Cloud Computing for Infectious Disease Surveillance and Control: Development and Evaluation of a Hospital Automated Laboratory Reporting System

Identification of Early Warning Signals of Infectious Diseases in Hospitals by Integrating Clinical Treatment and Disease Prevention

The global incidence of infectious diseases has increased in recent years, posing a significant threat to human health. Hospitals typically serve as frontline institutions for detecting infectious diseases. However, accurately identifying warning signals of infectious diseases in a timely manner, especially emerging infectious diseases, can be challenging. Consequently, there is a pressing need to integrate treatment and disease prevention data to conduct comprehensive analyses aimed at preventing and controlling infectious diseases within hospitals. This paper examines the role of medical data in the early identification of infectious diseases, explores early warning technologies for infectious disease recognition, and assesses monitoring and early warning mechanisms for infectious diseases. We propose that hospitals adopt novel multidimensional early warning technologies to mine and analyze medical data from various systems, in compliance with national strategies to integrate clinical treatment and disease prevention. Furthermore, hospitals should establish institution-specific, clinical-based early warning models for infectious diseases to actively monitor early signals and enhance preparedness for infectious disease prevention and control.

Pathogen Discovery in the Post-COVID Era

Pathogen discovery plays a crucial role in the fields of infectious diseases, clinical microbiology, and public health. During the past four years, the global response to the COVID-19 pandemic highlighted the importance of early and accurate identification of novel pathogens for effective management and prevention of outbreaks. The post-COVID era has ushered in a new phase of infectious disease research, marked by accelerated advancements in pathogen discovery. This review encapsulates the recent innovations and paradigm shifts that have reshaped the landscape of pathogen discovery in response to the COVID-19 pandemic. Primarily, we summarize the latest technology innovations, applications, and causation proving strategies that enable rapid and accurate pathogen discovery for both acute and historical infections. We also explored the significance and the latest trends and approaches being employed for effective implementation of pathogen discovery from various clinical and environmental samples. Furthermore, we emphasize the collaborative nature of the pandemic response, which has led to the establishment of global networks for pathogen discovery.

Trends in using IoT with machine learning in smart health assessment

The Internet of Things (IoT) provides a rich source of information that can be uncovered using machine learning (ML). The decision-making processes in several industries, such as education, security, business, and healthcare, have been aided by these hybrid technologies. For optimum prediction and recommendation systems, ML enhances the Internet of Things (IoT). Machines are already making medical records, diagnosing diseases, and monitoring patients using IoT and ML in the healthcare industry. Various datasets need different ML algorithms to perform well. It's possible that the total findings will be impacted if the predicted results are not consistent. In clinical decision-making, the variability of prediction outcomes is a major consideration. To effectively utilise IoT data in healthcare, it's critical to have a firm grasp of the various machine learning techniques in use. Algorithms for categorization and prediction that have been employed in the healthcare industry are highlighted in this article. As stated earlier, the purpose of this work is to provide readers with an in-depth look at current machine learning algorithms and how they apply to IoT medical data. 

Implementation of an automated cluster alert system into the routine work of infection control and hospital epidemiology: experiences from a tertiary care university hospital

Background

Early detection of clusters of pathogens is crucial for infection prevention and control (IPC) in hospitals. Conventional manual cluster detection is usually restricted to certain areas of the hospital and multidrug resistant organisms. Automation can increase the comprehensiveness of cluster surveillance without depleting human resources. We aimed to describe the application of an automated cluster alert system (CLAR) in the routine IPC work in a hospital. Additionally, we aimed to provide information on the clusters detected and their properties.

Methods

CLAR was continuously utilized during the year 2019 at Charité university hospital. CLAR analyzed microbiological and patient-related data to calculate a pathogen-baseline for every ward. Daily, this baseline was compared to data of the previous 14 days. If the baseline was exceeded, a cluster alert was generated and sent to the IPC team. From July 2019 onwards, alerts were systematically categorized as relevant or non-relevant at the discretion of the IPC physician in charge.

Results

In one year, CLAR detected 1,714 clusters. The median number of isolates per cluster was two. The most common cluster pathogens were Enterococcus faecium (n = 326, 19 %), Escherichia coli (n = 274, 16 %) and Enterococcus faecalis (n = 250, 15 %). The majority of clusters (n = 1,360, 79 %) comprised of susceptible organisms. For 906 alerts relevance assessment was performed, with 317 (35 %) alerts being classified as relevant.

