Trends in infection-related patient safety incident reporting before and during the COVID-19 pandemic in Korea.

Purpose: The purpose of this study was to analyze the trends and characteristics of infection-related patient safety incident reporting before and during the coronavirus disease 2019 (COVID-19) pandemic in Korea, and to provide basic data for preventing infection-related patient safety incidents and improving their management. Methods: A cross-sectional analysis of secondary national data (Patient Safety Reporting Data) was conducted. In total, 517 infection-related patient safety incidents reported from 2018 to 2021 were analyzed. Changes in the number of reports before and during the COVID-19 pandemic and differences in variables related to infection-related patient safety incidents were analyzed using the chi-square test and independent t-test in SPSS 29.0. Results: This study found that infection-related patient safety incidents decreased during the COVID-19 pandemic compared to before the pandemic. Furthermore, incident-related characteristics, such as the type of healthcare organization, severity of harm, and post-incident actions, changed during the COVID-19 pandemic. Conclusion: The many changes in the infection control system and practices during the COVID-19 pandemic may have contributed to a decrease in the reporting of infection-related patient safety incidents. It is hoped that longitudinal studies on patient safety incidents related to the pandemic and analytical studies on factors influencing patient safety incidents will continue to be conducted to prevent and improve patient safety incidents. [ FROM AUTHOR] Copyright of Journal of Korean Biological Nursing Science is the property of Korean Society of Biological Nursing Science and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Information Technology, Healthcare Data and Analytics, and Clinical Engineering

During a health crisis and a pandemic, information technology, analytics, and clinical engineering departments within an acute-care hospital setting play a significant role in the delivery of healthcare services. Electronic health record systems have become equally as important as the technology infrastructure that underpins them and the healthcare service itself. Both healthcare workers and patients require network access for effective communications, both within the hospital and beyond. Collaboration tools within and across departments at all levels have become essential for business continuity and clinical care. During the COVID-19 crisis, the virtual workspace became the "new normal” for healthcare workers, and virtual care through telehealth platforms, for patients and caregivers, enabled a quality of care to be maintained while still protecting both patients and healthcare workers throughout the infectious pandemic surge. Providing such services required agile project planning, along with a collaborative team effort, to quickly and effectively respond to expanded patient capacity within SBH. This chapter documents how the IT department at SBH Health System was able to successfully adapt to the demanding requirements of the initial COVID-19 surge in New York City, and it further highlights the key lessons learned to help recognize the tools needed to assist enhanced clinical innovations during a health crisis, especially an infectious pandemic. © SBH Health System 2022.

Estimating the Under-ascertainment of COVID-19 cases in Toronto, Ontario, March to May 2020.

Background: Public health surveillance data do not always capture all cases, due in part to test availability and health care seeking behaviour. Our study aimed to estimate under-ascertainment multipliers for each step in the reporting chain for COVID-19 in Toronto, Canada. Design and methods: We applied stochastic modeling to estimate these proportions for the period from March 2020 (the beginning of the pandemic) through to May 23, 2020, and for three distinct windows with different laboratory testing criteria within this period. Results: For each laboratory-confirmed symptomatic case reported to Toronto Public Health during the entire period, the estimated number of COVID-19 infections in the community was 18 (5th and 95th percentile: 12, 29). The factor most associated with under-reporting was the proportion of those who sought care that received a test. Conclusions: Public health officials should use improved estimates to better understand the burden of COVID-19 and other similar infections.

Monitoring the security of audio biomedical signals communications in wearable IoT healthcare.

The COVID-19 pandemic has imposed new challenges on the healthcare industry as hospital staff are exposed to a massive coronavirus load when registering new patients, taking temperatures, and providing care. The Ebola epidemic of 2014 is another example of a pandemic which a hospital in New York decided to use an audio-based communication system to protect nurses. This idea quickly turned into an Internet of Things (IoT) healthcare solution to help to communicate with patients remotely. However, it has grabbed the attention of criminals who use this medium as a cover for secret communication. The merging of signal processing and machine-learning techniques has led to the development of steganalyzers with very higher efficiencies, but since the statistical properties of normal audio files differ from those of purely speech audio files, the current steganalysis practices are not efficient enough for this type of content. This research considers the Percent of Equal Adjacent Samples (PEAS) feature for speech steganalysis. This feature efficiently discriminates the least significant bit stego speech samples from clean ones with a single analysis dimension. A sensitivity of 99.82% was achieved for the steganalysis of 50% embedded stego instances using a classifier based on the Gaussian membership function.

