Skip to main content

A systematic review and knowledge mapping on ICT-based remote and automatic COVID-19 patient monitoring and care



e-Health has played a crucial role during the COVID-19 pandemic in primary health care. e-Health is the cost-effective and secure use of Information and Communication Technologies (ICTs) to support health and health-related fields. Various stakeholders worldwide use ICTs, including individuals, non-profit organizations, health practitioners, and governments. As a result of the COVID-19 pandemic, ICT has improved the quality of healthcare, the exchange of information, training of healthcare professionals and patients, and facilitated the relationship between patients and healthcare providers. This study systematically reviews the literature on ICT-based automatic and remote monitoring methods, as well as different ICT techniques used in the care of COVID-19-infected patients.


The purpose of this systematic literature review is to identify the e-Health methods, associated ICTs, method implementation strategies, information collection techniques, advantages, and disadvantages of remote and automatic patient monitoring and care in COVID-19 pandemic.


The search included primary studies that were published between January 2020 and June 2022 in scientific and electronic databases, such as EBSCOhost, Scopus, ACM, Nature, SpringerLink, IEEE Xplore, MEDLINE, Google Scholar, JMIR, Web of Science, Science Direct, and PubMed. In this review, the findings from the included publications are presented and elaborated according to the identified research questions. Evidence-based systematic reviews and meta-analyses were conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework. Additionally, we improved the review process using the Rayyan tool and the Scale for the Assessment of Narrative Review Articles (SANRA). Among the eligibility criteria were methodological rigor, conceptual clarity, and useful implementation of ICTs in e-Health for remote and automatic monitoring of COVID-19 patients.


Our initial search identified 664 potential studies; 102 were assessed for eligibility in the pre-final stage and 65 articles were used in the final review with the inclusion and exclusion criteria. The review identified the following eHealth methods—Telemedicine, Mobile Health (mHealth), and Telehealth. The associated ICTs are Wearable Body Sensors, Artificial Intelligence (AI) algorithms, Internet-of-Things, or Internet-of-Medical-Things (IoT or IoMT), Biometric Monitoring Technologies (BioMeTs), and Bluetooth-enabled (BLE) home health monitoring devices. Spatial or positional data, personal and individual health, and wellness data, including vital signs, symptoms, biomedical images and signals, and lifestyle data are examples of information that is managed by ICTs. Different AI and IoT methods have opened new possibilities for automatic and remote patient monitoring with associated advantages and weaknesses. Our findings were represented in a structured manner using a semantic knowledge graph (e.g., ontology model).


Various e-Health methods, related remote monitoring technologies, different approaches, information categories, the adoption of ICT tools for an automatic remote patient monitoring (RPM), advantages and limitations of RMTs in the COVID-19 case are discussed in this review. The use of e-Health during the COVID-19 pandemic illustrates the constraints and possibilities of using ICTs. ICTs are not merely an external tool to achieve definite remote and automatic health monitoring goals; instead, they are embedded in contexts. Therefore, the importance of the mutual design process between ICT and society during the global health crisis has been observed from a social informatics perspective. A global health crisis can be observed as an information crisis (e.g., insufficient information, unreliable information, and inaccessible information); however, this review shows the influence of ICTs on COVID-19 patients' health monitoring and related information collection techniques.

Key contributions to this review literature

• We systematically review different e-Health methods applicable to remote COVID-19 patient monitoring.

• We systematically review different data collection methods and data types collected by remote monitoring technologies in remote COVID-19 patient monitoring.

• We systematically review different approaches to design and develop an effective RPM system for COVID-19 patient monitoring case,

• We systematically review different ICT techniques to automate the COVID-19 patient monitoring.

• We systematically review benefits and shortcomings of RMTs in RPM systems for the COVID-19 patient monitoring.

• Semantic mapping and representation of obtained knowledge as an ontology model.

Peer Review reports



The COVID-19 pandemic has been a catalyst for developing and adopting widespread remote health monitoring technologies [1,2,3,4]. Indicating how these technologies were implemented in the early stages of this pandemic is essential in identifying barriers to their application and adoption, especially among the vulnerable populations [1,2,3,4]. The COVID-19 pandemic has pushed telehealth into the healthcare mainstream. One area of ​​telehealth that has seen particularly significant progress over the past two years is Remote Patient Monitoring (RPM). RPM benefits healthcare providers during the pandemic by facilitating hospitals that are already congested and allowing patients to be monitored and treated at home. Additionally, RPM reduces a patient’s time in situations where the COVID-19 virus potentially can spread [4]. In addition to the pandemic, RPM can keep patients away from high-cost environments in hospitals and at home, improving the patient experience while reducing costs [4]. A report based on data before the COVID-19 pandemic suggests that routine monitoring of hospitalized patients with continuous vital sign monitoring is associated with lower mortality [3]. Thus, with the advancement of ICTs, automatic and remote COVID-19 patient monitoring can play an increasingly significant role in health care to improve patient mortality by providing timely observation and care.

Societal structures, e-Health, and organizational processes are primarily influenced by ICT-driven information networks in today's global networked society. ICT, broadly defined as the internet, platforms, networks, telephony, applications, databases, and the underlying infrastructure, is a core element of the existing social order and e-Health, especially during the global COVID-19 pandemic. The importance of ICT extends beyond detecting, tracking, monitoring, managing, treating, and understanding epidemics. ICTs are our most effective chance to maintain social order and healthcare during the pandemic. During the pandemic, IoT technology has been used to monitor the health status of patients through wireless wearable sensors in various scenarios and diseases, such as non-communicable diseases and infectious diseases. Combining IoT-related technologies with early warning indicators commonly used in hospital wards can significantly improve healthcare delivery.


People with chronic medical conditions visit hospitals and clinics more often and are at higher risk for complications from COVID-19 [4]. As of June 2020, an estimated 41% of U.S. adults had delayed or avoided medical care, and people with chronic medical conditions were more likely to stay away from a hospital or clinic [4]. Even with state-of-the-art technologies, monitoring and managing patients who may be infected with COVID-19 remains a significant challenge. The disease can deteriorate rapidly in infected patients and continuous monitoring is usually required. The essential issue of COVID-19 is timely diagnosis and breaking the chain of transmission by isolating vulnerable population groups and patients. Thus, established technologies, operational infrastructures, and nursing resources should be used to develop an RPM plan for the care of COVID-19 patients. RPM has made considerable strides in collecting chronic patient data remotely [4]. An e-Health approach to remote monitoring of COVID-19 infected patients has many benefits, including early detection, reduced risk of transmission, efficient resource allocation, continuous monitoring, patient convenience, and data collection for research purposes. These motivations make remote monitoring an important tool in managing the COVID-19 pandemic.

ICTs are well-positioned to reduce the potential spread of disease and prevent the healthcare system from being overloaded with at-home COVID-19 screening, diagnosis, and monitoring. ICTs in e-Health are used to facilitate RPM [1,2,3,4,5,6] by offering the patients an ability to record, track, govern, analyze, and view their automatically recorded and self-reported data [7, 8]. ICT tools emphasize prospective information flow from patients to health professionals. The specific types of information collected may vary depending on the Remote Monitoring Technologies (RMTs) and the healthcare provider's requirements. However, the goal is to gather comprehensive and accurate data to assess the patient's condition remotely and provide appropriate care. The RMTs are a special category of ICT and use Internet-of-things (IoT) devices (e.g., wearable, and non-wearable sensors) for data collection. The nature of collected personal and health data is essential in COVID-19 automatic and remote patient surveillance and decision making. Adequate sensor and non-sensor data combined with data analytics approaches with Artificial Intelligence (AI) algorithms may improve predictive capabilities and allow for timely monitoring and management of health issues. The additional context of wearables can enable providers to make more informed decisions about a patient's care plan or treatment [4].

