Call For Papers: "Emerging Challenges and Advancements In Health Informatics with New Generation Unsupervised Learning"


Artificial intelligence (AI) is a highly effective method for fighting the COVID-19 pandemic. AI can be described as machine learning (ML), natural language processing (NLP), and computer vision applications used to teach computers to use large data-based models for pattern recognition, description, and prediction. Such functions can help identify (diagnose), forecast, and describe (treat) infections and assist in controlling their socioeconomic impacts. The pandemic has resulted in the loss of many lives as well as economic losses. There was much confusion surrounding predictions of both the effectiveness and negative implications of non-pharmaceutical and pharmaceutical solutions. A worthy goal is to strengthen AI, one of the most popular data analytics tools developed in the past decade or so, to help reduce these uncertainties. Data scientists have been willing to take up the opportunity. In AI, machine learning and its subset(deep learning) methods are employed in various applications to solve multiple problems that occur due to uncertainty; however, these problems are solved with the help of data collected from past events. Most machine learning and deep learning algorithms are trained to address the supervised learning problem, where the algorithms know the prediction requirements.

On the other hand, the clustering methods of data mining algorithms can group unknown data into structures. Based on knowledge discovery, this method finds a way to cluster the data without supervision. Most of these algorithms use distance metrics to complete the process. Combining machine learning and clustering algorithms may also be a potential solution for this problem. A benefit of unsupervised learning, which pushes us toward in-depth research, is its ability to tackle challenges that humans might find impossible either due to limited capacity or bias. The feeding of raw data sets into health-based data analytics systems can be progressive, while using unsupervised data sets allows for better predictive learning, which is beneficial when it comes to segmenting patients. It can easily separate data into groups without any form of bias that might otherwise hinder a human who may have pre-existing knowledge about the nature of the patients’ data. In addition, it comes closer to mimicking cognitive functions carried out by a human brain; it deduces patterns from around the world and slowly learns more about the world over time. Even though unsupervised learning has enormous potential to unravel the possibilities of next-generation AI in health informatics, there are a few implementation hurdles that must be overcome.

The focus of this special issue is to provide a platform and opportunity for researchers to find solutions to problems relating to both the current pandemic and future hazards. This special issue addresses the emerging challenges and advancements in health informatics based on the next generation of self-learning methodologies.

Subject Coverage

Topics may include but are not limited to the following:

  • Deep clustering network for health informatics
  • The selection of diverse datasets and problems to test and validate research outcomes
  • The exploration of the optimal deep learning methodology for data classifications 
  • Current approaches on deep clustering 
  • Generative adversarial network models for self-learning 
  • Challenges regarding adjusting hyper parameters, lack of interpretability, and lack of theoretical frameworks 
  • Joint unsupervised learning methodologies 
  • Health information standards and regulations
  • Security, privacy, and disparities in health information access
  • Knowledge sharing in online health communities
  • Affordances and constraints of health information technologies
  • Ubiquitous computing for chronic condition management
  • Consumer access to health information
  • Electronic medical records
  • Traditional data generated in past decades now being used with modern algorithms and process segment/classification
  • An optimized strategy to implement intelligent automation in analyzing data
  • Adequate parameter selection to avoid over fitting or underfitting
  • Data science and health analytics

Important Dates

Submission of manuscripts: June 5, 2021

Notification to authors: September 10, 2021

Final versions due: December 25, 2021

Please prepare your manuscript with the instructions found here:

Submissions should be sent through the online system at Authors should choose the section ‘Theme Issue 2021: Emerging Challenges and Advancements In Health Informatics with New Generation Unsupervised Learning’ when submitting papers (see FAQ article on how to submit to a theme issue:

Invited/accepted articles with corresponding authors from institutions that are not JMIR institutional members are subject to the regular JMIR Article Processing Fee (APF). For this theme issue, the APF is discounted by 20%.

Please see the fee schedule for details:

Guest Editors

Prof Dr B Nagaraj, Rathinam Group of Institutions, India

Prof Dr Danilo Pelusi, University of Teramo, Italy

Prof Valentina E Balas, Aurel Vlaicu University of Arad, Romania