Risk Scoring for Prediction of Acute Cardiac Complications from Imbalanced Clinical Data

Abstract

Fast and accurate risk stratification is essential in the emergency department (ED) as it allows clinicians to identify chest pain patients who are at high risk of cardiac complications and require intensive monitoring and early intervention. In this paper, we present a novel intelligent scoring system using heart rate variability, 12-lead electrocardiogram (ECG), and vital signs where a hybrid sampling-based ensemble learning strategy is proposed to handle data imbalance. The experiments were conducted on a dataset consisting of 564 chest pain patients recruited at the ED of a tertiary hospital. The proposed ensemble-based scoring system was compared with established scoring methods such as the modified early warning score and the thrombolysis in myocardial infarction score, and showed its effectiveness in predicting acute cardiac complications within 72 h in terms of the receiver operation characteristic analysis.

Machine Learning Dimensionality Reduction Showed Marginal Performance Benefit Over Stepwise Regression for Risk Stratification of Chest Pain Patients in the Emergency Department

“…Figure 5 shows ROC curves of HRnV models without using cardiac troponin. At feature dimensions of 13,21,13,29,24,17,18, and 18, the highest AUC values of PCA, KPCA, LSA, GRP, SRP, MDS, Isomap, and LLE were 0.852, 0.852, 0.852, 0.852, 0.851, 0.852, 0.845, and 0.849, respectively. The stepwise model without troponin yielded an AUC of 0.834 compared to 0.887 with troponin.…”

“…We had previously developed a heart rate variability (HRV) prediction model using readily available variables at the ED, in an attempt to reduce both diagnostic time and subjective components [22]. HRV characterizes beat-to-beat variation using time, frequency domain and nonlinear analysis [23], and has proven to be a good predictor of major adverse cardiac events (MACE) [22,24,25]. Most HRV-based scores were reported to be superior to TIMI and GRACE scores while achieving comparable performance with HEART score [17,24,26,27].…”

“…HRV characterizes beat-to-beat variation using time, frequency domain and nonlinear analysis [23], and has proven to be a good predictor of major adverse cardiac events (MACE) [22,24,25]. Most HRV-based scores were reported to be superior to TIMI and GRACE scores while achieving comparable performance with HEART score [17,24,26,27]. Recently, we established a new representation of beat-to-beat variation in ECGs, the heart rate n-variability (HRnV) [28].…”

ECG Monitoring Systems: Review, Architecture, Processes, and Key Challenges

“…This is because predicting the likelihood of expected disease development is considered a major human health concern nowadays. Many ECG monitoring systems were proposed not only to diagnose, but also to predict certain diseases such as arrhythmia [200,201], AF [63,202], Epilepsy [203,204], and other cardiovascular diseases [89,[205][206][207][208][209][210][211][212]. Many studies that are related to daily monitoring and activities during sleep, proposed different designs and specifications for wearable devices, such as shirts [33][34][35].…”

A probabilistic topic model for clinical risk stratification from electronic health records

“…Liu et al, present an intelligent scoring system for risk stratification of chest pain patients. In particular, they adopted a hybrid sampling-based ensemble learning strategy to handle EHR data imbalance problem [11]. Singh et al, evaluated three different approaches that use machine learning to build predictive models using temporal EHR data of patients with compromised kidney function.…”