Remote monitoring has revolutionized healthcare by connecting remote and hard-to-reach areas [3,4,5,6]. The IoT-based health system [9, 10] has the potential of continuous health state monitoring both indoors and outdoors. Especially in the COVID-19 pandemic, it is imperative to have an automatic remote monitoring system to assess patients remotely and control their spread in advance. AI algorithms are helpful in processing sensory observations and medical images for automatic vital health sign predictive modeling [9, 10]. Therefore, IoT and AI can be promising and enabling health technologies to automate RPM processes. The motivation reveals that an automatic RPM process can be invaluable in remote patient monitoring and care; however, a robust system design is critical [9, 10]. Considering this, designing and developing an effective RPM system can enhance patient care, improve health outcomes, increase accessibility, ensure continuity of care, reduce healthcare costs, and protect patient privacy.

Automating the monitoring of COVID-19 patients using ICTs can bring benefits such as efficiency, real-time monitoring, remote access, scalability, timely intervention, data analysis, resource optimization, and contribution to research and surveillance efforts [1,2,3,4,5,6, 9, 10]. These motivations can drive the adoption of automation technologies to improve patient care and effectively manage the COVID-19 pandemic. However, a successful collaboration with IT professionals, healthcare providers, and relevant stakeholders is important to guarantee successful functioning and deployment of the automated monitoring systems. Furthermore, by recognizing the strengths and weaknesses of RMTs, healthcare systems and providers can leverage their strengths while addressing the challenges to ensure the successful implementation and use of RPM systems.

Aim of the study

This systematic literature review aims to identify the relevant methods and different information management techniques to achieve ICT-based automatic and remote patient monitoring in COVID-19 infected patients care. In this context, the following research questions (RQs) have been formulated:

  • RQ1: Which e-Health methods are used for remote COVID-19 infected patient monitoring?

  • RQ2: What type of information is collected by RMTs in remote COVID-19 patient monitoring?

  • RQ3: What are different approaches to design and develop an effective RPM system?

  • RQ4: How to use ICTs to automate the COVID-19 patient monitoring?

  • RQ5: What are advantages and drawbacks of RMTs in RPM systems?


We performed a systematic literature review to formulate a detailed synopsis of the current literature on the topic in a reproducible and transparent way. We accomplished our systematic literature review following Wendler's proposals [11] to search online scientific databases. Systematic reviews convey a scientific synthesis of proof. It uses systematic and transparent strategies to comprehend, select, and strictly assess related basic research and extract and explore facts from the research covered in the evaluation [12]. We used the PRISMA [13] (see Supplementary Material—1) and Rayyan [14] evidence-based framework for the systematic review and meta-analyses. Afterward, we used the Scale for the Assessment of Narrative Review Articles (SANRA) [15] to assess the articles in the final round.

Search strategy

We identified relevant publications in the following electronic databases EBSCOhost, Scopus, ACM, Nature, SpringerLink, IEEE Xplore, MDPI, Google Scholar, JMIR, Web of Science, and PubMed. This study’s search strategy was created in collaboration with the library of the University of Agder (UiA) in Norway. We identified related search keywords using the MeSH terms, synonyms, keywords from relevant articles, and self-determined search terms. The tools, such as “EndNote (V. X9)”, “DOAJ”, “Sherpa/Romeo”, and “Microsoft Excel (MS Office 365 V. 16.x)” were used to effectively search, collect, and select related articles. We filtered our literature search with the search string: (COVID-19 or COVID 19) AND (remote monitoring OR automatic monitoring) AND (Technologies) AND (health monitoring), and the used filters to narrow down the search list were: Abstract, Free full text, Case Reports, Classical Article, Clinical Conference, Clinical Study, Clinical Trial, Clinical Trial Protocol, Comparative Study, Evaluation Study, Meta-Analysis, Observational Study, Randomized Controlled Trial, Review, Systematic Review, Humans, and English.

Eligibility criteria

This study strictly focuses on research articles related to automatic and remote monitoring of COVID-19 infected patients. Therefore, we aimed to include qualitative, quantitative, and mixed studies that described COVID-19 patients’ remote and automatic health monitoring methods with ICTs and associated existing and emerging techniques. The eligibility criteria for article selection are described in Table 1.

Table 1 The Eligibility criteria for article selection

Data extraction

Data was collected in a structured format from a list of selected full-text research articles. In collaboration with the library of UiA, two researchers (AC and JD) conducted the electronic database searches independently. Furthermore, AC and JD cross-checked and hand-searched a few articles from online scientific databases to avoid missed articles during the initial search method. AC and JD prepared independent Microsoft Excel files to extract the following important information for article screening after the initial search – Title, Author names, type of the article (RPM or Automatic RPM), Publication Year, Scientific Database, Keywords, Abstract, Keynote from the Conclusion, Access Type (Open Access or UiA Subscribed Access, or Restricted Access), Technology Used, Technology Focus (e.g., deep learning, machine learning, IoT and wearables, IoT and Non-wearables, ontology), Study Focus (methodologies, information management, technology, challenges, new ideation), and Monitoring Subject (COVID-19 infected patients or other types of patients, e.g., recovered). AC and JD then filtered out their common search articles and prepared a master search list. MR and AP helped AC and JD to narrow down the master search list further by manual screening.

Quality scoring for final selection

We divided and distributed initially selected articles among the authors to complete the screening using the Rayyan collaboration and research tool. After the individual screening, results were reviewed by other authors to eliminate differences between reviewers. The eligible peer review articles were identified by the manual review, quality score, and manual assessment of reference lists of related articles. First, we checked the Title, Keywords, Abstract, and Conclusion of the articles. We then independently reviewed each article to see if it qualified for final inclusion. In the prefinal assessment, for data extraction, we maintained an Excel spreadsheet with the following fields—Title, Reference, Author, Nature of the paper (review, conceptual, methodology, survey, and implementation), Year, Country of research, Key terms, Keywords, Publication channel, Technology use, Peer-reviewed, Key findings (outcome, measures, processes, methods, theory, components, and results), Nature of assessment (qualitative, quantitative, or both), Type of monitoring, Key challenges, and Quality score based on SANRA. The quality of the included articles was assessed using the SANRA 0–2-point scale. We graded individual papers based on the six quality parameters defined in (Table 2).

Table 2 SANRA scaling, based on the quality parameters

Individual quality parameters were further categorized on a 0–2–point scale. Finally, we calculated the mean score of the six quality parameters. The number of studies included in the pre-final assessment was 102, with a SANRA score greater than 1.8.

In the final assessment, 65 articles achieved a SANRA score greater than the cut-off of 1.9. Table 3 describes the research topics and types of scientific articles identified and selected in the final assessment. [2,3,4, 7,8,9,10,11,12,13,14,15,16,17,18,19], and [20] are studies relevant for study narration and formulation and are not a part of 65 papers selected through this systematic literature review.

Table 3 Research topics and count of articles with SANRA score > 1.9

Knowledge representation

Our key findings for each RQ are presented in the form of ontology mapping (an object-oriented paradigm). Ontologies play a crucial role in knowledge representation and are essential for enabling intelligent systems to understand and work with complex, domain-specific information. They provide a foundation for building knowledge-based applications that can automate reasoning, decision-making, and information retrieval tasks. We designed and developed the ontology mapping in the Protégé (v. 5.x) open-source software and visualized the ontology using the OWLViz tool in Protégé [16, 17]. In the object-oriented representation, owl:Thing acts as a global parent class and the arrows define a hierarchical relationship (IS-A) between the concepts [18, 19].


Selected articles and corresponding research contribution(s)

The electronic search resulted in 664 articles, including 196 duplicates. In the pre-final stage, we selected 102 articles for full-text review after checking the abstract, conclusion, length of the paper, and the availability of the full text. In the final stage, we included peer-reviewed publications only, resulting in 65 peer-reviewed articles from different countries, such as the USA, China, Canada, UK, Portugal, Australia, India, Italy, Japan, Oman, Egypt, Saudi Arabia, Brazil, Bangladesh, Iran, Iraq, Turkey, Tunisia, Germany, and France. The articles are related to ICT-based remote and/or automatic COVID-19 infected patient monitoring, AI decision making models, e-Health methods, wearable IoTs, ontology-based IoT, information management, usefulness, and associated challenges. Most of the selected articles are indexed in PubMed (n = 52; 80%). The PRISMA flow diagram in Fig. 1 summarizes the entire process of article searching, filtering, and selection. Figure 2 illustrates the percentage (%) of qualitative, quantitative, and mixed studies.

