ABSTRACT
Objectives: To provide an update overview on the current status of healthcare systems in the Maghreb region (Algeria, Morocco, and Tunisia) and to emphasize the progress made in the midst of the challenges facing these countries. Method(s): A descriptive comparative approach of healthcare systems in the three countries, based on data from sources with an established methodology, including descriptive healthcare data from the WHO database. Result(s): The population of the Maghreb will increase from 102 million to 132 million by 2050. The current population is mostly centered in Algeria and Morocco, accounting for 77%. Annual healthcare expenditure per capita is 447.9$, 776.8$ and 854.6$ in Morocco, Tunisia and Algeria, respectively. The average infant mortality rate per 1000 live improved to 10.9 in Tunisia, 16.8 in Morocco and 18.9 in Algeria. Maternal mortality rates have dropped to 43 and 48.5/100 000 births in Tunisia and Algeria, respectively while remaining relatively high in Morocco: 72.6. Number of hospital beds/1000 inhabitants is only 1.1 in Morocco, 1.9 and 2.9 in Algeria and Tunisia, respectively. The number of physicians/1000 people was 0.73 in Morocco, 1.3 in Tunisia and 1.72 in Algeria. This remains considerably low compared to the 3.9/1000 in Europe. The Maghreb countries are currently facing an exodus of physicians, mainly to France, which represents 7.1% and 10.7% of Tunisians and Moroccans, respectively, and more than 24% for Algerians. The Maghreb countries were very early mobilized (governments, ministries of health, civil society) to fight against COVID-19 and have successfully controlled the pandemic, according to pre-established control strategies and the strongly commitment of health professional. Conclusion(s): Despite the considerable progress made, the Maghreb countries still face major challenges. Physicians migration, rising cost of care and endemic infectious disease outbreaks constitute a huge hurdle on the already overburdened and resilient healthcare systems.Copyright © 2023
ABSTRACT
This research article presents an analysis of health data collected from wearable devices, aiming to uncover the practical applications and implications of such analyses in personalized healthcare. The study explores insights derived from heart rate, sleep patterns, and specific workouts. The findings demonstrate potential applications in personalized health monitoring, fitness optimization, and sleep quality assessment. The analysis focused on the heart rate, sleep patterns, and specific workouts of the respondents. Results indicated that heart rate values during functional strength training fell within the target zone, with variations observed between different types of workouts. Sleep patterns were found to be individualized, with variations in sleep interruptions among respondents. The study also highlighted the impact of individual factors, such as demographics and manually defined information, on workout outcomes. The study acknowledges the challenges posed by the emerging nature of wearable devices and technological constraints. However, it emphasizes the significance of the research, highlighting variations in workout intensities based on heart rate data and the individualized nature of sleep patterns and disruptions. Perhaps the future cognitive healthcare platform may harness these insights to empower individuals in monitoring their health and receiving personalized recommendations for improved well-being. This research opens up new horizons in personalized healthcare, transforming how we approach health monitoring and management.
