Manuscript Topics
Smart Internet of Healthcare Things opens up an opportunity to create a wide range of patient centred applications. Modern healthcare is structured such that there is lots of administrative and technological friction which hinders efficient data processing. For example, a medical diagnosis is based on the critical analysis of available evidence. The evidence is collected through measurements and the analysis is largely done by human practitioners. The fact that there are many practitioners and indeed even more patients provide strong evidence that we are already operating with big data. This gives rise to meta-analysis methods where we use the continuum of diagnosis and data to make abstract statements. Given access to the right data, it is possible to track the location of disease hotspots using IoT. However, with respect to big data with IoT and its distribution we are operating with one hand tied behind our back, because human centred data analysis is inefficient and inflexible. That problem applies to both data analysis for diagnosis and data analysis to establish abstract facts about a disease.

Smart Internet of Healthcare Things is one way to conceptualise and frame individual solutions to the data distribution and analysis problem. There is widespread consensus about the fact that computing machinery benefits healthcare. There is the first level of computing technology in healthcare where we have an almost mechanistic understanding of what the problem solutions should do. For example, store and communicate patient records. The second level centres on data driven decisions. On this level human experts and AI algorithms work cooperatively on improving outcomes for patients. The rationale behind this human machine cooperation comes from cost considerations and from limitations of human perception.  For example, the raw data rate, delivered by medical imaging, exceeds the available information bandwidth of a human practitioner. In other words, it is not economically feasible for a reading expert to analyse every detail contained in medical images. That might lead to intra- and inter-observer variability during the data analysis which reduces the diagnosis quality. We need medical decision support systems that extract relevant information from the available data such that the rate of evidence is matched with the available bandwidth of the human practitioner. Many deep learning (DL) techniques, like convolution neural networks (CNN), long short- term memory (LSTM), autoencoder, deep generative models and deep belief networks have been developed for this information refinement task. The third level is concerned with automated meta-analysis based on deep learning techniques. Availability of rich datasets is key for these applications for deep networks to be effective. Unfortunately, in this area healthcare regulation, which governs access to rich datasets, clashes with fundamental and exploratory research. By the very nature of investigation, research is in a weak position, because it is impossible to show preliminary results which justify access to the rich datasets. A steady flow of Smart Internet of Healthcare Things research is needed to improve that situation.

With the current call for the special issue on Smart Internet of Healthcare Thing, we plan to expand current knowledge on IoT big data for healthcare. We are especially interested in trailblazing applications which are based on the second level of computing technology. We expect these problem solutions to feature deep networks that provide focus and sustained cognition beyond current best practices. To increase the relevance of the research work, we request investigators to outline how a proposed Smart Internet of Healthcare Things solution works in a hybrid work environment where human experts work alongside AI algorithms. Transitioning from the second to the third level is also an important topic. Big data takes centre stage during this transition. Therefore, we call for papers which describe efforts to make big healthcare data available for the design of Smart Internet of Healthcare Things. The third level of computing technology in healthcare is an open research field. We address that fact by accepting well-reasoned speculative papers which might take the form of an expert review and conclude with a proposal for practical work.

The topics of this special issue include, but are not limited to the following:
• IoT Big data with machine learning for health care
• Deep learning with Big data for Internet of Healthcare Things
• Artificial Intelligence for IoT big health data
• Evolutionary algorithms for Internet of medical big data things
• Patient led health care big IoT data
• Real time Internet of healthcare things
• Deep learning methods for modern health care using IoT big data
• Integration of AI with Deep learning for modern health care with IoT
• IoT Based Big data Geo tagging with patients for Covid-19 data processing
• Internet of People Enabled Internet of Healthcare Things
• AI for Health informatics and Medical Imaging

Instructions for authors
http://www.aimspress.com/mbe/news/solo-detail/instructionsforauthors
Please submit your manuscript to online submission system
https://aimspress.jams.pub/