contemporary heart transplantation: Results from the UNOS database

State‐of‐the‐art machine learning algorithms for the prediction of outcomes after contemporary heart transplantation: Results from the UNOS database

Predicting health outcomes through machine learning in pediatric heart transplantation: Use of national data from the United Network for Organ Sharing

Using a DEA–AutoML Approach to Track SDG Achievements

Contact Info

Product

Resources

About