Fig. 1
figure 1

PRISMA flow diagram of the performed systematic literature review

Fig. 2
figure 2

Percentage (%) of qualitative, quantitative, and mixed studies

Table 4 groups selected studies according to their focus and categories based on the key areas in ICT-based remote and automatic COVID-19 patient monitoring and care, comprehensive literature search with appropriate keywords and search terms related to each category to ensure comprehensive coverage, summarization of main outcomes, results, and conclusions of the study related to the specific research category, implications of the research for healthcare practice, policy, and future research directions. According to Table 4, the research focus can be classified into nine categories to understand the articles better to answer the RQs. In Table 4, we have cited sources of each category appropriately to provide an accurate and reliable summary.

Table 4 Included studies, their research category and key findings

Supplementary Table 1 (see Supplementary Material—2) describes selected publication types, e-Health methods (such as telehealth, telemedicine, and mHealth), used RMTs for required health data collection, and the collected data types. The data has been collected with different RMTs, such as smartphone applications, wearable devices (such as, smartwatches, fitness trackers, temperature patches), connected health devices (such as, pulse oximeters, glucose monitors, blood pressure monitors), and remote monitoring platforms. Moreover, Supplementary Table 1 represents monitoring of symptoms, medication adherence, and physiological parameters (or vital health signs, such as heart rate, blood pressure, respiratory rate, body temperature, glycemic response, oxygen saturation) from COVID-19 infected patients under remote care settings.

Supplementary Table 2 (see Supplementary Material—3) describes adopted approaches to designing and developing an RPM system. It is crucial to recognize that these approaches are not isolated from one another (i.e., mutually exclusive). Therefore, a combination of different approaches can be employed to create a comprehensive and effective remote patient monitoring system. The process of selecting an approach depends on the specific requirements, resources, and technological infrastructure in a particular healthcare setting. By following these approaches, the design and development of a RPM system can be enhanced to precisely meet the needs of patients and healthcare providers, facilitate effective remote patient monitoring, and finally improve the outcomes of patients and enhance healthcare delivery.

In medicine a sign is defined as an objective, observable health problem that another person can recognize; whereas a symptom (e.g., Pain, fever, fatigue, and difficulty breathing) is the manifestation of a medical condition that a patient is experiencing. Symptoms can be subjective (when they are experienced only by the patient) and objective (when they can be observed by a healthcare provider). They are not the same as diseases as they are simply indications that something is wrong with the body. A wide variety of factors, such as infections, injuries, and chronic medical conditions can cause them. The most critical medical signs are vital signs, such as heart rate, respiratory rate, body temperature, glycemic response, and blood pressure. Symptoms are chronic, relapsing, and remission. In this review, we identified diagnostic signs and chronic symptoms. Vital signs help to diagnose specific disease symptoms. According to the review, RPM can be perfectly integrated with telehealth when a specific health condition of a COVID-19 patient needs to be monitored. The ability to monitor certain aspects of a COVID-19 patient's health from home has become an increasingly popular telehealth option and can reduce patients' travel costs and infection risk.

Supplementary Table 3 (see Supplementary Material—4) describes different study designs, statistical analysis on population data or public datasets in automatic and/or remote COVID-19 patient monitoring systems, corresponding research outcomes, and AI model performances (if applicable). We have divided the study design into the following three categories: Random controlled study, empirical study, and mixed study (a combination of both). The random controlled studies primarily include a qualitative evaluation, whereas the empirical studies focus on a quantitative evaluation. The studies included in Supplementary Table 3 belong to the "Observational study program" category as mentioned in Table 4.

Supplementary Table 4 (see Supplementary Material—5) elaborates on studies related to the automatic RPM process. RMTs offer several advantages and drawbacks. Table 5 explains the benefits, and Table 6 presents the barriers to RMTs for COVID-19 patients.

Table 5 Benefits of using RMTs
Table 6 Barriers to use RMTs

Answering to RQs

The research findings captured from Table 4 to Table 6 helped to answer our identified RQs. This systematic literature review identified 12 studies contributing to answering RQ1 (see Supplementary Table 1); 24 studies contribute to our RQ2 (see Supplementary Table 1); 28 studies contribute to our RQ3 (see Supplementary Table 2); 19 studies contribute to RQ4 (see Supplementary Table 4); 28 studies contribute to RQ5 (see Table 5 and Table 6 (several studies contributed to more than one RQ).

COVID-19 results in comorbidities (e.g., respiratory symptoms, cardiovascular symptoms, diabetic symptoms); thus, a continuous health monitoring is important [20]. A wide range of ICTs have been used to improve public health strategies, and the pandemic has increased the use of e-Health methods. To answer RQ1 we reviewed different e-Health methods and digital transformations as a part of remote health monitoring in COVID-19 patients. The identified e-Health methods for ICT-based remote COVID-19 patient screening, diagnosis, monitoring, planning, and consultation have been Telehealth, Telemedicine, and mHealth (see Fig. 3). The collection and assessment of data are essential to monitor, measure, assess, and diagnose COVID-19 risks associated with the care and monitoring of an infected patient (home quarantined or hospitalized).

Fig. 3
figure 3

The semantic representation of eHealth methods for ICT-based remote COVID-19 patient monitoring and management

For RQ2, we reviewed different data types and their collection process with RMTs for remote COVID-19 patient monitoring. Continuous assessment of health and wellness data is essential for automatic detection of COVID-19 disease and predicting the severity for better decision-making and readiness. Several e-Health methods have been deployed with a focus on assessing and managing data related to patient’s context, personal information, biomarkers, health, and wellness. Vital signs and symptoms associated with COVID-19 have been collected with smart wearable devices, smartphones, video consultation, online questionnaires, and feedback generations over on-premises or cloud platforms. Smartphone applications help to collect daily lifestyle data. Body temperature collected with smart biosensors is an early warning sign of infection and a symptom of fever. ECG, HRV, PPG, respiratory rate, oxygen saturation, and blood pressure collected with smart biosensors are important for cardiovascular symptoms and stress management. Retinal data and glycemic response are important for diabetes symptoms. Figure 4 gives a structural representation of the collected data.

Fig. 4
figure 4

The semantic representation of processed data collected in RPM of COVID-19

For RQ3 we identified different approaches to designing and developing RPM processes (see Fig. 5). We found IoT platforms to be a promising technology for rapid diagnosis, dynamic monitoring and tracking, and better treatment and control without spreading the COVID-19 virus to non-infected individuals. Solutions such as HMP, computerized analyzers, tele consultation models, IoT-HMS framework, IoT-Remote patient monitoring framework, and AI-based decision-making helped stakeholders, such as governments, experts, medical staff, and citizens to prevent and respond to remote COVID-19 patient monitoring, incidence management and care.