Telehealth Utilization among Low Income Population during COVID-19: An Analysis of COVID-19 Research Database

The COVID-19 Research Database is a public data platform. This platform is a result of private and public partnerships across industries to facilitate data sharing and promote public health research. We analyzed its linked database and examined claims of 2,850,831 unique persons to investigate the influence of demographic, socio-economic, and behavioral factors on telehealth utilization in the low-income population. Our results suggest that patients who had higher education, income, and full-time employment were more likely to use telehealth. Patients who had unhealthy behaviors such as smoking were less likely to use telehealth. Our findings suggest that interventions to bolster education, employment, and healthy behaviors should be considered to promote the use of telehealth services. © 2023 IEEE Computer Society. All rights reserved.

Implementing a Data Integration Infrastructure for Healthcare Data – A Case Study

Conducting epidemiologic research usually requires a large amount of data to establish the natural history of a disease and achieve meaningful study design, and interpretations of findings. This is, however, a huge task because the healthcare domain is composed of a complex corpus and concepts that result in difficult ways to use and store data. Additionally, data accessibility should be considered because sensitive data from patients should be carefully protected and shared with responsibility. With the COVID-19 pandemic, the need for sharing data and having an integrated view of the data was reaffirmed to identify the best approaches and signals to improve not only treatments and diagnoses but also social answers to the epidemiological scenario. This paper addresses a data integration scenario for dealing with COVID-19 and cardiovascular diseases, covering the main challenges related to integrating data in a common data repository storing data from several hospitals. Conceptual architecture is presented to deal with such approaches and integrate data from a Portuguese hospital into the common repository used to explore data in a standardized way. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Managing Security of Healthcare Data for a Modern Healthcare System.

The advent of Artificial Intelligence (AI) and the Internet of Things (IoT) have recently created previously unimaginable opportunities for boosting clinical and patient services, reducing costs and improving community health. Yet, a fundamental challenge that the modern healthcare management system faces is storing and securely transferring data. Therefore, this research proposes a novel Lionized remora optimization-based serpent (LRO-S) encryption method to encrypt sensitive data and reduce privacy breaches and cyber-attacks from unauthorized users and hackers. The LRO-S method is the combination of hybrid metaheuristic optimization and improved security algorithm. The fitness functions of lion and remora are combined to create a new algorithm for security key generation, which is provided to the serpent encryption algorithm. The LRO-S technique encrypts sensitive patient data before storing it in the cloud. The primary goal of this study is to improve the safety and adaptability of medical professionals' access to cloud-based patient-sensitive data more securely. The experiment's findings suggest that the secret keys generated are sufficiently random and one of a kind to provide adequate protection for the data stored in modern healthcare management systems. The proposed method minimizes the time needed to encrypt and decrypt data and improves privacy standards. This study found that the suggested technique outperformed previous techniques in terms of reducing execution time and is cost-effective.

Lessons learned from developing a COVID-19 algorithm governance framework in Aotearoa New Zealand

Aotearoa New Zealand's response to the COVID-19 pandemic has included the use of algorithms that could aid decision making. Te Pokapū Hātepe o Aotearoa, the New Zealand Algorithm Hub, was established to evaluate and host COVID-19 related models and algorithms, and provide a central and secure infrastructure to support the country's pandemic response. A critical aspect of the Hub was the formation of an appropriate governance group to ensure that algorithms being deployed underwent cross-disciplinary scrutiny prior to being made available for quick and safe implementation. This framework necessarily canvassed a broad range of perspectives, including from data science, clinical, Māori, consumer, ethical, public health, privacy, legal and governmental perspectives. To our knowledge, this is the first implementation of national algorithm governance of this type, building upon broad local and global discussion of guidelines in recent years. This paper describes the experiences and lessons learned through this process from the perspective of governance group members, emphasising the role of robust governance processes in building a high-trust platform that enables rapid translation of algorithms from research to practice.

