Gradient Boosting on Decision Trees for Mortality Prediction in Transcatheter Aortic Valve Implantation

@article{Mamprin2020GradientBO,
  title={Gradient Boosting on Decision Trees for Mortality Prediction in Transcatheter Aortic Valve Implantation},
  author={Marco Mamprin and Jo M. Zelis and Pim A. L. Tonino and Svitlana Zinger and Peter H. N. de With},
  journal={Proceedings of the 2020 10th International Conference on Biomedical Engineering and Technology},
  year={2020}
}
  • Marco MamprinJ. Zelis P. D. With
  • Published 8 January 2020
  • Computer Science
  • Proceedings of the 2020 10th International Conference on Biomedical Engineering and Technology
Current prognostic risk scores in cardiac surgery are based on statistics and do not yet benefit from machine learning. Statistical predictors are not robust enough to correctly identify patients who would benefit from Transcatheter Aortic Valve Implantation (TAVI). This research aims to create a machine learning model to predict one-year mortality of a patient after TAVI. We adopt a modern gradient boosting on decision trees algorithm, specifically designed for categorical features. In… 

Figures and Tables from this paper

Inter-Center Cross-Validation and Finetuning without Patient Data Sharing for Predicting Transcatheter Aortic Valve Implantation Outcome

This research demonstrates that the predicting capabilities of deep learning models can be extended to and cross-validated with other centers, independent of limitations in data-sharing policies, and shows that finetuning can be exploited to considerably improve the accuracy of the prediction models.

Feature Selection and Prediction of Heart diseases using Gradient Boosting Algorithms

  • P. AnuradhaV. David
  • Computer Science
    2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS)
  • 2021
feature importance ranking of two gradient boosting algorithms XGBoost and CatBoost were computed on Cleveland, Statlog heart and SA heart data sets and the classifiers exhibited improved performance on selected features when compared to their performance on all features.

Finding improved predictive models with Generalized Boosted Models on Hungarian Myocardial Infarction Registry

New predictive modelling results achieved with Generalized Boosted Models (GBM) on the dataset of Hungarian Myocardial Infarction Registry are presented, representing a strong and stable learner with almost the similar predictive power as the previously published random forest models.

A review of machine learning for cardiology.

This paper reviews recent cardiology literature and reports how Artificial Intelligence Tools (specifically, Machine Learning techniques) are being used by physicians in the field, and discusses the main open issues in applying Machine Learning tools to cardiology tasks.

Identification of patients at risk of cardiac conduction diseases requiring a permanent pacemaker following TAVI procedure: a deep-learning approach on ECG signals

This study confirms that it is possible to identify and stratify even further, the risk for patients that will develop CCD after TAVI, by using the information available in the ECG data immediately following the procedure.

Exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomes

The results indicate that machine learning methods can be used to exploit the predictive value ofPROMs and thereby support clinical decision making, given that the PROMs hold enough predictive power.

Developing a Novel Continuous Metabolic Syndrome Score: A Data Mining Based Model

The research results show that high TG and central obesity have the greatest impact on MetS and FBS has no effect on the final prognosis and in the preliminary stages of MetS, WC, HDL and SBP are the most important influencing factors that play an important role in forecasting.

References

SHOWING 1-10 OF 18 REFERENCES

Prediction of Poor Outcome After Transcatheter Aortic Valve Replacement.

EuroSCORE II and STS as mortality predictors in patients undergoing TAVI.

In this cohort, the STS and EuroSCORE II were predictors of in-hospital and 30-days mortality in patients with severe aortic stenosis undergoing TAVI.

EuroSCORE II.

Cardiac surgical mortality has significantly reduced in the last 15 years despite older and sicker patients, and EuroSCORE II is better calibrated than the original model yet preserves powerful discrimination.

Addressing the Class Imbalance Problem in Medical Datasets

This paper examines the performance of over-sampled and under-sampling techniques to balance cardiovascular data and proposes an improved under sampling technique that displays significant better performance than the existing methods.

A Unified Approach to Interpreting Model Predictions

A unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations), which unifies six existing methods and presents new methods that show improved computational performance and/or better consistency with human intuition than previous approaches.

Random Forests

Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.

Consistent Individualized Feature Attribution for Tree Ensembles

This work develops fast exact tree solutions for SHAP (SHapley Additive exPlanation) values, which are the unique consistent and locally accurate attribution values, and proposes a rich visualization of individualized feature attributions that improves over classic attribution summaries and partial dependence plots, and a unique "supervised" clustering.

XGBoost: A Scalable Tree Boosting System

This paper proposes a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning and provides insights on cache access patterns, data compression and sharding to build a scalable tree boosting system called XGBoost.

CatBoost: unbiased boosting with categorical features

This paper presents the key algorithmic techniques behind CatBoost, a new gradient boosting toolkit and provides a detailed analysis of this problem and demonstrates that proposed algorithms solve it effectively, leading to excellent empirical results.