Fig. 5
figure 5

The semantic representation of RPM design and development approaches in COVID-19 patient monitoring

The success of the RPM program in COVID-19 patient monitoring has been dependent on the identification of the key characteristics, appropriate implementation of RMTs and ICT techniques. RQ4 reviewed ICT techniques (e.g., IoT, Deep Learning, Machine Learning, and Federated Learning) for an automatic and remote COVID-19 patient monitoring (see Fig. 6). The machine learning and deep learning techniques have been beneficial for analyzing cough, voice, and breathing acoustic, image (e.g., chest X-ray, CT-scan) and signal processing (e.g., time-series), image segmentation (e.g., U-Net), predictive modeling based on real-time symptom, vital signs and medical records, pattern recognition and clustering of symptoms against the following performance metrics – accuracy, precision, recall, F1-score, and area-under-curve. The proposed federated model [32] ensures accurate long-term AI-based decision-making using federated batch machine learning algorithms installed on the cloud infrastructure. The IoT technologies helped to design and develop simple, reliable, and low-cost microcontroller-based wireless monitoring system that can automatically record vital physiological data. In continuous and real-time patient monitoring, all the collected health and wellness data can be transferred to the backend server or cloud storage using an IoT communication and secure protocols for future decision-making and alert generation. The used deep learning algorithms have been LSTM, 1D-CNN, 2D-CNN, RNN, transfer learning (e.g., VGG-16, ResNet50), and GRU. The associated machine learning algorithms have been unsupervised (K-Means, LDA), and supervised (ANN, LR, SVM, BR, NB, KNN, and CART).

Fig. 6
figure 6

The semantic representation of ICT techniques used in automatic and remote COVID-19 patient monitoring

For RQ5 we identified associated benefits and drawbacks with the usage of RMTs in the RPM program for COVID-19 remote patient monitoring and care. In particular, the literature review has highlighted the requirements, opportunities, and drawbacks for RMTs in the RPM healthcare system.


Principle findings

The COVID-19 pandemic has shown the importance of RPM and management to provide timely care [63, 64]. Automation in remote monitoring is a promising and challenging research task. RPM involves RMTs that allow healthcare services to track individuals [21, 41, 64, 70]. An automatic RPM system requires a cyclic process of data collection, data processing for health status monitoring, decision-making based on the processed data, recommendation generation, and action to be performed based on the care input by the patients and/or caregivers [6, 21, 41, 42, 64, 70]. Here, we discuss the findings related to identified research questions.

The advent of electronics for wearable sensors and emerging telemedicine tools helped to address remote COVID-19 patient monitoring, and management deficiencies [1, 5, 63, 64]. Telehealth offered multiple modes (e.g., telecare) and means (e.g., IoT devices) of interaction for COVID-19 patients and physicians. Telehealth attempted to meet the needs of COVID-19 patients by sensing disease progression and preventing life-threatening conditions [530, 63, 67, 73]. In literature, the words "telemedicine" and "telehealth" are frequently used. The relationship between telehealth and telemedicine varies depending on the source and context; however, telemedicine is a subcategory of telehealth. Telehealth is a broader term that includes both clinical services and a broader range of remote healthcare services and activities. Telehealth includes telemedicine conversations, but it also includes remote patient monitoring, health education, administrative functions, and non-healthcare aspects that are telecommunicated through technology. Telemedicine is concerned with the utilization of telecommunication technology for remote healthcare services, such as virtual conversations between patients and providers that lead to diagnoses, treatments, and follow-up care. Telemedicine primarily apprehensions the transmission of clinical services over the internet.

Heart disease, diabetes, chronic obstructive pulmonary disease, and obesity are increased risk of severe illness from COVID-19. Therefore, continuous monitoring of vital physiological parameters and symptoms are essential for COVID-19 patients. Therefore, Supplementary Table 1 represents different types of data, purpose, and their nature (processed and/or raw) and their collection methods. It necessitates the transformation in patient tracking and caregiving through the integration of remote technologies. Recent advancements in ICT techniques, e-Health methods, and continuous remote monitoring have become essential in managing health symptoms and vital health signs of COVID-19 patients in the remote care settings [6, 72, 73, 75,76,77]. These technologies have changed the landscape of RPM and become more useful than ever. By leveraging exciting developments in personalization, digitization, health, and patient engagement, healthcare providers have improved health outcomes. In remote monitoring, necessary digital tools are required to collect health metrics and make the recorded data usable, reasonable, and applicable. Data exchange and recorded health and wellness data via secure messaging technologies with store-and-forward services had the lowest penetration rates in virtual COVID-19 disease management. The choice of telehealth communication services and interaction patterns in use cases, disease categories, and applications has played a key role in the success of telehealth, telemedicine, and mHealth management infrastructure and its impact on a better future healthcare system [21, 63, 64, 71].

This systematic literature review has discussed the contributions of ontology, IoT, and AI to propose complementary and multidisciplinary technologies to combat COVID-19, providing opportunities for more comprehensive research and accelerated knowledge acquisition and knowledge representation [21, 27, 45, 46, 56, 65, 68]. Supplementary Table 2 presents different RPM design approaches (e.g., design science), design framework, algorithm design, and various initiatives such as mobile apps, web platforms, and smart analytics for early detection and general COVID-19 health management. AI plays a crucial role in measuring, assessing, and diagnosing risk.

According to Supplementary Table 3 and Supplementary Table 4, AI has been a useful tool to detect and predict, at a large-scale, COVID-19 infected patients health conditions in a remote care setting. However, the exponentially rapid increase in the number of patients requires efficient, fast, and accurate predictions of the possible outcomes of COVID-19 infected patients for appropriate treatment using AI techniques. There is an urgent need to integrate AI technologies into wireless infrastructure (IoT/IoMT), real-time detection, and processing of end-user devices [25, 26, 31, 39, 53]. ICTs have become one of the essential components in developing connected smart IoMT devices. The data generated by IoMT devices is increasing rapidly due to the number of connected devices [31, 39]. The state of the COVID-19 outbreak has led to the need for IoMT, which can provide effective automated monitoring solutions. Therefore, analyzing IoMT data is extremely important. AI is gaining attention in automation applications based on big data generated by IoMT devices. AI and IoMT-driven telemedicine technology is a new-generation telehealth solution for remote and automated COVID-19 patient monitoring, which will redefine RPM solutions with AI and IoMT technology.

Remote monitoring of COVID-19 patients at home has raised trust issues related to RMT's ethical data collection; therefore, transparency and data protection must be guaranteed [6, 21, 41, 42, 63, 64, 70, 75, 78, 79]. Using ICT to monitor COVID-19 patients presents several ethical challenges [21, 70, 76]. One of the major concerns is the possibility that personal health information may be collected and processed in a manner that violates the privacy of patients. Information collected should be used solely for the purpose of providing medical care and should not be shared with third parties without the consent of the patient. When deploying ICT to monitor patients, there is also the risk of data breaches and cyberattacks. To ensure that patients' personal and medical information is protected, appropriate security measures must be in place. The inability of some patients to access technology or an internet connection may result in disparities in the quality of care. No matter what their technological capabilities are, all patients should have access to the same level of care. Moreover, information collected via remote monitoring may not be as accurate as information collected through in-person assessment. Therefore, the information collected should be reliable, and patients should receive appropriate follow-up care based on the information collected.

Chronic conditions have additional complexity and require long-term data to identify trends in COVID-19 patient conditions or measure the effectiveness of remote monitoring programs [6, 24, 70,71,72]. According to our review, ICT solutions such as wearables are closing the gap between clinical diagnostic devices and short-term fitness wearables by creating solutions that take clinical sensors, connect them, and use them for long-term data collection, and enhance the data availability for AI-assisted analytics. Combining continuous data with RPM and data analysis approaches (see Supplementary Table 2), AI can improve predictive capabilities for more timely intervention and management of remote patient monitoring. AI and sensor fusion technologies, including IoT/IoMT solutions, have shown promising results with enhanced potential for remote monitoring through ideal wearable solutions for long-term monitoring of COVID-19 patients- (see Supplementary Table 3 and Supplementary Table 4). The use of remote monitoring systems and associated technologies can complement face-to-face consultations and potentially increase COVID-19 patients' autonomy in treatment and disease management to decrease the no-show rate and the patients’ waiting times.

The use of wearable mobile devices as an early detection and real-time monitoring tool can enable remote monitoring to address unprecedented challenges. According to Tables 8 and 9, the RPM systems are of excellent help not only to COVID-19 patients but also to healthcare professionals. However, RPM still only works for some afflicted people, depending on their location and remote access capabilities. Additionally, physicians need to use extra effort to engage patients and motivate them to use RPM. Another disadvantage of RMP is that the device's accuracy needs to be proven [6, 21, 24, 70,71,72]. If the possibility of inaccuracy exists, the effectiveness of RPM remains uncertain.