ABSTRACT
Objectives: Clinical Practice Research Datalink (CPRD) Aurum contains primary care electronic health records, including vaccinations and nearly complete capture of SARS-CoV-2 PCR test results between August 2020-March 2022. Our objective was to build code lists to define a cohort of persons diagnosed with COVID in England using routinely collected health data. Method(s): Persons aged 1 year or older were indexed on first COVID diagnosis from August 1, 2020 - January 31, 2022. We developed SNOMED code lists to define high risk of severe disease: 1) National Health Service's (NHS) list of highest risk conditions;2) PANORAMIC trial inclusion criteria;3) UK Health Security Agency (UKHSA) clinical risk groups. COVID vaccinations were defined as of December 1, 2021 using medical and product codes. Code lists were developed using wildcard search terms which were reviewed by multiple independent reviewers, and inclusion/exclusion was determined by consensus. All lists for diagnoses were reviewed by a UK physician. Result(s): We identified 2,257,907 people diagnosed in primary care with COVID;46% were male and mean age was 34 years, comparable to governmental data for the same period reporting 47% of cases in England were male and mean age was 34 years. We identified 12% at high risk of severe disease using the NHS definition, 31% using the PANORAMIC trial criteria, and 10% using the UKHSA clinical risk groups. Among adults, 86.1% had >=1 and 80.2% had >=2 COVID vaccine doses (2% and 0.2% lower than official reports, respectively). Conclusion(s): This cohort represented the age and sex distribution of COVID cases, and the COVID vaccination coverage, in England through January 2022. Definitions were built using reproducible methods that can be leveraged for future work. The high capture of COVID vaccinations supports the use of this cohort to examine clinical and societal benefits of COVID vaccination in England.Copyright © 2023
ABSTRACT
As we all know, COVID-19 appears to be having a terrible impact on world health and well-being. Furthermore, at its peak, the COVID-19 cases worldwide reached a huge number i.e., in millions. The objective of the present work is to develop a model that detects COVID-19 utilizing CT-Scan Image Dataset and DL Techniques. As the number of verified cases rises, it becomes more critical to monitor and precisely categorize healthy and infected people. RT-PCR testing is the most used approach for the detection of Covid-19. However, several investigations have found that it has a low sensitivity in the early stages. Computer tomography (CT) is also used to detect image-morphological patterns of COVID-19-related chest lesions. The RT-PCR technique for diagnosing COVID has some drawbacks. For starters, test kits are insufficiently available, necessitating greater testing time and the sensitivity of testing varies. Therefore, employing CT scan pictures to screen COVID-19 is essential. The results showed that CT scan pictures might efficiently identify COVID-19, saving more lives. A Convolutional Neural Network (CNN) is a sort of Artificial Neural Network that is commonly used for image/object detection with class. An Input layer, Hidden layers, and an Output layer are common components of a neural network (NN). CNN is inspired by the brain's architecture. Artificial neurons or nodes in CNNs, like neurons in the brain, take inputs, process them, and deliver the result as output. Illness severity can be detected and calculated for future scopes and research. Another challenge encountered when dealing with severity infection detection and extending the existing work by using frameworks in order to increase accuracy. The proposed ECNN technique outperformed than CNN in terms of accuracy (95.35), execution time, and performance. This study could be extended or improved in the future by directing severity identification on the CT-Scan image dataset. © 2023 IEEE.
ABSTRACT
The Covid-19 pandemic ushered in multiple paradigms of personal health data sharing with particular emphasis on Person-to-Institution sharing and Institution-to-Institution sharing. While the data aggregated by technology companies and health authorities was instrumental in the development of vaccines and ultimately flattening the curve of infection rates, egregious abuses of privacy occurred. In many instances acceptable guarantees of appropriate utility for the data were not made available. Personal health data sharing for the containment of infections with privacy limitations present a classic case of collaboration among mutually distrustful entities. In this regard the blockchain network and attendant protocols for data integrity, transaction transmission and provenance can prove useful. Thus, in this paper we present a blockchain-based method for disease surveillance in a smart environment where smart contracts are deployed to monitor public locations instead of individuals. The data aggregated is analysed and tagged with a lifetime commensurate with the time for infection. Once the data utility period has elapsed the monitored data are removed from the active surveillance pool and the entities involved can be notified. Such a method of continual surveillance protects privacy by shifting the emphasis from individuals to locations. Experimental data suggests this method is efficient and can be implemented on top of existing disease surveillance strategies for later pandemics.
ABSTRACT
Registries play an instrumental role in facilitating the transfer, aggregation, and analysis of standardized data in health information exchange (HIE). One such example is a health worker registry (HWR), a central, authoritative registry that maintains the unique identities of health workers according to a defined, minimum data set. Currently, data comprising workers' information—such as education, licensure, and place of employment—are collected through disparate methods and maintained in a variety of information systems. Harmonization of these data via an HWR can support interoperability and comparability of worker information across systems, thereby facilitating efficient workforce enumeration, planning, regulation and deployment, verification of training and education, identification of workforce shortages, and rapid communication and coordination of emergency response. In fact, HWR technologies played a role in coordinating response to both Ebola in West Africa in 2014 and more recently in response to COVID-19, making a HWR integral to nations' infrastructure upgrades postpandemic. This chapter identifies who is considered a "health worker” and why a registry of these individuals is a useful component of an HIE, especially in the wake of the COVID-19 pandemic. It also provides guidance on selection of data elements and standards to include in the development of an HWR. © 2023 Elsevier Inc. All rights reserved.
