Weight-based multiple empirical kernel learning with neighbor discriminant constraint for heart failure mortality prediction

Wang, Zhe; Wang, Bolu; Zhou, Yangming; Li, Dongdong; Yin, Yanlin

doi:10.1016/j.jbi.2019.103340

Cited by 13 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, nine representative classifiers are selected to compare with the proposed SSMEKL. The comparison algorithms are MK-MHKS, 39 SMKSVM, 26 SVM, 40 GLMKL, 41 TSVM, 42 EasyMKL, 43 XGBoost, 44 WMEKL-NDC, 45 and RGC. 46 MK-MHKS is a classic and efficient multiple kernel learning algorithm.…”

Section: Methodsmentioning

confidence: 99%

Semi‐supervised multiple empirical kernel learning with pseudo empirical loss and similarity regularization

Guo

Wang

et al. 2021

Int J of Intelligent Sys

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Semi‐supervised multiple empirical kernel learning with pseudo empirical loss and similarity regularization

Guo

Wang

et al. 2021

Int J of Intelligent Sys

Self Cite

View full text Add to dashboard Cite

show abstract

“…Despite the wider application of various supervised learning methods such as SVM [9], [10], deep learning [11], RF, decision tree (DT) [12], MLP [13], and LR [14] for HF prediction, the effectiveness of these HF prediction methods have scope for improvement and requires much research effort. The literature review shows that most of the supervised methods are developed on the original dataset and the significance of pre-processing such as feature scaling, and dimensionality reduction for the linear model such as SVM is widely ignored [15]- [20]. To address the research gap, this study investigates feature scaling, and PCA as a method for improving the performance of DT, RF, and SVM models for HF prediction.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of feature scaling for improving the performance of supervised learning methods

Assegie¹,

Paulraj²,

Velmurugan

et al. 2023

Bulletin EEI

View full text Add to dashboard Cite

This article evaluates the performance of the support vector machine (SVM), decision tree (DT), and random forest (RF) on the dataset that contains the medical records of 299 patients with heart failure (HF) collected at the Faisalabad Institute of Cardiology and the Allied hospital in Pakistan. The dataset contains 13 descriptive features of physical, clinical, and lifestyle information. The study compared the performance of three classification algorithms employing pre-processing techniques such as min-max scaling, and principal component analysis (PCA). The simulation result shows that the performance of the DT, and RF decreased with dimensionality reduction while the SVM improved with dimensionality reduction. The SVM achieved 84.44%. Thus, feature scaling improves the performance of the SVM. The RF performs at 82.22%, the DT at 81.11%, and the SVM shows an improvement of 1.64% with scaled features, compared to the original dataset.

show abstract

“…However, the high dimensionality, sparsity, and heterogeneity of EMR data [ 12 , 18 ] pose many obstacles for directly inputting the raw data into machine learning–based predictive models. Some manual and data-driven feature engineering methods [ 15 , 19 ], though time-consuming and laborious, were used to select important features or extract useful information for predictive tasks. Moreover, the performance of predictive models relies heavily on the representation of data.…”

Section: Introductionmentioning

confidence: 99%

“…EMR data can be used to not only reflect the health status of patients and record the treatment trajectory, but also help doctors in making clinical decisions [1][2][3][4][5][6] and improving the efficiency of diagnosis and treatment [1,7,8]. One of the most prevalent and practical tasks of the secondary use of EMR data is building models to predict the disease status [8][9][10] and treatment outcomes [11][12][13][14][15][16][17] for a patient, using machine learning algorithms.…”

Section: Introductionmentioning

confidence: 99%

Improving the Performance of Outcome Prediction for Inpatients With Acute Myocardial Infarction Based on Embedding Representation Learned From Electronic Medical Records: Development and Validation Study

Huang¹,

Zheng²,

Ma³

et al. 2022

J Med Internet Res

View full text Add to dashboard Cite

Background The widespread secondary use of electronic medical records (EMRs) promotes health care quality improvement. Representation learning that can automatically extract hidden information from EMR data has gained increasing attention. Objective We aimed to propose a patient representation with more feature associations and task-specific feature importance to improve the outcome prediction performance for inpatients with acute myocardial infarction (AMI). Methods Medical concepts, including patients’ age, gender, disease diagnoses, laboratory tests, structured radiological features, procedures, and medications, were first embedded into real-value vectors using the improved skip-gram algorithm, where concepts in the context windows were selected by feature association strengths measured by association rule confidence. Then, each patient was represented as the sum of the feature embeddings weighted by the task-specific feature importance, which was applied to facilitate predictive model prediction from global and local perspectives. We finally applied the proposed patient representation into mortality risk prediction for 3010 and 1671 AMI inpatients from a public data set and a private data set, respectively, and compared it with several reference representation methods in terms of the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and F1-score. Results Compared with the reference methods, the proposed embedding-based representation showed consistently superior predictive performance on the 2 data sets, achieving mean AUROCs of 0.878 and 0.973, AUPRCs of 0.220 and 0.505, and F1-scores of 0.376 and 0.674 for the public and private data sets, respectively, while the greatest AUROCs, AUPRCs, and F1-scores among the reference methods were 0.847 and 0.939, 0.196 and 0.283, and 0.344 and 0.361 for the public and private data sets, respectively. Feature importance integrated in patient representation reflected features that were also critical in prediction tasks and clinical practice. Conclusions The introduction of feature associations and feature importance facilitated an effective patient representation and contributed to prediction performance improvement and model interpretation.

show abstract

Weight-based multiple empirical kernel learning with neighbor discriminant constraint for heart failure mortality prediction

Cited by 13 publications

References 39 publications

Semi‐supervised multiple empirical kernel learning with pseudo empirical loss and similarity regularization

Semi‐supervised multiple empirical kernel learning with pseudo empirical loss and similarity regularization

Evaluation of feature scaling for improving the performance of supervised learning methods

Improving the Performance of Outcome Prediction for Inpatients With Acute Myocardial Infarction Based on Embedding Representation Learned From Electronic Medical Records: Development and Validation Study

Contact Info

Product

Resources

About