Building a Risk Prediction Model for Postoperative Pulmonary Vein Obstruction via Quantitative Analysis of CTA Images

Abstract

Total anomalous pulmonary venous connection (TAPVC) is a rare but mortal congenital heart disease in children and can be repaired by surgical operations. However, some patients may suffer from pulmonary venous obstruction (PVO) after surgery with insufficient blood supply, necessitating special follow-up strategy and treatment. Therefore, it is a clinically important yet challenging problem to predict such patients before surgery. In this paper, we address this issue and propose a computational framework to determine the risk factors for postoperative PVO (PPVO) from computed tomography angiography (CTA) images and build the PPVO risk prediction model. From clinical experiences, such risk factors are likely from the left atrium (LA) and pulmonary vein (PV) of the patient. Thus, 3D models of LA and PV are first reconstructed from low-dose CTA images. Then, a feature pool is built by computing different morphological features from 3D models of LA and PV, and the coupling spatial features of LA and PV. Finally, four risk factors are identified from the feature pool using the machine learning techniques, followed by a risk prediction model. As a result, not only PPVO patients can be effectively predicted but also qualitative risk factors reported in the literature can now be quantified. Finally, the risk prediction model is evaluated on two independent clinical datasets from two hospitals. The model can achieve the AUC values of 0.88 and 0.87 respectively, demonstrating its effectiveness in risk prediction.

A Cardiac Deep Learning Model (CDLM) to Predict and Identify the Risk Factor of Congenital Heart Disease

“…Dritsas, E. et al [28] The screening tools and predictive models are used to identify risk groups for newborns suffering from CHD. These tools allow for early detection, helping to identify those at higher risk and provide them with appropriate care Ng, W. et al [29] Machine learning is also being used to develop a risk index which can help in the present analysis of pregnancy and predict the possibility of a newborn having CHD Balakrishnan, M. et al [30] The machine learning algorithms such as logistic regression and decision trees can be used to analyze the data collected from maternal laboratory tests, clinical laboratory data, and other studies predicting CHD Williams, R. et al [31] Through CHD prediction using machine learning techniques such as supervised learning, it is possible to develop predictive models that are able to accurately predict CHD in newborns Ravi, R. et al [32] With data obtained through laboratory tests combined with machine learning algorithms such as logistic regression and decision trees, it is possible for doctors to create accurate predictive models Pei, Y. et al [33] Integrated patient data from a great variety of sources can be used to create efficient machine learning models that use ML algorithms to identify at-risk newborns before their birth Shishah, W. et al [34] The machine learning classification approach can be used to identify at-risk infants and diagnose them quickly, allowing doctors to take preventative measures early on Iscra, K. et al [35] The machine learning technology has been utilized to develop predictive models for the diagnosis of newborns with CHD. These models have been applied to large datasets of neonatal ICU admissions and have shown promising results in terms of accuracy and speed of diagnostics…”

“…Ravi, R. et al [ 32 ] discussed that by using the data obtained through laboratory tests combined with machine learning algorithms such as logistic regression and decision trees, doctors can create accurate predictive models to help them determine the likelihood of a baby being born with CHD. Pei, Y. et al [ 33 ] expressed that doctors can be better prepared for the postoperative complications that may arise. Additionally, integrated patient data from various sources can be used to create efficient machine learning models using ML algorithms to identify at-risk newborns before birth.…”

“…If heart failure is suspected, the cardiologist recommends additional diagnostic methods. Electrocardiography is used for detecting congenital and acquired defects at any age [ 33 ]. It also corrects arrhythmias, electrical axis displacements, and conduction system disorders.…”