ABSTRACT
Health information exchange (HIE) now exists in diverse forms within and across countries. However, our HIE infrastructure is fragmented, which impedes the ability to meet the needs of varied data sharing use cases—particularly public health data needs that became evident during the COVID-19 pandemic. In response, several efforts—some within the United States and some outside the United States—have started to undertake work to help tie existing HIE approaches together into a more seamless whole. While the societal benefits of doing so are clear, there are substantial cost and complexity involved, leaving it an open question as to how successful they will be. This chapter describes three major efforts underway to advance HIE infrastructure at scale—the Trusted Exchange Framework and Common Agreement (a US policy strategy), the Joint Action Towards the European Health Data Space (an EU initiative), and the emerging concept of health data utility models as more comprehensive repositories of health data with strong government requirements for participation. For each, we describe the effort as well as discuss potential challenges to implementation and success in achieving the intended outcomes. We also discuss a complementary issue related to health data integration and usability of exchanged health information that will become more acute as efforts to advance data sharing at scale are pursued. © 2023 Elsevier Inc. All rights reserved.
ABSTRACT
Objective To analyze the clinical features of patients with coronavirus disease 2019COVID-19in Wuhan, and we provide reference for further prevention and control of the disease. Methods We collected the clinical data of patients with COVID-19 in Dongxihu Shelter Hospital of Wuhan from February 7 to March 6, 2020. The main symptoms, blood test results, lung CT results, and nucleic acid negative conversion were analyzed. Results A total of 654 patients were included, 17526.76%were mild, and 47973.24%were general. There were 344 males (52.60%), and 310 females (47.40%). The patients were with a mean age of49.36+/-10.30years, and 97 patients (14.83%) with a history of hypertension, 51 patients (7.80%) had a history of diabetes. The main clinical symptoms were fever with 547(83.64%) patients, 186 cases (28.44%) had chills, 15 cases (2.29%) had shiver, 342(52.29%) had fatigue symptoms, 413(63.15%) had cough, 137(20.95%) had chest tightness, and 109(16.67%) had diarrhea during the course of the disease. Blood routine tests of 395 patients, the white blood cell count (WBC) was (4.12+/-1.46)x109/L. The total white blood cell count was normal in 378 cases(95.70%), increased in 7(1.77%), and decreased in 10(2.53%). The lymphocyte percentage was (23.10+/-10.02)%, lymphocyte1.06+/-0.37x109/L. The percentage and count of lymphocyte were low. All the 654 cases were examined by CT, 175 cases (26.76%) showed normal lung CT, 422 cases (64.52%) showed patchy or segmental ground-glass opacity, and 57 cases (8.72%) showed multilobar consolidation, ground-glass shadow coexisted with consolidation or streak shadow. The interval between positive nucleic acid test before admission and negative test after admission was as short as 5 days and as long as 24 days, the average was (12.35+/-3.73) days. Conclusion Fever, coughing, and fatigue are the main symptoms in patients with COVID-19. The typical lung CT findings can be used as the basis for clinical diagnosis and disease evaluation. Patients with mild and common type had better prognosis.Copyright © 2021 Editorial Office of Chinese Journal of Schistosomiasis Control. All rights reserved.
ABSTRACT
Contradictions as a data quality indicator are typically understood as impossible combinations of values in interdependent data items. While the handling of a single dependency between two data items is well established, for more complex interdependencies, there is not yet a common notation or structured evaluation method established to our knowledge. For the definition of such contradictions, specific biomedical domain knowledge is required, while informatics domain knowledge is responsible for the efficient implementation in assessment tools. We propose a notation of contradiction patterns that reflects the provided and required information by the different domains. We consider three parameters (α, ß, θ): the number of interdependent items as α, the number of contradictory dependencies defined by domain experts as ß, and the minimal number of required Boolean rules to assess these contradictions as θ. Inspection of the contradiction patterns in existing R packages for data quality assessments shows that all six examined packages implement the (2,1,1) class. We investigate more complex contradiction patterns in the biobank and COVID-19 domains showing that the minimum number of Boolean rules might be significantly lower than the number of described contradictions. While there might be a different number of contradictions formulated by the domain experts, we are confident that such a notation and structured analysis of the contradiction patterns helps to handle the complexity of multidimensional interdependencies within health data sets. A structured classification of contradiction checks will allow scoping of different contradiction patterns across multiple domains and effectively support the implementation of a generalized contradiction assessment framework.