Conclusions

CLAR demonstrated the capability of detecting small clusters and clusters of susceptible organisms. Future improvements must aim to reduce the number of non-relevant alerts without impeding detection of relevant clusters. Digital solutions to IPC represent a considerable potential for improved patient care. Systems such as CLAR could be adapted to other hospitals and healthcare settings, and thereby serve as a means to fulfill these potentials.

Logical Observation Identifiers Names and Codes (LOINC®) Applied to Microbiology: A National Laboratory Mapping Experience in Taiwan

Background and Objective: Logical Observation Identifiers Names and Codes (LOINC) is a universal standard for identifying laboratory tests and clinical observations. It facilitates a smooth information exchange between hospitals, locally and internationally. Although it offers immense benefits for patient care, LOINC coding is complex, resource-intensive, and requires substantial domain expertise. Our objective was to provide training and evaluate the performance of LOINC mapping of 20 pathogens from 53 hospitals participating in the National Notifiable Disease Surveillance System (NNDSS). Methods: Complete mapping codes for 20 pathogens (nine bacteria and 11 viruses) were requested from all participating hospitals to review between January 2014 and December 2016. Participating hospitals mapped those pathogens to LOINC terminology, utilizing the Regenstrief LOINC mapping assistant (RELMA) and reported to the NNDSS, beginning in January 2014. The mapping problems were identified by expert panels that classified frequently asked questionnaires (FAQs) into seven LOINC categories. Finally, proper and meaningful suggestions were provided based on the error pattern in the FAQs. A general meeting was organized if the error pattern proved to be difficult to resolve. If the experts did not conclude the local issue’s error pattern, a request was sent to the LOINC committee for resolution. Results: A total of 53 hospitals participated in our study. Of these, 26 (49.05%) used homegrown and 27 (50.95%) used outsourced LOINC mapping. Hospitals who participated in 2015 had a greater improvement in LOINC mapping than those of 2016 (26.5% vs. 3.9%). Most FAQs were related to notification principles (47%), LOINC system (42%), and LOINC property (26%) in 2014, 2015, and 2016, respectively. Conclusions: The findings of our study show that multiple stage approaches improved LOINC mapping by up to 26.5%.

Digital Data Sources and Their Impact on People's Health: A Systematic Review of Systematic Reviews

Background: Digital data sources have become ubiquitous in modern culture in the era of digital technology but often tend to be under-researched because of restricted access to data sources due to fragmentation, privacy issues, or industry ownership, and the methodological complexity of demonstrating their measurable impact on human health. Even though new big data sources have shown unprecedented potential for disease diagnosis and outbreak detection, we need to investigate results in the existing literature to gain a comprehensive understanding of their impact on and benefits to human health.

Objective: A systematic review of systematic reviews on identifying digital data sources and their impact area on people's health, including challenges, opportunities, and good practices.

Methods: A multidatabase search was performed. Peer-reviewed papers published between January 2010 and November 2020 relevant to digital data sources on health were extracted, assessed, and reviewed.

Results: The 64 reviews are covered by three domains, that is, universal health coverage (UHC), public health emergencies, and healthier populations, defined in WHO's General Programme of Work, 2019–2023, and the European Programme of Work, 2020–2025. In all three categories, social media platforms are the most popular digital data source, accounting for 47% (N = 8), 84% (N = 11), and 76% (N = 26) of studies, respectively. The second most utilized data source are electronic health records (EHRs) (N = 13), followed by websites (N = 7) and mass media (N = 5). In all three categories, the most studied impact of digital data sources is on prevention, management, and intervention of diseases (N = 40), and as a tool, there are also many studies (N = 10) on early warning systems for infectious diseases. However, they could also pose health hazards (N = 13), for instance, by exacerbating mental health issues and promoting smoking and drinking behavior among young people.

