Deep Learning Assisted Big Data Analytics for Biomedical Applications and Digital Healthcare
Guest Editors
Dr. Gai-Ge Wang (Lead GE)
Department of Computer Science and Technology,
Ocean University of China,
266100 Qingdao, China
Dr. Xiao-Zhi Gao
Docent (Adjunct Professor)
Machine Vision and Pattern Recognition Laboratory,
School of Engineering Science,
Lappeenranta University of Technology,
53851 Lappeenranta, Finland
Dr. Yan Pei
Associate Professor
Computer Science Division,
The University of Aizu,
Tsuruga, Ikki-machi, Aizu-Wakamatsu,
Fukushima 965-8580, Japan
Although big data and deep learning techniques are sprawled across various industries, the significance of such innovative technologies can extend to save lives. The amount of data available in the healthcare industry is vast and if put to use in the right direction can assist doctors and healthcare professionals in making informed medical decisions. Deep learning empowered big data analytics can present new opportunities in the field of biomedical and healthcare informatics, medical diagnosis, and digital healthcare. Biomedical devices and applications need to collect, store, and process large amounts of medical data every day. In such cases, big data tools can seamlessly automate the tasks of extracting useful and relevant information from large datasets with the help of deep learning and neural networks. The management of big data tasks has been assisted by parallel computing such as MapReduce by Google, Hadoop, cloud computing etc. Biomedical devices such as smart biomaterials, smart wearable sensors, biomedical imaging systems, and eye-tracking systems collect healthcare data and send them to a centralized or decentralized system for analysis. The collaboration of deep learning algorithms with big data analytics can detect existing links between the data and probable risks, aid with medical decision making and diagnosis, and improve the quality and speediness of the current healthcare systems.
Deep learning assisted big data analytics can revolutionize the digital healthcare service. Deep learning models and algorithms can effectively analyse the health data, symptoms, diagnostic results, and other health parameters of a patient. These types of disruptive healthcare technologies can enable real-time data collection and remote health monitoring through sensors or mobile health applications, predict medical conditions and risks, and suggest suitable medications or fix medical appointments. The existing deep learning models can analyse both structured and unstructured data types. This can seamlessly improve the current state of health records and patient monitoring through digital healthcare systems. Also, deep learning models can be used to identify or classify health insurance frauds. In spite of the advantages, data heterogeneity, privacy and security, traceability and accountability of medical data, adequate system architecture etc. are the existing challenges that need to be addressed through innovative techniques and disruptive technologies.
The list of topics of interest include but are not limited to the following:
- The development of deep learning empowered big data analytics systems for clinical decision making
- Deep learning techniques for biomedical and healthcare education
- Deep learning and big data n collaboration with smart computing techniques for bioinformatics and biomechanics
- The Internet of Things (IoT) and Big Data analytics for remote e-health monitoring systems
- Knowledge-based and agent-based big data models for bioinformatics systems
- Smart biomedical instruments for improved accuracy in medical diagnosis
- Big data analytics and data mining techniques for biomedical applications
- Automation of health data classification and identification using Natural Language Processing (NLP) and Deep Learning
- Enhancements in medical records and patient monitoring using cloud computing and big data analytics
- Innovative system architectures for digital healthcare systems
Big Data is the leading peer-reviewed journal covering the challenges and opportunities in collecting, analyzing, and disseminating vast amounts of data. The Journal is under the editorial leadership of Editor-in-Chief Zoran Obradovic, PhD, Temple University, and other leading investigators. View the entire editorial board.
Benefits of publishing with Big Data:
- Indexed in PubMed/MEDLINE, Web of Science JCR Science Citation Index Expanded (SCIE), among other leading indexing services
- Fast and user-friendly electronic submission
- Efficient and constructive peer review
- Prompt online publication
- High global visibility: accessible in 170 countries worldwide
- Open Access options available
Visit the Journal's website to view more information for authors including manuscript guidelines, information on available author services, and publication costs.