Subject(s)
COVID-19 , Data Accuracy , HumansABSTRACT
OBJECTIVES: Multimorbidity is the presence of two or more chronic health conditions. Tuberculosis (TB) survivors are known to have higher prevalence of multimorbidity, although prevalence estimates from high-income low-TB incidence jurisdictions are not available and potential differences in the patterns of chronic disease among TB survivors with multimorbidity are poorly understood. In this study, we aimed to (1) compare the prevalence of multimorbidity among TB survivors with matched non-TB controls in a high-income setting; (2) assess the robustness of aim 1 analyses to different modelling strategies, unmeasured confounding, and misclassification bias; and (3) among people with multimorbidity, elucidate chronic disease patterns specific to TB survivors. METHODS: A population-based cohort study of people immigrating to British Columbia, Canada, 1985-2015, using health administrative data. Participants were divided into two groups: people diagnosed with TB (TB survivors) and people not diagnosed with TB (non-TB controls) in British Columbia. Coarsened exact matching (CEM) balanced demographic, immigration, and socioeconomic covariates between TB survivors and matched non-TB controls. Our primary outcome was multimorbidity, defined as ≥2 chronic diseases from the Elixhauser comorbidity index. RESULTS: In the CEM-matched sample (n=1962 TB survivors; n=1962 non-TB controls), we estimated that 21.2% of TB survivors (n=416), compared with 12% of non-TB controls (n=236), had multimorbidity. In our primary analysis, we found a double-adjusted prevalence ratio of 1.74 (95% CI: 1.49-2.05) between TB survivors and matched non-TB controls for multimorbidity. Among people with multimorbidity, differences were observed in chronic disease frequencies between TB survivors and matched controls. CONCLUSION: TB survivors had a 74% higher prevalence of multimorbidity compared with CEM-matched non-TB controls. TB-specific multimorbidity patterns were observed through differences in chronic disease frequencies between the matched samples. These findings suggest a need for TB-specific multimorbidity interventions in high-income settings such as Canada. We suggest TB survivorship as a framework for developing person-centred interventions for multimorbidity among TB survivors.
RéSUMé: OBJECTIFS: La multimorbidité est la présence de deux affections chroniques ou plus. On sait que la prévalence de la multimorbidité est plus élevée chez les survivants de la tuberculose, mais il n'y a pas d'estimations de prévalence disponibles dans les entités administratives à revenu élevé et à faible incidence de tuberculose, et les différences potentielles dans les structures de la morbidité chronique chez les survivants de la tuberculose atteints de multimorbidité sont mal comprises. Dans cette étude, nous avons voulu 1) comparer la prévalence de la multimorbidité chez des survivants de la tuberculose appariés à des témoins sans tuberculose dans un milieu à revenu élevé; 2) évaluer la robustesse des analyses du 1er objectif par rapport à différentes stratégies de modélisation, à la confusion non mesurée et au biais d'erreur de classification; et 3) élucider, chez les personnes atteintes de multimorbidité, les structures de la morbidité chronique propres aux survivants de la tuberculose. MéTHODE: Nous avons mené à l'aide de données administratives sur la santé une étude de cohorte populationnelle des personnes ayant immigré en Colombie-Britannique (Canada) entre 1985 et 2015. Les participants ont été divisés en deux groupes : les personnes ayant un diagnostic de tuberculose (« survivants de la tuberculose ¼) et les personnes n'ayant pas de diagnostic de tuberculose (« témoins sans tuberculose ¼) en Colombie-Britannique. Un appariement exact avec groupement (coarsened exact matching [CEM]) a permis d'équilibrer les covariables démographiques, socioéconomiques et d'immigration entre les survivants de la tuberculose et les témoins sans tuberculose appariés. Notre principal résultat a été la multimorbidité, définie comme étant la présence de ≥ 2 affections chroniques selon