A novel blockchain-based architectural modal for healthcare data integrity: Covid19 screening laboratory use-case.

In this paper, we are proposing a blockchain-based architectural model to ensure the integrity of healthcare-sensitive data in an AI-based medical research context. In our approach, we will use the HL7 FHIR standardized data structure to ensure the interoperability of our approach with the existing hospital information systems (HIS). Indeed, structuring the data coming from several heterogeneous sources would enhance its quality. In addition, a standardised data structure would help establish a more accurate security and data protection model throughout the process of data collection cleansing and processing. Hence, we designed our architecture to be interoperable with all FHIR-based HISs to add a trust layer to the current medical research process. In this paper we are to achieve our goal, we will combine continua healthcare IoT architecture and Hyperledger fabric architecture. Our trust layer model is composed of four components: (1) an architecture that integrates with the HL7 FHIR data exchange framework, which extends an open protocol that supports efficient standards-based healthcare data exchange (2) a blockchain layer to support access control and auditing of FHIR health records that are stored in the data exchange network databases; (3) a distributed architecture consisting of multiple trusted nodes ensure privacy protection for health data; and (4) an application programming interface (API) will be available for use by the network.

Smart Health and Cybersecurity in the Era of Artificial Intelligence

Since 2020, the world has been impacted badly by the pandemic situation that arose due to the coronavirus. Artificial intelligence plays a crucial role in the healthcare system, specifically identifying symptoms of disease with the help of various machine learning algorithms during the diagnosis stage. The identified symptoms in various diagnostic tests are used to predict the clinical outcome of early detection of diseases, which results in human life saving. Machine learning algorithms have been successfully used in automated interpretation. With the advanced technology of cybersecurity aspects, we can emphasize data protection for better results. Artificial intelligence can enhance the security of medical science data. Furthermore, they improvise cybersecurity techniques with machine learning technologies. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Comprehensive Information Retrieval Using Fine-Tuned Bert Model and Topic-Assisted Query Expansion

Retrieving relevant information covering different aspects of user information needs and ranking them based on their diverse nature are some of the important problems in the information retrieval domain. Identifying a document content covering multiple aspects of information pertaining to a query is of interest to users who wish to see everything about the query. The specific portions (information nuggets) of such documents may talk about specific aspects, and similar aspects of information can be seen across top k retrieved documents. We have proposed an information retrieval framework using the fine-tuned BERT model that identifies such aspects across top k documents and identifies such aspect based information in the form of information nuggets. Similar information nuggets are clustered based on their contextual relevance to specific aspects of the query. This work also applies topic-assisted query expansion to prune the final retrieved set of information nuggets, and the final retrieved set of information covers diverse aspects of user information needs. The experiment results done on three dataset, including COVID-19 dataset, shows that the proposed topic-assisted fine-tuned BERT model shows a better performance in comparison with the standard Vector Space Model. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Deep Learning Based Multi-Label Prediction of Hospitalization for COVID-19 Cases

Health informatics is an interdisciplinary area where computer science and related disciplines meet to address problems and support healthcare and medicine. In particular, computer has played an important role in medicine. Many existing computer-based systems (e.g., machine learning models) for healthcare applications produce binary prediction (e.g., whether a patient catches a disease or not). However, there are situations in which a non-binary prediction (e.g., what is hospitalization status of a patient) is needed. As a concrete example, over the past two years, people around the world have been affected by the coronavirus disease 2019 (COVID-19) pandemic. There have been works on binary prediction to determine whether a patient is COVID-19 positive or not. With availability of alternative methods (e.g., rapid test), such a binary prediction has become less important. Moreover, with the evolution of the disease (e.g., recent development of COVID-19 Omicron variant), multi-label prediction of the hospitalization status has become more important when compared with binary prediction on the confirmation of cases. Hence, in this paper, we present a multi-label prediction system for computer-based medical applications. Our system makes use of autoencoders (consisting of encoders and decoders) and few-shot learning to predict the hospitalization status (e.g., ICU, semi-ICU, regular wards, or no hospitalization). The prediction is important for allocation of medical resources (e.g., hospital facilities and medical staff), which in turn affect patient lives. Experimental results on real-life open datasets show that, when training with only a few data, our multilabel prediction system gave a high F1-score when predicting hospitalization status of COVID-19 cases. © 2022 IEEE.

