Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Embracing Uncertainty Flexibility: Harnessing a Supervised Tree Kernel to Empower Ensemble Modelling for 2D Echocardiography-Based Prediction of Right Ventricular Volume

Tuan A. Bohoran, Polydoros N. Kampaktsis, Laura McLaughlin, Jay Leb, Gerry P. McCann, Archontis Giannakidis

TL;DR

An instance-based method is employed which uses the learned tree structure to identify the nearest training samples to a target instance and then uses a number of distribution types to more flexibly model the output to complement the volume predictions with uncertainty scores.

Abstract

The right ventricular (RV) function deterioration strongly predicts clinical outcomes in numerous circumstances. To boost the clinical deployment of ensemble regression methods that quantify RV volumes using tabular data from the widely available two-dimensional echocardiography (2DE), we propose to complement the volume predictions with uncertainty scores. To this end, we employ an instance-based method which uses the learned tree structure to identify the nearest training samples to a target instance and then uses a number of distribution types to more flexibly model the output. The probabilistic and point-prediction performances of the proposed framework are evaluated on a relatively small-scale dataset, comprising 100 end-diastolic and end-systolic RV volumes. The reference values for point performance were obtained from MRI. The results demonstrate that our flexible approach yields improved probabilistic and point performances over other state-of-the-art methods. The appropriateness of the proposed framework is showcased by providing exemplar cases. The estimated uncertainty embodies both aleatoric and epistemic types. This work aligns with trustworthy artificial intelligence since it can be used to enhance the decision-making process and reduce risks. The feature importance scores of our framework can be exploited to reduce the number of required 2DE views which could enhance the proposed pipeline's clinical application.

Embracing Uncertainty Flexibility: Harnessing a Supervised Tree Kernel to Empower Ensemble Modelling for 2D Echocardiography-Based Prediction of Right Ventricular Volume

TL;DR

An instance-based method is employed which uses the learned tree structure to identify the nearest training samples to a target instance and then uses a number of distribution types to more flexibly model the output to complement the volume predictions with uncertainty scores.

Abstract

The right ventricular (RV) function deterioration strongly predicts clinical outcomes in numerous circumstances. To boost the clinical deployment of ensemble regression methods that quantify RV volumes using tabular data from the widely available two-dimensional echocardiography (2DE), we propose to complement the volume predictions with uncertainty scores. To this end, we employ an instance-based method which uses the learned tree structure to identify the nearest training samples to a target instance and then uses a number of distribution types to more flexibly model the output. The probabilistic and point-prediction performances of the proposed framework are evaluated on a relatively small-scale dataset, comprising 100 end-diastolic and end-systolic RV volumes. The reference values for point performance were obtained from MRI. The results demonstrate that our flexible approach yields improved probabilistic and point performances over other state-of-the-art methods. The appropriateness of the proposed framework is showcased by providing exemplar cases. The estimated uncertainty embodies both aleatoric and epistemic types. This work aligns with trustworthy artificial intelligence since it can be used to enhance the decision-making process and reduce risks. The feature importance scores of our framework can be exploited to reduce the number of required 2DE views which could enhance the proposed pipeline's clinical application.
Paper Structure (11 sections, 3 equations, 4 figures, 6 tables)

This paper contains 11 sections, 3 equations, 4 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Materials & Methods
  3. Dataset
  4. Gradient-Boosted Regression Trees
  5. Instance-based Uncertainty Quantification
  6. Implementation
  7. Evaluation Metrics
  8. Exemplars
  9. Explainability
  10. Results
  11. Discussion and Conclusions

Figures (4)

  • Figure 1: IBUG flow chart. For a target instance, IBUG collects the training instances at each leaf it traverses, keeps the $k$ most frequent samples, and then uses those instances to model the output distribution.
  • Figure 2: The conditional output normal distributions for test instances that were predicted with high [(a) and (b)] and low [(c) and (d)] accuracy.
  • Figure 3: The conditional output logistic distributions for test instances that were predicted with high [(e) and (f)] and low [(g) and (h)] accuracy.
  • Figure 4: Feature importance plot for the IBUG model with CatBoost as the base learner.