Challenges in rapid technology deployment

Healthcare services implementing RPM should anticipate the challenges associated with rapid technology deployment (see Table 6) and provide appropriate support to address these challenges, including strategies to support consumers' use of health information technology. Despite remarkable technological advances (see Table 5), extensive hospital and home remote monitoring services are not widely used by the healthcare system. Before healthcare systems can benefit from remote monitoring and automated patient management services, they must overcome the following hurdles – a. selection of algorithms: continuous monitoring can improve safety and reduce clinician workload. This approach should be combined with better algorithms to use automatic monitoring and clinical data to diagnose the cause of clinical deterioration and recommend treatment, b. task management: a service line must be established to monitor and manage patients with COVID-19. Generally, a group of physicians, such as emergency medical technicians or hospital physicians, execute a home monitoring program, develop protocols, admit, and monitor patients, and manage the quality of care. This service line should also have a research focus to understand better if, how, why, and in whom these therapies improve quality and value, c. data privacy: the synergy of IoT/IoMT, AI, and Federated Learning faces challenges related to privacy, latency, and lack of context. Emerging edge intelligence technologies may provide an opportunity to address such issues. AI algorithms should be used to make better and automatic predictions from limited public health data. Security and privacy methods can be used to protect sensitive health information, d. limited knowledge: there is evidence of reluctance to manage telehealth systems due to low technology adoption rates and a lack of support from public or private entities in developing technology to provide health services that meet people's needs, e. limited funding: insufficient hospital funding and a lack of patient attention pose challenges in hotspots. By providing care delivered remotely, we can focus on in-person care in the hospital or at home only for those who need it. It could enable systems to expand, protect lives and safeguard economic activity, f. collaboration across vendors: value maximization is required when healthcare systems combine and integrate multiple technologies such as monitoring, telemonitoring, chatbots, triage and scheduling, and g. standards: appropriate selection and enrollment of protocols that match patient risk and needs, with a menu of monitoring types and durations, required monitoring, and responses to patient deteriorating conditions or abnormal readings, g. protocols must address patient needs through therapies such as home health care services, pharmacy services, physical therapy, laboratory, and imaging testing, and telemedicine physician or clinic services, h. the Role of AI: Even with clinical evidence, RPM can improve efficiency without AI. With AI, we can improve efficiency by orders of magnitude. The AI-based RPM identifies patients potentially needing attention based on AI analysis of data. With the help of AI, RPM has the potential to be an essential part of the solution to soaring healthcare costs due to an aging population. AI-based RPM identifies patients who may need attention based on AI data analysis. Additionally, an AI decision support module can also be used alone to diagnose such COVID-19 patients. For example, AI can automatically change a patient's medication, direct a patient to a lab for additional testing, or advise a patient on diet and exercise, and i. Population demography: Most of the reported studies focus on adults and very limited studies focused on elderly population. A diversity in study is needed.


We have identified the following limitations in this literature review – a. the availability and quality of the relevant studies have been limited on this topic, b. the lack of related technical and empirical evidence-based studies on high-quality randomized controlled trials, c. studies scoped on this topic use various designs, methodologies, and outcome measures, leading to heterogeneity in the data which causes challenges to directly compare and combine study outcomes, hypothetically affecting the meta-analysis and generalizability of the findings, d. major studies have focused on specific patient populations, settings, or regions, limiting the generalizability of the findings to a broader range of COVID-19 patients, and e. the COVID-19 pandemic is still relatively recent, and many remote patient monitoring studies have focused on short-term outcomes; therefore, it has limited long-term data available on the effectiveness and sustainability of ICT-based remote monitoring for COVID-19 patients. Despite these limitations, this systematic literature review provides a valuable synthesis of the available evidence in ICT-based remote and automatic COVID-19 patient monitoring and care.


This systematic literature review has revealed different e-Health methods, associated RMTs, approaches, different collected data types, adoption of ICT tools for automatic remote patient monitoring, benefits, and constraints for RMTs in COVID-19 case. Digital health tools can improve efficiency, accessibility, and quality of care. A wide range of wearable sensors has shown great potential for non-invasive, early, and on-time diagnosis and monitoring of COVID-19 patients. Advances in smart wearable sensors or devices represent an excellent opportunity to accelerate the transformation of connected medical technology.

RPM can be a good alternative for COVID-19 patient monitoring based on their health risks and needs. While improved home monitoring may enhance safety and value, empirical evidence to support the benefits of this approach is limited. Home monitoring and the home hospital model offer the potential to transform care and enable many hospital patients to receive care at home. However, healthcare systems must partner with technology producers to accelerate learning and create excellent value for patients, clinicians, and healthcare organizations. More research is required to understand what strategic features are helpful, their cost-effectiveness, and relevancy to different age groups. The choice of e-Health communication services plays a vital role in the success of remote disease management. Further research should focus on the security and privacy of COVID-19 monitoring systems that handle sensitive patient data.

AI-based disease management is likely to be highly controversial among regulators and healthcare professionals, depending on how much freedom AI is given to determine remote COVID-19 patient treatment. However, it also has the potential to free human doctors from routine disease management tasks, allowing them to focus on patients who do not respond to standard treatment options. It will enable doctors to treat many more patients than they currently have. Diagnosis requires a doctor; however, their treatment can be largely automated once a patient is diagnosed. As remote patient monitoring systems evolve into AI-driven disease management systems, we can radically improve the availability and quality of care and help address the healthcare cost crisis. Collaboration that leverages the expertise of clinicians, data scientists, engineers, and nurses will be critical to facilitate this progress and may be even more desirable if a further wave of the pandemic occurs.

Availability of data and materials

All data generated or analysed during this study are included in this published article [and its supplementary information files].



Artificial Intelligence


Artificial Neural Network


Convolutional Neural Network


Decision Tree Regression


Biometric Monitoring Technologies




Bayesian Ridge


COVID-19 Disease Diagnosis


Area Under the Curve


Mean Squared Error


Mean Absolute Error


Deep Learning


Electronic Health


Global Positioning System


Early Warning Score 2




Genetic Algorithm


Home Monitoring Program


Information and Communication Technology


Internet of Things




K-Nearest Neighbors


Long-short-Term Memory


Logistic Regression


Linear Discriminant Analysis


Mobile Health


Machine Learning


Naive Bayesian


Preferred Reporting Items for Systematic Reviews and Meta-Analyses


Remote Monitoring Technology


Research Questions


Remote Patient Monitoring


Recurrent Neural Network


Scale for the Assessment of Narrative Review Articles


Oxygen Saturation


Support Vector Machine


University of Agder


  1. Oliver J, Dutch M, Rojek A, Putland M, Knott JC. Remote COVID-19 patient monitoring system: a qualitative evaluation. BMJ Open. 2022;12(5):e054601.

    PubMed  Google Scholar 

  2. Chatterjee A, Gerdes MW, Martinez SG. Statistical explorations and univariate timeseries analysis on COVID-19 datasets to understand the trend of disease spreading and death. Sensors. 2020;20(11):3089.

    CAS  PubMed  PubMed Central  Google Scholar 

  3. Pronovost PJ, Cole MD, Hughes RM. Remote Patient Monitoring During COVID-19: An Unexpected Patient Safety Benefit. JAMA. 2022;327(12):1125–6.

    CAS  PubMed  Google Scholar 

  4. Taylor L. Covid-19: Hong Kong reports world’s highest death rate as zero covid strategy fails. BMJ. 2022;376(o420):35177535.

    Google Scholar 

  5. Hutchings OR, Dearing C, Jagers D, Shaw MJ, Raffan F, Jones A, Ritchie AG. Virtual health care for community management of patients with COVID-19 in Australia: observational cohort study. J Med Internet Res. 2021;23(3):e21064.