Lessons learned from developing a COVID-19 algorithm governance framework in Aotearoa New Zealand

Aotearoa New Zealand’s response to the COVID-19 pandemic has included the use of algorithms that could aid decision making. Te Pokapū Hātepe o Aotearoa, the New Zealand Algorithm Hub, was established to evaluate and host COVID-19 related models and algorithms, and provide a central and secure infrastructure to support the country’s pandemic response. A critical aspect of the Hub was the formation of an appropriate governance group to ensure that algorithms being deployed underwent cross-disciplinary scrutiny prior to being made available for quick and safe implementation. This framework necessarily canvassed a broad range of perspectives, including from data science, clinical, Māori, consumer, ethical, public health, privacy, legal and governmental perspectives. To our knowledge, this is the first implementation of national algorithm governance of this type, building upon broad local and global discussion of guidelines in recent years. This paper describes the experiences and lessons learned through this process from the perspective of governance group members, emphasising the role of robust governance processes in building a high-trust platform that enables rapid translation of algorithms from research to practice. [ FROM AUTHOR] Copyright of Journal of the Royal Society of New Zealand is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

The experiences of 33 national COVID-19 dashboard teams during the first year of the pandemic in the World Health Organization European Region: A qualitative study.

Background: Governments across the World Health Organization (WHO) European Region have prioritised dashboards for reporting COVID-19 data. The ubiquitous use of dashboards for public reporting is a novel phenomenon. Objective: This study explores the development of COVID-19 dashboards during the first year of the pandemic and identifies common barriers, enablers and lessons from the experiences of teams responsible for their development. Methods: We applied multiple methods to identify and recruit COVID-19 dashboard teams, using a purposive, quota sampling approach. Semi-structured group interviews were conducted from April to June 2021. Using elaborative coding and thematic analysis, we derived descriptive and explanatory themes from the interview data. A validation workshop was held with study participants in June 2021. Results: Eighty informants participated, representing 33 national COVID-19 dashboard teams across the WHO European Region. Most dashboards were launched swiftly during the first months of the pandemic, February to May 2020. The urgency, intense workload, limited human resources, data and privacy constraints and public scrutiny were common challenges in the initial development stage. Themes related to barriers or enablers were identified, pertaining to the pre-pandemic context, pandemic itself, people and processes and software, data and users. Lessons emerged around the themes of simplicity, trust, partnership, software and data and change. Conclusions: COVID-19 dashboards were developed in a learning-by-doing approach. The experiences of teams reveal that initial underpreparedness was offset by high-level political endorsement, the professionalism of teams, accelerated data improvements and immediate support with commercial software solutions. To leverage the full potential of dashboards for health data reporting, investments are needed at the team, national and pan-European levels.