l'indice de comorbidité d'Elixhauser. RéSULTATS: Dans l'échantillon CEM (n = 1 962 survivants de la tuberculose; n = 1 962 témoins sans tuberculose), nous avons estimé que 21,2 % des survivants de la tuberculose (n = 416), contre 12 % des témoins sans tuberculose (n = 236), étaient atteints de multimorbidité. Dans notre analyse primaire, nous avons obtenu un ratio de prévalence doublement ajusté de 1,74 (IC de 95 % : 1,49-2,05) entre les survivants de la tuberculose et les témoins sans tuberculose appariés pour ce qui est de la multimorbidité. Chez les personnes atteintes de multimorbidité, des différences ont été observées dans la fréquence des maladies chroniques entre les survivants de la tuberculose et les témoins appariés. CONCLUSION: Les survivants de la tuberculose avaient une prévalence de multimorbidité supérieure de 74 % à celle des témoins sans tuberculose appariés selon la méthode CEM. Les structures de multimorbidité propres à la tuberculose ont été observées selon les différences dans la fréquence des maladies chroniques entre les échantillons appariés. Ces constatations indiquent qu'il faudrait mener des interventions sur la multimorbidité propres à la tuberculose dans des milieux à revenu élevé comme le Canada. Nous suggérons d'utiliser la survie à la tuberculose comme cadre d'élaboration d'interventions centrées sur la personne pour lutter contre la multimorbidité chez les survivants de la tuberculose.
ABSTRACT
The Covid-19 pandemic catalyzed many exciting forms of health data sharing. Aside from the institution-to-institution health data sharing among cooperating institutions for research and discovery of insights in healthcare, individual-to-many and individual-to-individual health data sharing also came to the fore. However, the security risks involved here are substantial since health data disclosures can lead to privacy and security breaches or complications. In this research, we present a scheme to enable individuals to share details of medical experiences with other individuals or interested groups. Our system provides the sharing entities with anonymity and thus, facilitates rapid dissemination of empirical insights during public health emergencies like Covid-19.
ABSTRACT
Introduction: La France dispose d'une des bases de donnees medico-administratives les plus completes et homogenes au monde: le Systeme national des donnees de sante (SNDS). Cette base de donnees, initialement destinee a la gestion financiere de l'Assurance maladie, a longtemps ete sous-exploitee pour la recherche en sante en raison de sa complexite. Pour faciliter sa reutilisation, une piste de travail est sa standardisation via l'utilisation de modeles de donnees communs. Methodes: Depuis 2020, le Health Data Hub (HDH) transforme le SNDS vers le modele OMOP-CDM (<< Observational Medical Outcomes Partnership - Common Data Model >>). Cette transformation permet de creer un modele relationnel centre sur une table "patient" et de facilement reconstruire les parcours de soins. A partir d'un extrait du SNDS couvrant la periode 2019-2020 pour une population hospitalisee pour COVID (SNDS Fast-Track), un alignement des schemas de donnees et des terminologies ont ete realises. Les scripts de transformation sont developpes en Python et les validations sont effectuees via les logiciels du consortium OHDSI. Des travaux d'harmonisation ont ete realises avec des partenaires institutionnels (AP-HP, BPE). Resultats: Ce travail a permis de passer d'une base de donnees de plus de 180 tables a moins de 20 tables. Les alignements de terminologies ont ete realises par des internes en medecine sur plusieurs milliers de codes de differentes nomenclatures (CCAM, NABM, CSARR, etc.) vers SNOMED-CT. L'ensemble est disponible via la documentation collaborative du SNDS. Des travaux sont menes pour elargir le perimetre temporel (2015-2021). Discussion/Conclusion: La standardisation des bases de donnees de sante assure leur normalisation et interoperabilite, rendant leur exploitation croisee au niveau national et international plus efficace. L'utilisation de modeles de donnees communs accelere le partage de donnees, de documentation et de programmes. Plusieurs initiatives europeennes sont actuellement en cours telles que l'action conjointe TEHDAS et le pilote EHDS2 mene par le HDH. Mots-cles: Interoperabilite;SNDS;OMOP-CDM;Open source;ETL Declaration de liens d'interets: Les auteurs declarent ne pas avoir de liens d'interets.Copyright © 2023