    PubMed  PubMed Central  Google Scholar 

  6. Yang S, Fichman P, Zhu X, Sanfilippo M, Li S, Fleischmann KR. The use of ICT during COVID-19. Proc Assoc Inf Sci Technol. 2020;57(1):e297 Epub 2020 Oct 22. PMID: 33173819; PMCID: PMC7645918.

    Article  PubMed  PubMed Central  Google Scholar 

  7. Bouabida, K., Malas, K., Talbot, A., Desrosiers, M. È., Lavoie, F., Lebouché, B., ... & Pomey, M. P. (2021). Remote Patient Monitoring Program for COVID-19 Patients Following Hospital Discharge: A Cross-Sectional Study. Front Digit Health, 153.

  8. Chatterjee A, Prinz A, Gerdes M, Martinez S. Digital Interventions on Healthy Lifestyle Management: Systematic Review. J Med Internet Res. 2021;23(11):e26931.

    PubMed  PubMed Central  Google Scholar 

  9. Lukas H, Xu C, Yu Y, Gao W. Emerging Telemedicine Tools for Remote COVID-19 Diagnosis, Monitoring, and Management. ACS Nano. 2020;14(12):16180–93. (Epub 2020 Dec 14).

    Article  CAS  PubMed  Google Scholar 

  10. Greiwe J, Nyenhuis SM. Wearable Technology and How This Can Be Implemented into Clinical Practice. Curr Allergy Asthma Rep. 2020;20(8):36.

    Article  PubMed  PubMed Central  Google Scholar 

  11. Wendler R. The maturity of maturity model research: A systematic mapping study. Inf Softw Technol. 2012;54(12):1317–39.

    Google Scholar 

  12. Xiao Y, Watson M. Guidance on conducting a systematic literature review. J Plan Educ Res. 2019;39(1):93–112.

    Google Scholar 

  13. Moher D, Altman DG, Liberati A, Tetzlaff J. PRISMA statement. Epidemiology. 2011;22(1):128.

    PubMed  Google Scholar 

  14. Ouzzani M, Hammady H, Fedorowicz Z, Elmagarmid A. Rayyan—a web and mobile app for systematic reviews. Syst Rev. 2016;5(1):1–10.

    Google Scholar 

  15. Baethge C, Goldbeck-Wood S, Mertens S. SANRA—a scale for the quality assessment of narrative review articles. Research integrity and peer review. 2019;4(1):1–7.

    Google Scholar 

  16. Chatterjee A, Prinz A, Gerdes M, Martinez S. An automatic ontology-based approach to support logical representation of observable and measurable data for healthy lifestyle management: Proof-of-concept study. J Med Internet Res. 2021;23(4):e24656.

    PubMed  PubMed Central  Google Scholar 

  17. Chatterjee A, Prinz A. Personalized Recommendations for Physical Activity e-Coaching (OntoRecoModel): Ontological Modeling. JMIR Med Inform. 2022;10(6):e33847.

    PubMed  PubMed Central  Google Scholar 

  18. Chatterjee A, Pahari N, Prinz A, Riegler M. Machine learning and ontology in eCoaching for personalized activity level monitoring and recommendation generation. Sci Rep. 2022;12(1):1–26.

    Google Scholar 

  19. Chatterjee, A., Pahari, N., Riegler, M., & Prinz, A. (2022, October). LSTM Step Prediction and Ontology-Based Recommendation Generation in Activity eCoaching. In 2022 18th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob) (pp. 13–18). IEEE.

  20. The Problem of COVID-19 and Chronic Disease. Webpage:

  21. Wong CK, Ho DTY, Tam AR, Zhou M, Lau YM, Tang MOY, Tong RCF, Rajput KS, Chen G, Chan SC, Siu CW, Hung IFN. Artificial intelligence mobile health platform for early detection of COVID-19 in quarantine subjects using a wearable biosensor: protocol for a randomised controlled trial. BMJ Open. 2020;10(7):e038555.

    Article  PubMed  PubMed Central  Google Scholar 

  22. Iwendi C, Bashir AK, Peshkar A, Sujatha R, Chatterjee JM, Pasupuleti S, Jo O. COVID-19 patient health prediction using boosted random forest algorithm. Front Pub Health. 2020;8:357.

    Google Scholar 

  23. Messaoud S, Bouaafia S, Maraoui A, Khriji L, Ammari AC, Machhout M. Virtual Healthcare Center for COVID-19 Patient Detection Based on Artificial Intelligence Approaches. Can J Infect Dis Med Microbiol. 2022;2022:6786203.

    PubMed  PubMed Central  Google Scholar 

  24. Jing, S., Qian, Q., She, H., Shan, T., Lu, S., Guo, Y., & Liu, Y. (2021). A Novel Prediction Method Based on Artificial Intelligence and Internet of Things for Detecting Coronavirus Disease (COVID-19). Secur Commun Netw, 2021.

  25. Kollu PK, Kumar K, Kshirsagar PR, Islam S, Naveed QN, Hussain MR, Sundramurthy VP. Development of advanced artificial intelligence and IoT automation in the crisis of COVID-19 Detection. J Healthc Eng. 2022;2022:1987917.

    PubMed  PubMed Central  Google Scholar 

  26. Rohmetra, H., Raghunath, N., Narang, P., Chamola, V., Guizani, M., & Lakkaniga, N. R. (2021). AI-enabled remote monitoring of vital signs for COVID-19: methods, prospects and challenges. Computing, 1–27.

  27. Otoom M, Otoum N, Alzubaidi MA, Etoom Y, Banihani R. An IoT-based framework for early identification and monitoring of COVID-19 cases. Biomed Signal Process Control. 2020;62:102149.

    PubMed  PubMed Central  Google Scholar 

  28. Un KC, Wong CK, Lau YM, Lee JCY, Tam FCC, Lai WH, Siu CW. Observational study on wearable biosensors and machine learning-based remote monitoring of COVID-19 patients. Sci Rep. 2021;11(1):1–9.

    Google Scholar 

  29. Tang Z, Hu H, Xu C, Zhao K. Exploring an efficient remote biomedical signal monitoring framework for personal health in the COVID-19 pandemic. Int J Environ Res Public Health. 2021;18(17):9037.

    CAS  PubMed  PubMed Central  Google Scholar 

  30. Mehrdad S, Wang Y, Atashzar SF. Perspective: Wearable Internet of Medical Things for remote tracking of symptoms, prediction of health anomalies, implementation of preventative measures, and control of virus spread during the era of COVID-19. Front Robot AI. 2021;8:610653.

    PubMed  PubMed Central  Google Scholar 

  31. Singh A, Kaur A, Dhillon A, Ahuja S, Vohra H. Software system to predict the infection in COVID‐19 patients using deep learning and web of things. Softw Pract Exp. 2022;52(4):868–86.

    PubMed  Google Scholar 

  32. Kallel A, Rekik M, Khemakhem M. Hybrid-based framework for COVID-19 prediction via federated machine learning models. J Supercomput. 2022;78(5):7078–105.

    PubMed  Google Scholar 

  33. Chen Z, Li M, Wang R, Sun W, Liu J, Li H, Wang X. Diagnosis of COVID-19 via acoustic analysis and artificial intelligence by monitoring breath sounds on smartphones. J Biomed Inform. 2022;130:104078.

    PubMed  PubMed Central  Google Scholar 

  34. Gupta, G., Salehi, A. W., Sharma, B., Kumar, N., & Vaidya, P. (2022). COVID-19: automated detection and monitoring of patients worldwide using machine learning. In Modeling, Control and Drug Development for COVID-19 Outbreak Prevention (pp. 731–761). Springer, Cham.

  35. Jaber MM, Alameri T, Ali MH, Alsyouf A, Al-Bsheish M, Aldhmadi BK, Jarrar MT. Remotely monitoring COVID-19 patient health condition using metaheuristics convolute networks from IoT-based wearable device health data. Sensors. 2022;22(3):1205.