Semantic Behavior Analysis of COVID-19 Patients: A Collaborative Framework

The world we live in today, where technology has become a very integral part of our lives, has new, untapped resources that can bring about massive changes in the health sector. The Internet and social media have become the flag bearers of the tech-savvy world. Some of the services provided by the various social media platforms like chats, comments, blogs, captions, as well as reviews are starting to get studied for Natural Language Processing (NLP) and Text Analytics. A generation that scrounges up even the silliest of answers on the internet, it is very common for people to search for their health-related queries on social media. In this book chapter, we intend to propose a model for extracting data complying with health records and health-related text documents of the COVID-19 patients from some of the top social media forums and present a semantic framework. Given the fact that social media allows a more open and direct form of communication, among health workers, patients, and even curious students and researchers, it is a reliable source for addressing public health problems. In these tough times, when the entire world is suffering from the deadly Coronavirus pandemic, we hope our work gets the perfect infrastructure to grow on. Our book chapter puts forth a model to apply a semantic framework to retrieve healthcare data related to the Corona virus and COVID-19 pandemic from some of the social media forums available online and perform semantic analysis on the data. Social media can play a huge role in this aspect as people’s experiences with the pandemic and patients affected by the virus from the root of information that is circulated online. This research work tries to provide a useful and reliable method of data retrieval and data extraction, which would catch data in its unstructured form like patient questions and discussions among doctors and patients, people who have had a close look on the virus, analyze the semantic nature of the data, and present it in a more structured manner so that it can be put to effective and immediate use. The sole purpose of our framework is aiming to help detect and predict the symptoms of Coronavirus through the textual data extracted from the various social media platforms. © 2021 Scrivener Publishing LLC.

Smart Health and Cybersecurity in the Era of Artificial Intelligence

Since 2020, the world has been impacted badly by the pandemic situation that arose due to the coronavirus. Artificial intelligence plays a crucial role in the healthcare system, specifically identifying symptoms of disease with the help of various machine learning algorithms during the diagnosis stage. The identified symptoms in various diagnostic tests are used to predict the clinical outcome of early detection of diseases, which results in human life saving. Machine learning algorithms have been successfully used in automated interpretation. With the advanced technology of cybersecurity aspects, we can emphasize data protection for better results. Artificial intelligence can enhance the security of medical science data. Furthermore, they improvise cybersecurity techniques with machine learning technologies. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Assessing Progress Toward the Vision of a Comprehensive, Shared Electronic Care Plan: Scoping Review.

BACKGROUND: Care plans are central to effective care delivery for people with multiple chronic conditions. But existing care plans-which typically are difficult to share across care settings and care team members-poorly serve people with multiple chronic conditions, who often receive care from numerous clinicians in multiple care settings. Comprehensive, shared electronic care (e-care) plans are dynamic electronic tools that facilitate care coordination and address the totality of health and social needs across care contexts. They have emerged as a potential way to improve care for individuals with multiple chronic conditions. OBJECTIVE: To review the landscape of e-care plans and care plan-related initiatives that could allow the creation of a comprehensive, shared e-care plan and inform a joint initiative by the National Institutes of Health and the Agency for Healthcare Research and Quality to develop e-care planning tools for people with multiple chronic conditions. METHODS: We conducted a scoping review, searching literature from 2015 to June 2020 using Scopus, Clinical Key, and PubMed; we also searched the gray literature. To identify initiatives potentially missing from this search, we interviewed expert informants. Relevant data were then identified and extracted in a structured format for data synthesis and analysis using an expanded typology of care plans adapted to our study context. The extracted data included (1) the perspective of the initiatives; (2) their scope, (3) network, and (4) context; (5) their use of open syntax standards; and (6) their use of open semantic standards. RESULTS: We identified 7 projects for e-care plans and 3 projects for health care data standards. Each project provided critical infrastructure that could be leveraged to promote the vision of a comprehensive, shared e-care plan. All the e-care plan projects supported both broad goals and specific behaviors; 1 project supported a network of professionals across clinical, community, and home-based networks; 4 projects included social determinants of health. Most projects specified an open syntax standard, but only 3 specified open semantic standards. CONCLUSIONS: A comprehensive, shared, interoperable e-care plan has the potential to greatly improve the coordination of care for individuals with multiple chronic conditions across multiple care settings. The need for such a plan is heightened in the wake of the ongoing COVID-19 pandemic. While none of the existing care plan projects meet all the criteria for an optimal e-care plan, they all provide critical infrastructure that can be leveraged as we advance toward the vision of a comprehensive, shared e-care plan. However, critical gaps must be addressed in order to achieve this vision.

Encoding laboratory testing data: case studies of the national implementation of HHS requirements and related standards in five laboratories.