ABSTRACT
The last both authors contributed equally Purpose To design clinical and public health policies, including immunization, during the COVID-19 pandemic, it is critical to monitor not only infections due to SARS-CoV-2 but other pathogens as well. We evaluated interim results from the first year of a multi-site study of community-acquired pneumonia (CAP) and early onset hospital-acquired pneumonia (HAP) in Germany to assess the contribution of different pathogens over time. Methods This multicenter trial is being conducted from January 2021 to December 2023 at three hospitals in Thuringia: Jena University Hospital (1396 beds), SRH Hospitals Gera (951 beds) and Suhl (653 beds). Adult hospitalized patients with CAP/early onset HAP are identified by a screening algorithm which includes assessment by a study physician. Study procedures included: health data collection, urine specimens (using S. pneumoniae serotype-specific urinary antigen detection assays (UAD-1/2) and BinaxNOW), and nasopharyngeal swabs (analyzed by multiplex microbiological analysis), disease severity assessments, mortality (follow-up to day 90), pathogen spectrum, and quality of life (follow-up to day 180). Results Within the first year (2021), 760 patients (58 % male, 70 % >= 60 years) were enrolled. ICU admission occurred in 16.1 % of cases, and 9.2 % required mechanical ventilation. Pathogens were identified for 553 cases. SARS-CoV-2 was identified in 78.4 % in the first half of the year while S. pneumoniae was detected in 6 cases (2.1 %;2/6 as a co-infection (0.7 %)). Other respiratory viruses were detected in 18 of 338 cases, of which 15 (4.2 %) were coinfections with SARS-CoV-2. In the second half of 2021, SARS-CoV-2 was identified in 58.3 % of cases, however, other pathogens occurred more frequently including S. pneumoniae 10.2 % (n/N = 34/333;13/34 as a co-infection with SARS-CoV-2 (3.9 %)) and other respiratory viruses 11.4 % (n/N = 41/360;11/41 as a co-infection with SARS-CoV-2 (3.0 %)). Influenza was not detected. Conclusion While SARS-CoV-2 remained the most common pathogen among patients with CAP/early onset HAP during the study year, other pathogens reemerged during the second half of 2021. Correspondingly, co-infections with SARS-CoV-2 increased, with pneumococci as the leading pathogen.
ABSTRACT
The Covid-19 pandemic ushered in multiple paradigms of personal health data sharing with particular emphasis on Person-to-Institution sharing and Institution-toInstitution sharing. While the data aggregated by technology companies and health authorities was instrumental in the development of vaccines and ultimately flattening the curve of infection rates, egregious abuses of privacy occurred. In many instances acceptable guarantees of appropriate utility for the data were not made available. Personal health data sharing for the containment of infections with privacy limitations present a classic case of collaboration among mutually distrustful entities. In this regard the blockchain network and attendant protocols for data integrity, transaction transmission and provenance can prove useful. Thus, in this paper we present a blockchain-based method for disease surveillance in a smart environment where smart contracts are deployed to monitor public locations instead of individuals. The data aggregated is analysed and tagged with a lifetime commensurate with the time for infection. Once the data utility period has elapsed the monitored data are removed from the active surveillance pool and the entities involved can be notified. Such a method of continual surveillance protects privacy by shifting the emphasis from individuals to locations. Experimental data suggests this method is efficient and can be implemented on top of existing disease surveillance strategies for later pandemics. © 2023 IEEE.