    CAS  PubMed  PubMed Central  Google Scholar 

  36. Amini N, Shalbaf A. Automatic classification of severity of COVID-19 patients using texture feature and random forest based on computed tomography images. Int J Imaging Syst Technol. 2022;32(1):102–10.

    PubMed  Google Scholar 

  37. Kassania SH, Kassanib PH, Wesolowskic MJ, Schneidera KA, Detersa R. Automatic detection of coronavirus disease (COVID-19) in X-ray and CT images: a machine learning based approach. Biocybern Biomed Eng. 2021;41(3):867–79.

    PubMed  PubMed Central  Google Scholar 

  38. Nandy S, Adhikari M. Intelligent health monitoring system for detection of symptomatic/asymptomatic COVID-19 patient. IEEE Sens J. 2021;21(18):20504–11.

    CAS  Google Scholar 

  39. Tan, L., Yu, K., Bashir, A. K., Cheng, X., Ming, F., Zhao, L., & Zhou, X. (2021). Toward real-time and efficient cardiovascular monitoring for COVID-19 patients by 5G-enabled wearable medical devices: a deep learning approach. Neural Comput Appl 1–14.

  40. Hemdan, E. E. D., El-Shafai, W., & Sayed, A. (2022). CR19: A framework for preliminary detection of COVID-19 in cough audio signals using machine learning algorithms for automated medical diagnosis applications. J Ambient Intell Humanized Comput 1–13.

  41. Mirjalali S, Peng S, Fang Z, Wang CH, Wu S. Wearable Sensors for Remote Health Monitoring: Potential Applications for Early Diagnosis of Covid-19. Adv Mater Technol. 2021;3:2100545. Epub ahead of print.

    Article  CAS  Google Scholar 

  42. Seshadri DR, Davies EV, Harlow ER, Hsu JJ, Knighton SC, Walker TA, Voos JE, Drummond CK. Wearable Sensors for COVID-19: A Call to Action to Harness Our Digital Infrastructure for Remote Patient Monitoring and Virtual Assessments. Front Digit Health. 2020;23(2):8.

    Article  Google Scholar 

  43. Jiang W, Majumder S, Kumar S, Subramaniam S, Li X, Khedri R, Deen MJ. A wearable tele-health system towards monitoring COVID-19 and chronic diseases. IEEE Rev Biomed Eng. 2021;15:61–84.

    Google Scholar 

  44. Khan MM, Mehnaz S, Shaha A, Nayem M, Bourouis S. IoT-based smart health monitoring system for COVID-19 patients. Comput Math Methods Med. 2021;2021:8591036.

    PubMed  PubMed Central  Google Scholar 

  45. Paganelli AI, Velmovitsky PE, Miranda P, Branco A, Alencar P, Cowan D, Morita PP. A conceptual IoT-based early-warning architecture for remote monitoring of COVID-19 patients in wards and at home. Internet Things. 2022;18:100399.

    Google Scholar 

  46. Al Bassam N, Hussain SA, Al Qaraghuli A, Khan J, Sumesh EP, Lavanya V. IoT based wearable device to monitor the signs of quarantined remote patients of COVID-19. Informatics in medicine unlocked. 2021;24:100588.

    PubMed  PubMed Central  Google Scholar 

  47. Ullah F, Haq HU, Khan J, Safeer AA, Asif U, Lee S. Wearable iots and geo-fencing based framework for COVID-19 remote patient health monitoring and quarantine management to control the pandemic. Electronics. 2021;10(16):2035.

    CAS  Google Scholar 

  48. Leese MI, Bernstein JP, Dorociak KE, Mattek N, Wu CY, Beattie Z, Hughes A. Older adults’ daily activity and mood changes detected during the COVID-19 pandemic using remote unobtrusive monitoring technologies. Innov Aging. 2021;5(4):igab032.

    PubMed  PubMed Central  Google Scholar 

  49. Ushigome E, Yamazaki M, Hamaguchi M, Ito T, Matsubara S, Tsuchido Y, Fukui M. Usefulness and safety of remote continuous glucose monitoring for a severe COVID-19 patient with diabetes. Diabetes Technol Ther. 2021;23(1):78–80.

    CAS  PubMed  Google Scholar 

  50. de Morais Barroca Filho, I., Aquino, G., Malaquias, R. S., Girão, G., & Melo, S. R. M. (2021). An IoT-based healthcare platform for patients in ICU beds during the COVID-19 outbreak. Ieee Access, 9, 27262-27277

  51. Atta RM. Cost-effective vital signs monitoring system for COVID-19 patients in smart hospital. Heal Technol. 2022;12(1):239–53.

    Google Scholar 

  52. Jain, A., Prasad, J., & Velho, D. B. D. V. (2022, March). covIoT: Integrated Patient Monitoring And Sanitization System. In 2022 International Conference on Communication, Computing and Internet of Things (IC3IoT) (pp. 1–6). IEEE.

  53. Tripathy, H. K., Mishra, S., Suman, S., Nayyar, A., & Sahoo, K. S. (2022). Smart COVID-shield: an IoT driven reliable and automated prototype model for COVID-19 symptoms tracking. Computing, 1–22.

  54. Raposo A, Marques L, Correia R, Melo F, Valente J, Pereira T, Silva HPD. e-CoVig: a novel mHealth system for remote monitoring of symptoms in COVID-19. Sensors. 2021;21(10):3397.

    CAS  PubMed  PubMed Central  Google Scholar 

  55. Nasser, N., Emad-ul-Haq, Q., Imran, M., Ali, A., Razzak, I., & Al-Helali, A. (2021). A smart healthcare framework for detection and monitoring of COVID-19 using IoT and cloud computing. Neural Comput Appl 1–15.

  56. Sharma N, Mangla M, Mohanty SN, Gupta D, Tiwari P, Shorfuzzaman M, Rawashdeh M. A smart ontology-based IoT framework for remote patient monitoring. Biomed Signal Process Control. 2021;68:102717.

    Google Scholar 

  57. Ullah N, Khan JA, Almakdi S, Khan MS, Alshehri M, Alboaneen D, Raza A. A novel CovidDetNet deep learning model for effective COVID-19 infection detection using chest radiograph images. Appl Sci. 2022;12(12):6269.

    CAS  Google Scholar 

  58. Pancaldi F, Pezzuto GS, Cassone G, Morelli M, Manfredi A, D’Arienzo M, Sebastiani M. VECTOR: An algorithm for the detection of COVID-19 pneumonia from velcro-like lung sounds. Comput Biol Med. 2022;142:105220.

    CAS  PubMed  PubMed Central  Google Scholar 

  59. Kör, H., Erbay, H., & Yurttakal, A. H. (2022). Diagnosing and differentiating viral pneumonia and COVID-19 using X-ray images. Multimedia Tools Appl 1–17.

  60. Bargshady G, Zhou X, Barua PD, Gururajan R, Li Y, Acharya UR. Application of CycleGAN and transfer learning techniques for automated detection of COVID-19 using X-ray images. Pattern Recogn Lett. 2022;153:67–74.

    Google Scholar 

  61. Akyol K, Şen B. Automatic Detection of Covid-19 with Bidirectional LSTM Network Using Deep Features Extracted from Chest X-ray Images. Interdiscip Sci. 2022;14(1):89–100.

    CAS  PubMed  Google Scholar 

  62. Zandehshahvar M, van Assen M, Maleki H, Kiarashi Y, De Cecco CN, Adibi A. Toward understanding COVID-19 pneumonia: A deep-learning-based approach for severity analysis and monitoring the disease. Sci Rep. 2021;11(1):1-10.y.

    Google Scholar 

  63. Chowdhury D, Hope KD, Arthur LC, Weinberger SM, Ronai C, Johnson JN, Snyder CS. Telehealth for Pediatric Cardiology Practitioners in the Time of COVID-19. Pediatr Cardiol. 2020;41(6):1081–91. (Epub 2020 Jul 12 PMID: 32656626).

