Multitask Deep Learning and Semantic Knowledge in Intelligent Healthcare
1Sejong University, Seoul, UK
2Sungkyunkwan University, Suwon, Republic of Korea
3Galala University, Suez, Egypt
4Federation University, Brisbane, Australia
Multitask Deep Learning and Semantic Knowledge in Intelligent Healthcare
Description
In recent years, the use of wearable sensors and social networking in the healthcare industry has been rapidly increasing. Wearable sensors are utilized to continuously monitor a patient’s body internally and externally to detect chronic diseases, such as Alzheimer’s disease (AD) and heart disease. Social network data are utilized to identify various factors such as emotional status and accrued stress, which can contribute to the status of a patient’s health. To date, numerous machine learning-based healthcare systems have been proposed to monitor chronic patients who use wearable sensors and social network data.
However, these systems are not well-equipped to efficiently consider the characteristics of biomedical data, which are unstructured and noisy, and are therefore difficult to handle for chronic patient monitoring. For example, wearable devices generate a huge amount of healthcare data, and to extract valuable information from data and effectively analyze data to provide quick and accurate diagnosis is challenging. Also, electronic medical records (EMRs) are unstructured and constantly increasing in size due to daily medical testing. Moreover, EMR data can be corrupted by signal artifacts such as missing values and noise, which decreases system performance and generates inaccurate results. Therefore, there is a need for an intelligent system and semantic knowledge that can automatically handle the extracted information from biomedical data, and can analyze the extracted data to identify hidden symptoms of chronic disease and predict a patient’s health condition. In addition, multitask deep learning models are required in intelligent healthcare that can process both sensors and textual data (biomedical data) for decease prediction.
The aim of this Special Issue is to address the areas of advanced deep learning modeling and semantic knowledge for intelligent healthcare. These two aspects can help the existing healthcare system process and analyze unstructured and noisy biomedical data to allow physicians to diagnose patients. This Special Issue will explore the new challenges of multitask deep learning models and semantic knowledge in intelligent healthcare. The submission of high-quality and state-of-the-art original research and review papers on this subject are encouraged.
Potential topics include but are not limited to the following:
- Ontology and multitask deep learning model in healthcare recommendation systems
- Fuzzy semantic knowledge for IoT-based healthcare systems
- Semantic knowledge-based clinical decision support system
- Multitask deep learning model with ontology for Alzheimer’s disease detection
- Multitask deep learning-based Intelligent Alzheimer’s disease recommendation systems
- Ensemble deep learning models for disease prediction
- Multitask deep learning models for processing the electronic medical records
- Natural language processing in healthcare systems for biomedical data
- Reinforcement learning and ontology models for valuation of biomedical data
- Applications of type-2 fuzzy ontology in healthcare system
- Semantic knowledge-based reasoning framework for IoT-based healthcare systems
- Ontology-based applications in intelligent healthcare
- Multitask deep learning-based social networking data analysis for patient stress detection
- Wearable sensors in healthcare monitoring systems
- Semantic knowledge-based information extraction and information retrieval in healthcare systems