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.

In the modern world, mental health disorder is one of the serious problems for every nation around the globe, especially in this Covid-19 pandemic period. These illnesses affect not only patient's mental health but also physical health, thus, reduce productivity and quality of human work. Mental health disorder is complex and also takes many forms. In this study, we pay attention to depression (unipolar and bipolar) illness. We conducted our experiment on the open dataset named Depresjon, which was collected from activity motion signals on wearable devices of 32 healthy people and 23 depressed (unipolar and bipolar) patients over several days in a row with a total of 814 samples. Firstly, we did the preprocessing data step in order to make the dataset fitting the DL model input. After that, we deployed many individual DL models to make the first predictions. Next, we generated Deep Stacked Generalization Ensemble Learning (DeSGEL) models which were able to learn how to make the best combination of predictions from previous individual well-trained models. Finally, we made a comparison among the individual and the proposed DeSGEL models. The results showed that the DeSGEL models had outperformed other corresponding individual models. Specifically, among the individual models, VGG16 had the best performance. However, the DeSGEL Resnet based showed an extremely outstanding performance over other individual and ensemble DL models. In detail, these models had Accuracy, Precision, Sensitivity, Specification, F1 score, MCC and AUC of 0.94, 0.91, 0.89, 0.96, 0.90, 0.85 and 0.92 respectively for Individual VGG16 model, and 0.96, 0.96, 0.92, 0.98, 0.94, 0.91 and 0.95 respectively for the DeSGEL Resnet based model. We found that applying Deep learning, especially DeSGEL models using activity motion signal data from wearable devices could be a prospective direction for the early diagnosis of mental health disorders.

In the modern world, with so much inherent stress, mental health disorders (MHDs) are becoming more common in every country around the globe, causing a significant burden on society and patients’ families. MHDs come in many forms with various severities of symptoms and differing periods of suffering, and as a result it is difficult to differentiate between them and simple to confuse them with each other. Therefore, we propose a support system that employs deep learning (DL) with wearable device data to provide physicians with an objective reference resource by which to make differential diagnoses and plan treatment. We conducted experiments on open datasets containing activity motion signal data from wearable devices to identify schizophrenia and mood disorders (bipolar and unipolar), the datasets being named Psykose and Depresjon. The results showed that, in both workflow approaches, the proposed framework performed well in comparison with the traditional machine learning (ML) and DL methods. We concluded that applying DL models using activity motion signal data from wearable devices represents a prospective objective support system for MHD differentiation with a good performance.

Span>Sleep is not only very important for physical health but also the mental health of human, that was addressed by many previous studies. Today, with the development of technology, which opens in the application for improving quality of sleep, such as wearable devices, artificial intelligence, neural network. In this study, we applied deep learning (DL) neural networks and smart wearable devices to predict the quality of sleep. The data was collected on students (mean age = 20.79) during 106 days by Fitbit Charge HR™ device. The results showed DL models could predict sleep quality base on physical activities in awake time.