    Article  PubMed  PubMed Central  Google Scholar 

  64. Galiero R, Pafundi PC, Nevola R, Rinaldi L, Acierno C, Caturano A, Salvatore T, Adinolfi LE, Costagliola C, Sasso FC. The Importance of Telemedicine during COVID-19 Pandemic: A Focus on Diabetic Retinopathy. J Diabetes Res. 2020;14(2020):9036847.

    Article  Google Scholar 

  65. Shanbehzadeh M, Kazemi-Arpanahi H, Kalkhajeh SG, Basati G. Systematic review on telemedicine platforms in lockdown periods: Lessons learned from the COVID-19 pandemic. J Educ Health Promot. 2021;30(10):211.

    Article  Google Scholar 

  66. Lapão LV, Peyroteo M, Maia M, Seixas J, Gregório J, Da Silva MM, Correia JC. Implementation of digital monitoring services during the COVID-19 pandemic for patients with chronic diseases: design science approach. J Med Internet Res. 2021;23(8):e24181.

    PubMed  PubMed Central  Google Scholar 

  67. Baldinger M, Heinrich A, Adams T, Martens E, Dommasch M, Müller A, Schmidt G. TELECOVID: remote vital signs monitoring of COVID-19 risk patients in home isolation with an in-ear wearable. IEEE Pervasive Computing. 2021;20(2):58–62.

    Google Scholar 

  68. Coffey JD, Christopherson L.A, Glasgow AE, Pearson KK, Brown JK, Gathje SR, Haddad TC. Implementation of a multisite, interdisciplinary remote patient monitoring program for ambulatory management of patients with COVID-19. NPJ Digit Med. 2021;4(1):1–11.

    Google Scholar 

  69. Tabacof L, Kellner C, Breyman E, Dewil S, Braren S, Nasr L, Putrino D. Remote patient monitoring for home management of coronavirus disease 2019 in New York: a cross-sectional observational study. Telemed EHealth. 2021;27(6):641–8.

    Google Scholar 

  70. Houlding E, Mate KKV, Engler K, Ortiz-Paredes D, Pomey MP, Cox J, Hijal T, Lebouché B. Barriers to Use of Remote Monitoring Technologies Used to Support Patients With COVID-19: Rapid Review. JMIR Mhealth Uhealth. 2021;9(4):e24743.

    Article  PubMed  PubMed Central  Google Scholar 

  71. Choudhary P, Bellido V, Graner M, Altpeter B, Cicchetti A, Durand-Zaleski I, Kristensen FB. The Challenge of Sustainable Access to Telemonitoring Tools for People with Diabetes in Europe: Lessons from COVID-19 and Beyond. Diabetes Ther. 2021;12(9):2311–27. (Epub 2021 Aug 14).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  72. Brahmbhatt DH, Ross HJ, Moayedi Y. Digital Technology Application for Improved Responses to Health Care Challenges: Lessons Learned From COVID-19. Can J Cardiol. 2022;38(2):279–91. (Epub 2021 Dec 1).

    Article  PubMed  Google Scholar 

  73. Manta C, Jain SS, Coravos A, Mendelsohn D, Izmailova ES. An Evaluation of Biometric Monitoring Technologies for Vital Signs in the Era of COVID-19. Clin Transl Sci. 2020;13(6):1034–44. (Epub 2020 Oct 12 PMID: 32866314).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  74. Vindrola-Padros C, Sidhu MS, Georghiou T, Sherlaw-Johnson C, Singh KE, Tomini SM, Fulop NJ. The implementation of remote home monitoring models during the COVID-19 pandemic in England. EClinicalMedicine. 2021;34:100799.

    PubMed  PubMed Central  Google Scholar 

  75. Peyroteo M, Ferreira IA, Elvas LB, Ferreira JC, Lapão LV. Remote Monitoring Systems for Patients With Chronic Diseases in Primary Health Care: Systematic Review. JMIR Mhealth Uhealth. 2021;9(12):e28285.

    Article  PubMed  PubMed Central  Google Scholar 

  76. Thomas MJ, Lal V, Baby AK, Rabeeh Vp M, James A, Raj AK. Can technological advancements help to alleviate COVID-19 pandemic? a review. J Biomed Inform. 2021;117:103787. (Epub 2021 Apr 20).

    Article  PubMed  PubMed Central  Google Scholar 

  77. Kane H, Gourret Baumgart J, El-Hage W, Deloyer J, Maes C, Lebas MC, Marazziti D, Thome J, Fond-Harmant L, Denis F. Opportunities and Challenges for Professionals in Psychiatry and Mental Health Care Using Digital Technologies During the COVID-19 Pandemic: Systematic Review. JMIR Hum Factors. 2022;9(1):e30359. (PMID: 34736224).

    Article  PubMed  PubMed Central  Google Scholar 

  78. Fahy N, Williams GA, Habicht T, Köhler K, Jormanainen V, Satokangas M, Tynkkynen LK, Lantzsch H, Winklemann J, Cascini F, Belvis AGD, Morsella A, Poscia A, Ricciardi W, Silenzi A, Farcasanu D, Scintee SG, Vladescu C, Delgado EB, Pueyo EA, Romero FE. Use of digital health tools in Europe: Before, during and after COVID-19. Copenhagen (Denmark): European Observatory on Health Systems and Policies; 2021.

  79. De Simone V, Guarise P, Guardalben S, Padovani N, Tondelli S, Sandrini D, Visentin E, Zanotto G. Telecardiology during the Covid-19 pandemic: past mistakes and future hopes. Am J Cardiovasc Dis. 2020;10(2):34–47.

    PubMed  PubMed Central  Google Scholar 

  80. Ding X, Clifton D, Ji N, Lovell NH, Bonato P, Chen W, Zhang YT. Wearable sensing and telehealth technology with potential applications in the coronavirus pandemic. IEEE Rev Biomed Eng. 2020;14:48–70.

    Google Scholar 

  81. Panicacci, S., Ruiu, A., Lubrano, A., Donati, M., Olivelli, M., & Fanucci, L. (2022, March). SatNav E@ syCare Telemedicine Platform in the Management of Covid-19 Patients: Field Trial Results. In 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops) (pp. 757–762). IEEE.

Download references


The authors acknowledge the funding and infrastructure from the University of Agder, Norway, to carry out this research as a part of Digital Infrastructure for Robust and Scalable Patient Monitoring in Pandemic Response Situations (DIPAR) project for a duration 2020-2022 (funded by the Research Council of Norway). Thanks to Professor (Dr.) Margunn Aanestad, University of Agder, Norway (Faculty of Health and Sport Sciences) for supervising the project.


This research work is funded by University of Agder (UiA), Norway, and UiA will pay the open-access (OA) charge.

Author information

Authors and Affiliations



AC: Conceptualization, Ideation, Methodology, Software, Literature search, Formal analysis, Literature review, Literature Screening, Investigation, Writing—original draft, Writing—review & editing. AP: Literature review, Writing—review & editing. MR: Literature review, Writing—review & editing. JD: Literature search, Literature screening, and Literature review.

Corresponding author

Correspondence to Ayan Chatterjee.

Ethics declarations

Ethics approval and consent to participate

Not applicable.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Additional file 1. 

We added a PRISMA 2009 Checklist document as a part of this systematic literature review.

Additional file 2. 

Adopted publication types, e-Health methods, RMTs, and corresponding collected data as a part of RPM in COVID-19 case.

Additional file 3. 

Adopted approaches to design and develop an RPM program.

Additional file 4. 

Studies on trials and corresponding outcomes with model performances (if applicable).

Additional file 5. 

Studies related to automatic RPM process.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit The Creative Commons Public Domain Dedication waiver ( applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chatterjee, A., Prinz, A., Riegler, M.A. et al. A systematic review and knowledge mapping on ICT-based remote and automatic COVID-19 patient monitoring and care. BMC Health Serv Res 23, 1047 (2023).

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: