The increasing digitization of information, management, and retrieval systems, together with the rapid advancement of wearable devices and sensors, has led to the design, development, and broad use of effective mobile health apps and associated prediction and wellness systems. Indeed, big data and the Internet of Things (IoT) play a vital role in health-related applications, particularly in resolving disease biology at multiple scales, ranging from intracellular networks to cellular, tissue, organ, and whole-body systems. By integrating large, heterogeneous data from IoT-based devices and sensors and employing novel data mining, machine learning, and predictive analytics approaches, it is quickly becoming possible to build effective prediction systems for automatic inference and recommendation of disease diagnosis and treatment. At the same time, these approaches give rise to a number of research challenges, including security, privacy, usability, availability, and scalability, as well as the development of standards and the ability to continuously improve deployed tools and technologies “in the wild.”
This Research Topic addresses recent advances in data mining, machine learning, and predictive analytics of the growing volume of heterogeneous health data that is emerging from both real time, on-line and offline systems, and that exists in a variety of formats, types, and dimensions. The ability to capture, manage, characterize, classify, cluster, process, mine, and analyze such data represents a challenging task. Design and development of methods that enable capturing health data from IoT sensors; integrating, storing, and indexing these data; de-noising, enhancing, segmenting, and classifying the data; extracting and selecting features from the data; and transferring, sharing, and visualizing the data is essential. Key foci include security, privacy, and trust of the data and associated analytics. Also important is the governance of health data collected from and stored onmultiple, heterogeneous IoT devices, networks, platforms, and systems such as public and private clouds.
Further, this Research Topic will consider the emerging IoT ecosystem for health apps, including the design, deployment, and use of these technologies, and their associated ongoing refinement and evolution.
The increasing digitization of information, management, and retrieval systems, together with the rapid advancement of wearable devices and sensors, has led to the design, development, and broad use of effective mobile health apps and associated prediction and wellness systems. Indeed, big data and the Internet of Things (IoT) play a vital role in health-related applications, particularly in resolving disease biology at multiple scales, ranging from intracellular networks to cellular, tissue, organ, and whole-body systems. By integrating large, heterogeneous data from IoT-based devices and sensors and employing novel data mining, machine learning, and predictive analytics approaches, it is quickly becoming possible to build effective prediction systems for automatic inference and recommendation of disease diagnosis and treatment. At the same time, these approaches give rise to a number of research challenges, including security, privacy, usability, availability, and scalability, as well as the development of standards and the ability to continuously improve deployed tools and technologies “in the wild.”
This Research Topic addresses recent advances in data mining, machine learning, and predictive analytics of the growing volume of heterogeneous health data that is emerging from both real time, on-line and offline systems, and that exists in a variety of formats, types, and dimensions. The ability to capture, manage, characterize, classify, cluster, process, mine, and analyze such data represents a challenging task. Design and development of methods that enable capturing health data from IoT sensors; integrating, storing, and indexing these data; de-noising, enhancing, segmenting, and classifying the data; extracting and selecting features from the data; and transferring, sharing, and visualizing the data is essential. Key foci include security, privacy, and trust of the data and associated analytics. Also important is the governance of health data collected from and stored onmultiple, heterogeneous IoT devices, networks, platforms, and systems such as public and private clouds.
Further, this Research Topic will consider the emerging IoT ecosystem for health apps, including the design, deployment, and use of these technologies, and their associated ongoing refinement and evolution.
