E-health is an emerging topic—it includes ways to provide better patient diagnosis and smarter ways to analyse medical research through the use of the internet and digital technologies. E-health plays a crucial role during the current global pandemic, allowing online, mobile and social media consultations and data processing for population health surveillance, case identification and contact tracing. E-health has leveraged the billions of mobile and other connected devices, their apps and applications of AI, machine learning and natural language processing (Budd et al., 2020) for public health worldwide and even for pain control. For example, Pujol et al. (2019) report the use of Emotion Recognition software in Smart Cities to detect and control patients' pain when they are unable to express it. E-health has flourished in the era of cloud, mobile devices and the internet of things (IoT) by providing a wide variety of services and applications, including maintenance of e-health records, electronic means or requesting diagnostic tests, online and electronic prescription of medicines, clinical decision support systems, telemedicine, health knowledge management, medical expert systems, medical image processing, virtual health care teams, health informatics, alongside health-oriented research in grid and cloud computing platforms. This, however, has raised concerns in e-health data exchange, primarily around privacy, data integrity and ethical use of data, for example, for electronic patient records (Williams et al., 2015). This is of particular concern as high-performance computing architectures and smart algorithms are becoming widespread in e-health services: these advanced technologies need to be implemented with an ethical focus, such as making sensitive data anonymous and offering more checks or services to comply with legal framework and regulations, such as GDPR. This special issue is focused on advancements in digital technologies and IoT for e-health and medical supply chain systems. It contributes state-of-the-art research and applications in e-health records management, distribution, analysis, technology development and prototypes for ensuring efficiency, privacy and trust in real-world implementations, especially in large-scale computing environments. Through a careful review and selection process, the following articles have been included—they are all of the high quality and high academic rigour, and embody novel contributions, as per the Journal's standards. The first article, by Mydukuri et al. (2022), proposes a novel technique known as least square regressive Gaussian neuro-fuzzy multi-layered data classification (LSRGNFM-LDC), which provides improved accuracy in COVID-19 early prediction based on various symptoms featuring in collected data. The technique performs with better accuracy and lower time consumption, with pre-processing applied to each input feature to eradicate irrelevant data. A wide-ranging experimental evaluation is performed using the COVID database. The second article, by Sood and Rawat (2022), proposes a novel approach to address online learning and teaching issues related to students' well-being. The authors develop and use a fog-assisted cyber–physical system that deals with various aspects of panic, including within a virtual reality platform for remote learning. Authors use F-measure, accuracy and sensitivity to evaluate the performance of logistic regression (LR) and compare it with decision tree (DT), naive Bayes (NB) and k-means clustering (KM) techniques. They show the performance measure of various classification approaches identified LR (94.6%) as the most accurate technique followed by DT (92.4%), NB (90.2%) and KM (69.7%). The third article, by Periasamy et al. (2022), takes an artificial immune system approach to propose a novel technique for osteoporosis prediction. Their proposed work determines its possibility of occurrence based on essential factors such as smoking habits or calcium level, so that people at high risk can be referred for further investigation, hence enabling care providers to take precautionary measures at the right time and avoid the early development of osteoporosis. The experiments conducted demonstrate a promising result of 94% prediction accuracy. In the fourth article, by Hamil et al. (2022), the authors propose a new telehealth system for cardiac state prediction based on the automatic classification of ECG signals and identification of arrhythmias. The system uses secured wireless transmission and classification of multiple biosignals using e-Health sensors platform and Xbee modules with Arduino Uno Raspberry Pi as acquisition and processing units, respectively, and artificial intelligence by exploiting TensorFlow and Keras tools. The system is evaluated using real recorded signals and four PhysioNet databases. Their best-attained classification accuracy is 99.56%, confirming that the designed system allows a good trade-off between low cost and performance. In the last article, by Chong et al. (2022), the authors propose a computationally efficient and accurate data analysis tool known as topic modelling, which they apply to diabetes textual health data and genomic information. Topic modelling is an unsupervised machine learning algorithm for natural language processing that identifies relationships and associations within textual data collected from various sources and formats. The purpose of this paper is to explore various methods of topic modelling, mostly the latent Dirichlet allocation (LDA) model, and their applicability to achieve precision medicine and a personalized management system for diabetic patients. Based on the selected authors' work, guest editors have summed up and suggested the following areas for futuristic research focuses: Innovation-driven by COVID-19: Based on the development work by Mydukuri et al. (2022) and Sood and Rawat (2022), innovative services and platforms were designed and implemented due to COVID-19. Researchers have consistently searched for new ways to improve our work efficiently and provide services effectively. The new systems enable advanced algorithms to function well and remotely. Modern algorithms can provide high-performance evaluation: Pioneering algorithms have been developed. The performance evaluation has been the focus for projects for Sood and Rawat (2022), Periasamy et al. (2022), Hamil et al. (2022) and Chong et al. (2022). All of the researchers have demonstrated their accuracies and performance between 94% and 99.56%. Integration between Internet of Things, AI and medical research: All selected authors have clearly demonstrated the integrations of IoT, AI and medical research with different emphasis and approaches. It will be more common to see integrations between IoT and AI and its applications to different fields and sectors. Therefore, there are prominent aspects for IoT in e-health and medical supply chain systems, which play important roles in dealing with the COVID-19 crisis. As the supplies of medical services, equipment and materials can be under threat, IoT can provide sensible solutions. Additionally, modern algorithms can offer efficiency and better accuracy to help make better decisions and medical analyses. Integration of emerging technologies can offer next-generation services for e-health and medical supply chain systems. We are grateful for the opportunities to serve the Expert Systems community. We particularly thank the Editor-in-Chief, Special Issues Editor, Journal manager, reviewers and contributors for making our special issue happen. There is no any data involved in this editorial.