Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Mortality Prediction of Pulmonary Embolism Patients with Deep Learning and XGBoost

Yalcin Tur, Vedat Cicek, Tufan Cinar, Elif Keles, Bradlay D. Allen, Hatice Savas, Gorkem Durak, Alpay Medetalibeyoglu, Ulas Bagci

TL;DR

A new algorithm, called PEP-Net, for 30-day mortality prediction of PE patients based on the initial imaging data (CT) that opportunistically integrates a 3D Residual Network (3DResNet) with Extreme Gradient Boosting (XGBoost) algorithm with patient level binary labels without annotations of the emboli and its extent is presented.

Abstract

Pulmonary Embolism (PE) is a serious cardiovascular condition that remains a leading cause of mortality and critical illness, underscoring the need for enhanced diagnostic strategies. Conventional clinical methods have limited success in predicting 30-day in-hospital mortality of PE patients. In this study, we present a new algorithm, called PEP-Net, for 30-day mortality prediction of PE patients based on the initial imaging data (CT) that opportunistically integrates a 3D Residual Network (3DResNet) with Extreme Gradient Boosting (XGBoost) algorithm with patient level binary labels without annotations of the emboli and its extent. Our proposed system offers a comprehensive prediction strategy by handling class imbalance problems, reducing overfitting via regularization, and reducing the prediction variance for more stable predictions. PEP-Net was tested in a cohort of 193 volumetric CT scans diagnosed with Acute PE, and it demonstrated a superior performance by significantly outperforming baseline models (76-78\%) with an accuracy of 94.5\% (+/-0.3) and 94.0\% (+/-0.7) when the input image is either lung region (Lung-ROI) or heart region (Cardiac-ROI). Our results advance PE prognostics by using only initial imaging data, setting a new benchmark in the field. While purely deep learning models have become the go-to for many medical classification (diagnostic) tasks, combined ResNet and XGBoost models herein outperform sole deep learning models due to a potential reason for having lack of enough data.

Mortality Prediction of Pulmonary Embolism Patients with Deep Learning and XGBoost

TL;DR

A new algorithm, called PEP-Net, for 30-day mortality prediction of PE patients based on the initial imaging data (CT) that opportunistically integrates a 3D Residual Network (3DResNet) with Extreme Gradient Boosting (XGBoost) algorithm with patient level binary labels without annotations of the emboli and its extent is presented.

Abstract

Pulmonary Embolism (PE) is a serious cardiovascular condition that remains a leading cause of mortality and critical illness, underscoring the need for enhanced diagnostic strategies. Conventional clinical methods have limited success in predicting 30-day in-hospital mortality of PE patients. In this study, we present a new algorithm, called PEP-Net, for 30-day mortality prediction of PE patients based on the initial imaging data (CT) that opportunistically integrates a 3D Residual Network (3DResNet) with Extreme Gradient Boosting (XGBoost) algorithm with patient level binary labels without annotations of the emboli and its extent. Our proposed system offers a comprehensive prediction strategy by handling class imbalance problems, reducing overfitting via regularization, and reducing the prediction variance for more stable predictions. PEP-Net was tested in a cohort of 193 volumetric CT scans diagnosed with Acute PE, and it demonstrated a superior performance by significantly outperforming baseline models (76-78\%) with an accuracy of 94.5\% (+/-0.3) and 94.0\% (+/-0.7) when the input image is either lung region (Lung-ROI) or heart region (Cardiac-ROI). Our results advance PE prognostics by using only initial imaging data, setting a new benchmark in the field. While purely deep learning models have become the go-to for many medical classification (diagnostic) tasks, combined ResNet and XGBoost models herein outperform sole deep learning models due to a potential reason for having lack of enough data.

Paper Structure

This paper contains 4 sections, 2 equations, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Results
  4. Discussion and Concluding Remarks

Figures (3)

  • Figure 1: We have lobar (left) and distal PE (right) cases are illustrated, respectively.
  • Figure 2: Proposed PEP-Net architecture for mortality prediction for PE patients include four consecutive steps. Lung and cardiac region localizations (rough ROIs), feature extraction with deep nets, oversampling and dimensionality reduction, and an optimized classifier.
  • Figure 3: Left: ROC-AUC curve of different DL-based approaches used in this study; TPR-- True Positive Rate, FPR-- False Positive Rate. Middle: An example CT scan that PEP-Net predicts the 30-day mortality of PE patient with high probability. Right: An example CT scan that PEP-Net fails to predict the patient's 30-day mortality. Very subtle change is observed.