Conclusions: The digital data sources presented are essential for collecting and mining information about human health. The key impact of social media, electronic health records, and websites is in the area of infectious diseases and early warning systems, and in the area of personal health, that is, on mental health and smoking and drinking prevention. However, further research is required to address privacy, trust, transparency, and interoperability to leverage the potential of data held in multiple datastores and systems. This study also identified the apparent gap in systematic reviews investigating the novel big data streams, Internet of Things (IoT) data streams, and sensor, mobile, and GPS data researched using artificial intelligence, complex network, and other computer science methods, as in this domain systematic reviews are not common.

Trends in Using IoT with Machine Learning in Health Prediction System

Machine learning (ML) is a powerful tool that delivers insights hidden in Internet of Things (IoT) data. These hybrid technologies work smartly to improve the decision-making process in different areas such as education, security, business, and the healthcare industry. ML empowers the IoT to demystify hidden patterns in bulk data for optimal prediction and recommendation systems. Healthcare has embraced IoT and ML so that automated machines make medical records, predict disease diagnoses, and, most importantly, conduct real-time monitoring of patients. Individual ML algorithms perform differently on different datasets. Due to the predictive results varying, this might impact the overall results. The variation in prediction results looms large in the clinical decision-making process. Therefore, it is essential to understand the different ML algorithms used to handle IoT data in the healthcare sector. This article highlights well-known ML algorithms for classification and prediction and demonstrates how they have been used in the healthcare sector. The aim of this paper is to present a comprehensive overview of existing ML approaches and their application in IoT medical data. In a thorough analysis, we observe that different ML prediction algorithms have various shortcomings. Depending on the type of IoT dataset, we need to choose an optimal method to predict critical healthcare data. The paper also provides some examples of IoT and machine learning to predict future healthcare system trends.

Analysis of Monitoring, Early Warning and Emergency Response System for New Major Infectious Diseases in China and Overseas

In recent years, the impact of new major infectious diseases on people's normal life is becoming more and more frequent, which has brought great impact on people's life safety and social economy, especially the corona virus disease 2019, which has been sweeping the globe. Public health and disease prevention and control systems in different countries have different performances in response to the pandemic, but they all have exposed many shortcomings. Countries around the world urgently need to improve the monitoring, early warning and emergency response systems for new major infectious diseases. As the outpost and main part of medical rescue, the hospital urgently needs to establish a set of scientifically advanced emergency response mechanism that is suitable for the business process of the medical system and unified standards in order to improve the response efficiency and quality of emergency treatment.

Google Trends-based non-English language query data and epidemic diseases: a cross-sectional study of the popular search behaviour in Taiwan

OBJECTIVE

This study developed a surveillance system suitable for monitoring epidemic outbreaks and assessing public opinion in non-English-speaking countries. We evaluated whether social media reflects social uneasiness and fear during epidemic outbreaks and natural catastrophes.

DESIGN

Cross-sectional study.

SETTING

Freely available epidemic data in Taiwan.

MAIN OUTCOME MEASURE

We used weekly epidemic incidence data obtained from the Taiwan Centers for Disease Control and online search query data obtained from Google Trends between 4 October 2015 and 2 April 2016. To validate whether non-English query keywords were useful surveillance tools, we estimated the correlation between online query data and epidemic incidence in Taiwan.

RESULTS

With our approach, we noted that keywords ('common cold'), ('fever') and ('cough') exhibited good to excellent correlation between Google Trends query data and influenza incidence (r=0.898, p<0.001; r=0.773, p<0.001; r=0.796, p<0.001, respectively). They also displayed high correlation with influenza-like illness emergencies (r=0.900, p<0.001; r=0.802, p<0.001; r=0.886, p<0.001, respectively) and outpatient visits (r=0.889, p<0.001; r=0.791, p<0.001; r=0.870, p<0.001, respectively). We noted that the query ('enterovirus') exhibited excellent correlation with the number of enterovirus-infected patients in emergency departments (r=0.914, p<0.001).

CONCLUSIONS

These results suggested that Google Trends can be a good surveillance tool for epidemic outbreaks, even in Taiwan, the non-English-speaking country. Online search activity indicates that people are concerned about epidemic diseases, even if they do not visit hospitals. This prompted us to develop useful tools to monitor social media during an epidemic because such media usage reflects infectious disease trends more quickly than does traditional reporting.

