Neural networks versus Logistic regression for 30 days all-cause readmission prediction

Abstract

Heart failure (HF) is one of the leading causes of hospital admissions in the US. Readmission within 30 days after a HF hospitalization is both a recognized indicator for disease progression and a source of considerable financial burden to the healthcare system. Consequently, the identification of patients at risk for readmission is a key step in improving disease management and patient outcome. In this work, we used a large administrative claims dataset to (1) explore the systematic application of neural network-based models versus logistic regression for predicting 30 days all-cause readmission after discharge from a HF admission, and (2) to examine the additive value of patients’ hospitalization timelines on prediction performance. Based on data from 272,778 (49% female) patients with a mean (SD) age of 73 years (14) and 343,328 HF admissions (67% of total admissions), we trained and tested our predictive readmission models following a stratified 5-fold cross-validation scheme. Among the deep learning approaches, a recurrent neural network (RNN) combined with conditional random fields (CRF) model (RNNCRF) achieved the best performance in readmission prediction with 0.642 AUC (95% CI, 0.640–0.645). Other models, such as those based on RNN, convolutional neural networks and CRF alone had lower performance, with a non-timeline based model (MLP) performing worst. A competitive model based on logistic regression with LASSO achieved a performance of 0.643 AUC (95% CI, 0.640–0.646). We conclude that data from patient timelines improve 30 day readmission prediction, that a logistic regression with LASSO has equal performance to the best neural network model and that the use of administrative data result in competitive performance compared to published approaches based on richer clinical datasets.

Integration of Biodynamic Imaging and RNA-seq classifies chemotherapy response in canine diffuse large B-cell lymphoma

“…In these studies we use absolute shrinkage and selection operator LASSO (L1) and ridge (L2) regularized logistic regression, which are established machine learning techniques that generalize well to data not seen in training or validation sets (51, 52). To increase generalization, feature selection was employed based on variable Area-Under-the-Precision-Recall-Curve (AUPRC) ( Table S11-12 ).…”

MD-Manifold: A Medical Distance Based Manifold Learning Approach for Heart Failure Readmission Prediction

“…The readmission prediction for heart failure patients has a significant meaning in practice. In the US, heart failure is one of the main causes of medical institution admissions [3]. Within 30 days after the hospital discharge, approximately 24% heart failure patients would experience all-cause readmission, which costs around $17 billion every year [3].…”

“…In the US, heart failure is one of the main causes of medical institution admissions [3]. Within 30 days after the hospital discharge, approximately 24% heart failure patients would experience all-cause readmission, which costs around $17 billion every year [3]. The readmission is an indicator of disease progression and a source of the economic burden to the medical system [3].…”

“…Within 30 days after the hospital discharge, approximately 24% heart failure patients would experience all-cause readmission, which costs around $17 billion every year [3]. The readmission is an indicator of disease progression and a source of the economic burden to the medical system [3]. Therefore, the early identification of patients at risk of readmission is a crucial step for enhancing disease management and patient control.…”

Forecasting mortality rates using hybrid Lee–Carter model, artificial neural network and random forest

“…Apart from the above, other machine learning (ML) algorithms have been introduced in the literature. These include the Particle Swarm Optimization (PSO)-based ANN by Abdulkarim and Garko [21], logistic regression (LR) model by Allam et al [22], and Multilayer Perceptron neural network (MLPNN) by Puddu and Menotti [23]. Atsalakis et al [24] proposed to predict the mortality rate by using the Adaptive Neuro-Fuzzy Inference System (ANFIS) model, whereas Sakr et al [25] compared seven ML classification techniques, which included DT, RF, ANN, Naïve Bayesian Network (NBN), SVM, K-Nearest Neighbor (KNN), and Bayesian Classifier (BC) to forecast all-cause mortality by applying cardiorespiratory fitness data.…”