OBJECTIVE: Assess the effectiveness of providing Logical Observation Identifiers Names and Codes (LOINC®)-to-In Vitro Diagnostic (LIVD) coding specification, required by the United States Department of Health and Human Services for SARS-CoV-2 reporting, in medical center laboratories and utilize findings to inform future United States Food and Drug Administration policy on the use of real-world evidence in regulatory decisions. MATERIALS AND METHODS: We compared gaps and similarities between diagnostic test manufacturers' recommended LOINC® codes and the LOINC® codes used in medical center laboratories for the same tests. RESULTS: Five medical centers and three test manufacturers extracted data from laboratory information systems (LIS) for prioritized tests of interest. The data submission ranged from 74 to 532 LOINC® codes per site. Three test manufacturers submitted 15 LIVD catalogs representing 26 distinct devices, 6956 tests, and 686 LOINC® codes. We identified mismatches in how medical centers use LOINC® to encode laboratory tests compared to how test manufacturers encode the same laboratory tests. Of 331 tests available in the LIVD files, 136 (41%) were represented by a mismatched LOINC® code by the medical centers (chi-square 45.0, 4 df, P < .0001). DISCUSSION: The five medical centers and three test manufacturers vary in how they organize, categorize, and store LIS catalog information. This variation impacts data quality and interoperability. CONCLUSION: The results of the study indicate that providing the LIVD mappings was not sufficient to support laboratory data interoperability. National implementation of LIVD and further efforts to promote laboratory interoperability will require a more comprehensive effort and continuing evaluation and quality control.

Predictive Analytics to Support Health Informatics on COVID-19 Data

Bioinformatics and health informatics-in conjection with data science, data mining and machine learning-have been applied in numerous real-life applications including disease and healthcare analytics, such as predictive analytics of coronavirus disease 2019 (COVID-19). Many of these existing works usually require large volumes of data train the classification and prediction models. However, these data (e.g., computed tomography (CT) scan images, viral/molecular test results) that can be expensive to produce and/or not easily accessible. For instance, partially due to privacy concerns and other factors, the volume of available disease data can be limited. Hence, in this paper, we present a predictive analytics system to support health analytics. Specifically, the system make good use of autoencoder and few-shot learning to train the prediction model with only a few samples of more accessible and less expensive types of data (e.g., serology/antibody test results from blood samples), which helps to support prediction on classification of potential patients (e.g., potential COVID-19 patients). Moreover, the system also provides users (e.g., healthcare providers) with predictions on hospitalization status and clinical outcomes of COVID-19 patients. This provides healthcare administrators and staff with a good estimate on the demand for healthcare support. With this system, users could then focus and provide timely treatment to the true patients, thus preventing them for spreading the disease in the community. The system is helpful, especially for rural areas, when sophisticated equipment (e.g., CT scanners) may be unavailable. Evaluation results on a real-life datasets demonstrate the effectiveness of our digital health system in health analytics, especially in classifying patients and their medical needs.

Nowcasting (Short-Term Forecasting) of COVID-19 Hospitalizations Using Syndromic Healthcare Data, Sweden, 2020.

We report on local nowcasting (short-term forecasting) of coronavirus disease (COVID-19) hospitalizations based on syndromic (symptom) data recorded in regular healthcare routines in Östergötland County (population ≈465,000), Sweden, early in the pandemic, when broad laboratory testing was unavailable. Daily nowcasts were supplied to the local healthcare management based on analyses of the time lag between telenursing calls with the chief complaints (cough by adult or fever by adult) and COVID-19 hospitalization. The complaint cough by adult showed satisfactory performance (Pearson correlation coefficient r>0.80; mean absolute percentage error <20%) in nowcasting the incidence of daily COVID-19 hospitalizations 14 days in advance until the incidence decreased to <1.5/100,000 population, whereas the corresponding performance for fever by adult was unsatisfactory. Our results support local nowcasting of hospitalizations on the basis of symptom data recorded in routine healthcare during the initial stage of a pandemic.