A re-organizing biosurveillance framework based on fog and mobile edge computing

Biological threats are becoming a serious security issue for many countries across the world. Effective biosurveillance systems can primarily support appropriate responses to biological threats and consequently save human lives. Nevertheless, biosurveillance systems are costly to implement and hard to operate. Furthermore, they rely on static infrastructures that might not cope with the evolving dynamics of the monitored environment. In this paper, we present a reorganizing biosurveillance framework for the detection and localization of biological threats with fog and mobile edge computing support. In the proposed framework, a hierarchy of fog nodes are responsible for aggregating monitoring data within their regions and detecting potential threats. Although fog nodes are deployed on a fixed base station infrastructure, the framework provides an innovative technique for reorganizing the monitored environment structure to adapt to the evolving environmental conditions and to overcome the limitations of the static base station infrastructure. Evaluation results illustrate the ability of the framework to localize biological threats and detect infected areas. Moreover, the results show the effectiveness of the reorganization mechanisms in adjusting the environment structure to cope with the highly dynamic environment.

A systematic review on integration mechanisms in human and animal health surveillance systems with a view to addressing global health security threats

BACKGROUND

Health surveillance is an important element of disease prevention, control, and management. During the past two decades, there have been several initiatives to integrate health surveillance systems using various mechanisms ranging from the integration of data sources to changing organizational structures and responses. The need for integration is caused by an increasing demand for joint data collection, use and preparedness for emerging infectious diseases.

OBJECTIVE

To review the integration mechanisms in human and animal health surveillance systems and identify their contributions in strengthening surveillance systems attributes.

METHOD

The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Protocols (PRISMA-P) 2015 checklist. Peer-reviewed articles were searched from PubMed, HINARI, Web of Science, Science Direct and advanced Google search engines. The review included articles published in English from 1900 to 2018. The study selection considered all articles that used quantitative, qualitative or mixed research methods. Eligible articles were assessed independently for quality by two authors using the QualSyst Tool and relevant information including year of publication, field, continent, addressed attributes and integration mechanism were extracted.

RESULTS

A total of 102 publications were identified and categorized into four pre-set integration mechanisms: interoperability (35), convergent integration (27), semantic consistency (21) and interconnectivity (19). Most integration mechanisms focused on sensitivity (44.1%), timeliness (41.2%), data quality (23.5%) and acceptability (17.6%) of the surveillance systems. Generally, the majority of the surveillance system integrations were centered on addressing infectious diseases and all hazards. The sensitivity of the integrated systems reported in these studies ranged from 63.9 to 100% (median = 79.6%, n = 16) and the rate of data quality improvement ranged from 73 to 95.4% (median = 87%, n = 4). The integrated systems were also shown improve timeliness where the recorded changes were reported to be ranging from 10 to 91% (median = 67.3%, n = 8).

CONCLUSION

Interoperability and semantic consistency are the common integration mechanisms in human and animal health surveillance systems. Surveillance system integration is a relatively new concept but has already been shown to enhance surveillance performance. More studies are needed to gain information on further surveillance attributes.

Evaluation of a web-based tool for labelling potential hospital outbreaks: a mixed methods study

BACKGROUND

Labelling outbreaks in surveillance data is necessary to train advanced analytical methods for outbreak detection, but there is a lack of software tools dedicated to this task.

AIM

To evaluate the usability of a web-based tool by infection control practitioners for labelling potential outbreaks.

METHODS

A mixed methods design was used to evaluate how 25 experts from France and Canada interacted with a web-based application to identify potential outbreaks. Each expert used the application to retrospectively review 11-12 1-year incidence time series from 23 different types of micro-organism. The interactions between the users and the application were recorded and analysed using mixed effect models. The users' comments were analysed via qualitative methods.

FINDINGS

From the 240 reviews completed, 439 potential outbreaks were labelled, approximately half with a high probability. Significant heterogeneity was observed between users regarding their answers and behaviours (evaluation time, usage of the different options). A significant learning effect was also observed for the experts' interactions with the tool, but this did not seem to impact their answers. The content analysis of the comments highlighted the difficulty of early outbreak identification for practitioners, but also the potential utility of web applications such as that evaluated for routine surveillance.

CONCLUSION

The interactive web application was both usable and useful for infection control practitioners. Its implementation in routine practice could help professionals to identify potential outbreaks while creating data to train automated detection algorithms.