Deep Ensemble Learning Approaches in Healthcare to Enhance the Prediction and Diagnosing Performance: The Workflows, Deployments, and Surveys on the Statistical, Image-Based, and Sequential Datasets

Abstract

With the development of information and technology, especially with the boom in big data, healthcare support systems are becoming much better. Patient data can be collected, retrieved, and stored in real time. These data are valuable and meaningful for monitoring, diagnosing, and further applications in data analysis and decision-making. Essentially, the data can be divided into three types, namely, statistical, image-based, and sequential data. Each type has a different method of retrieval, processing, and deployment. Additionally, the application of machine learning (ML) and deep learning (DL) in healthcare support systems is growing more rapidly than ever. Numerous high-performance architectures are proposed to optimize decision-making. As reliability and stability are the most important factors in the healthcare support system, enhancing the predicted performance and maintaining the stability of the model are always the top priority. The main idea of our study comes from ensemble techniques. Numerous studies and data science competitions show that by combining several weak models into one, ensemble models can attain outstanding performance and reliability. We propose three deep ensemble learning (DEL) approaches, each with stable and reliable performance, that are workable on the above-mentioned data types. These are deep-stacked generalization ensemble learning, gradient deep learning boosting, and deep aggregation learning. The experiment results show that our proposed approaches achieve more vigorous and reliable performance than traditional ML and DL techniques on statistical, image-based, and sequential benchmark datasets. In particular, on the Heart Disease UCI dataset, representing the statistical type, the gradient deep learning boosting approach dominates the others with accuracy, recall, F1-score, Matthews correlation coefficient, and area under the curve values of 0.87, 0.81, 0.83, 0.73, and 0.91, respectively. On the X-ray dataset, representing the image-based type, the deep aggregation learning approach shows the highest performance with values of 0.91, 0.97, 0.93, 0.80, and 0.94, respectively. On the Depresjon dataset, representing the sequence type, the deep-stacked generalization ensemble learning approach outperforms the others with values of 0.91, 0.84, 0.86, 0.8, and 0.94, respectively. Overall, we conclude that applying DL models using our proposed approaches is a promising method for the healthcare support system to enhance prediction and diagnosis performance. Furthermore, our study reveals that these approaches are flexible and easy to apply to achieve optimal performance.

Predicting CTS Diagnosis and Prognosis Based on Machine Learning Techniques

“…A growing number of studies use ultrasound to evaluate cross-sectional area (CSA) and median nerve compression at the carpal tunnel. It is currently the most accepted method for diagnosing CTS [11] and is economical compared to other imaging methods, such as magnetic resonance imaging (MRI) [12][13][14][15].…”

Machine learning applications and challenges in graft-versus-host disease: a scoping review

“…In the healthcare domain, regression is a form of supervised learning used to predict continuous values, such as assessing the risk for GVHD occurrence or predicting post-HCT mortality [16,21]. Ensemble methods combine numerous models to enhance prediction accuracy [22]. Dimensionality reduction constitutes another potential method to enhance the predictive accuracy of ML models by reducing unimportant inputs, for instance by reducing image pixels (which can be thought of as inputs or ''dimensions'') that carry no diagnostic value on CT or MRI scans [23].…”

Big Data, Decision Models, and Public Health

“…Explainability is one of the key characteristics of healthcare support systems. The second paper, “ Deep Ensemble Learning Approaches in Healthcare to Enhance the Prediction and Diagnosing Performance: The Workflows, Deployments, and Surveys on the Statistical, Image-Based, and Sequential Datasets ”, by Nguyen et al [ 16 ], proposed three deep ensemble learning (DEL) approaches, each with stable and reliable performances, that are workable for the above-mentioned data types. The results of the experiment showed that our proposed approaches achieve better performance than traditional machine learning and deep learning techniques on sequential, image-based, and sequential benchmark datasets.…”