ABSTRACT
Early in 2020, the coronavirus Covid-19, which is produced by the SARS-CoV -2 strain, first gained international attention as a severe health threat. Covid-19 spread quickly around the world, forcing everyone to fight with preventative measures like masks, hand washing, and preserving social distance. But to prevent the virus, vaccination has been playing a key role. Vaccination records that contain patient data make this system very complicated because there is a risk of a privacy breach. Hackers may steal the personal health information of individuals or may carry out cyberattacks against any national health data server. Additionally, there is a chance that dishonest people can purchase and sell fake vaccine certificates on the black market. Blockchain can provide a solution to this regard by its features like data immutability, privacy, transparency and decentralization. For people, governments, and organizations interested in blockchain-based systems, we analyze the blockchain based vaccination management system in this study and provide a current summary. We envision our study to motivate more blockchain based systems. © 2022 IEEE.
ABSTRACT
The data age information is considerably more significant in open life, since individuals' well-being information just concluded regardless of whether COVID-19 impacted, and furthermore connected with all medical problems information. These information used to examine and anticipate the medical problems information by Machine Learning Algorithm, and afterward anticipated information need greater security. In this way, we applied the current strategy ChaCha technique and that strategy zeroed in as it were "encryption execution” so security is less. In this paper, to apply the new ES-BR22-001 strategy, this technique has 7 stages. The 1st stage is finding the K value. The 2nd stage is applying the K value in Eq. (1). The 3rd stage is finding the Sk values by using Eq. (1). The 4th stage is applying the Sk values in the sparse matrix. The 5th stage is sparse matrix values are converted into single line. The 6th stage is pairing all the values. The final stage is all paired values will be applied in the matrix. The new ES-BR22-001 method provides security and performance is good while compared to ChaCha method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
In China, healthcare specialists discovered a new and unknown virus around the end of December 2019. Later, it was recognized as Coronavirus;the virus rapidly spread over the globe. Lockdowns, and social isolation were the primary measures taken by every nation's government to control of the virus. In February 2022, the World Health Organization (WHO) announced that fast immunization reduces Coronavirus infection rates by 21 percent. After the COVID-19 epidemic, the researchers anticipated that another pandemic, mental health, would spread over the world. In fact, the psychological influence on the general population during and after the COVID-19 outbreak has grown vulnerable. The purpose of this work was to do a sentiment analysis on Twitter data using the Python programming language in order to determine the psychological influence of Twitter users in the post-COVID era.
ABSTRACT
With the development of Medical Internet of Things (MIoT) technology and the global COVID-19 pandemic, hospitals gain access to patients' health data from remote wearable medical equipment. Federated learning (FL) addresses the difficulty of sharing data in remote medical systems. However, some key issues and challenges persist, such as heterogeneous health data stored in hospitals, which leads to high communication cost and low model accuracy. There are many approaches of federated distillation (FD) methods used to solve these problems, but FD is very vulnerable to poisoning attacks and requires a centralised server for aggregation, which is prone to single-node failure. To tackle this issue, we combine FD and blockchain to solve data sharing in remote medical system called FedRMD. FedRMD use reputation incentive to defend against poisoning attacks and store reputation values and soft labels of FD in Hyperledger Fabric. Experimenting on COVID-19 radiography and COVID-Chestxray datasets shows our method can reduce communication cost, and the performance is higher than FedAvg, FedDF, and FedGen. In addition, the reputation incentive can reduce the impact of poisoning attacks. © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
ABSTRACT
With the Internet of Things and medical technology development, patients use wearable telemedicine devices to transmit health data to hospitals. The need for data sharing for public health has become more urgent under the COVID-19 pandemic. Previously, security protection technology was difficult to solve the increasing security risks and challenges of telemedicine. To address the above hindrances, Federated learning (FL) solves the difficulty for companies and institutions to share user data securely. The global server iterative aggregates the model parameters from the local server instead of uploading the user's data directly to the cloud server. We propose a new model of federated distillation learning called FedTD, which allows the different models between local hospital servers and global servers. Unlike traditional federated learning, we combine the knowledge distillation method to solve the non-Independent Identically Distribution (non-IID) problem of patient medical data. It provides a security solution for sharing patients' medical information among hospitals. We tested our approach on the COVID-19 Radiography and COVID-Chestxray datasets to improve the model performance and reduce communication costs. Extensive experiments show that our FedTD significantly outperforms the state-of-the-art. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.