Efficient Thorax Disease Classification and Localization Using DCNN and Chest X-ray Images.

Thorax disease is a life-threatening disease caused by bacterial infections that occur in the lungs. It could be deadly if not treated at the right time, so early diagnosis of thoracic diseases is vital. The suggested study can assist radiologists in more swiftly diagnosing thorax disorders and in the rapid airport screening of patients with a thorax disease, such as pneumonia. This paper focuses on automatically detecting and localizing thorax disease using chest X-ray images. It provides accurate detection and localization using DenseNet-121 which is foundation of our proposed framework, called Z-Net. The proposed framework utilizes the weighted cross-entropy loss function (W-CEL) that manages class imbalance issue in the ChestX-ray14 dataset, which helped in achieving the highest performance as compared to the previous models. The 112,120 images contained in the ChestX-ray14 dataset (60,412 images are normal, and the rest contain thorax diseases) were preprocessed and then trained for classification and localization. This work uses computer-aided diagnosis (CAD) system that supports development of highly accurate and precise computer-aided systems. We aim to develop a CAD system using a deep learning approach. Our quantitative results show high AUC scores in comparison with the latest research works. The proposed approach achieved the highest mean AUC score of 85.8%. This is the highest accuracy documented in the literature for any related model.

A Survey on COVID-19 Data Analysis Using AI, IoT, and Social Media.

Coronaviruses are a well-established and deadly group of viruses that cause illness in both humans and animals. The novel type of this virus group, named COVID-19, was firstly reported in December 2019, and, with the passage of time, coronavirus has spread to almost all parts of the world. Coronavirus has been the cause of millions of deaths around the world. Furthermore, many countries are struggling with COVID-19 and have experimented with various kinds of vaccines to eliminate the deadly virus and its variants. This survey deals with COVID-19 data analysis and its impact on human social life. Data analysis and information related to coronavirus can greatly help scientists and governments in controlling the spread and symptoms of the deadly coronavirus. In this survey, we cover many areas of discussion related to COVID-19 data analysis, such as how artificial intelligence, along with machine learning, deep learning, and IoT, have worked together to fight against COVID-19. We also discuss artificial intelligence and IoT techniques used to forecast, detect, and diagnose patients of the novel coronavirus. Moreover, this survey also describes how fake news, doctored results, and conspiracy theories were spread over social media sites, such as Twitter, by applying various social network analysis and sentimental analysis techniques. A comprehensive comparative analysis of existing techniques has also been conducted. In the end, the Discussion section presents different data analysis techniques, provides future directions for research, and suggests general guidelines for handling coronavirus, as well as changing work and life conditions.

Open-source electronic health record systems: A systematic review of most recent advances.

Open-source Electronic Health Records (OS-EHRs) are of pivotal importance in the management, operations, and administration of any healthcare organization. With the advancement of health informatics, researchers and healthcare practitioners have proposed various frameworks to assess the maturation of Open-source EHRs. The significance of OS-EHRs stems from the fact that vendor-based EHR implementations are becoming financially burdensome, with some vendors raking in more than $1 billion with one contract. Contrarily, the adoption of OS-EHRs suffers from a lack of systematic evaluation from the standpoint of a standard reference model. To this end, the Healthcare Information and Management Systems Society (HIMSS) has presented a strategic road map called EMR Adoption and Maturity (EMRAM). The HIMSS-EMRAM model proposes a stage-wise model approach that is globally recognized and can be essentially applied as a benchmark evaluation criteria for open-source EHRs. This paper offers an applied descriptive methodology over the frequently studied open-source EHRs currently operational worldwide or has the potential of adoption in healthcare settings. Besides, we also present profiling (User Support, Developer' Support, Customization Support, Technical details, and Diagnostic help) of studied OS-EHRs from developer's and user's perspectives using updated standard metrics. We carried out multi-aspect objective analysis of studied systems covering EHR functions, software based features and implementation. This review portrays systematic aspects of electronic medical record standards for open-source software implementations. As we observed in the literature, prevalent research and working prototypes lack systematic review of the HIMSS-EMRAM model and do not present evolving software features. Therefore, after the application of our assessment measures, the results obtained indicate that OS-EHRs are yet to acquire standard compliance and implementation. The findings in this paper can be beneficial in the planning and implementation of OS-EHRs projects in the future.

Agent-Based Semantic Role Mining for Intelligent Access Control in Multi-Domain Collaborative Applications of Smart Cities.

Significance and popularity of Role-Based Access Control (RBAC) is inevitable; however, its application is highly challenging in multi-domain collaborative smart city environments. The reason is its limitations in adapting the dynamically changing information of users, tasks, access policies and resources in such applications. It also does not incorporate semantically meaningful business roles, which could have a diverse impact upon access decisions in such multi-domain collaborative business environments. We propose an Intelligent Role-based Access Control (I-RBAC) model that uses intelligent software agents for achieving intelligent access control in such highly dynamic multi-domain environments. The novelty of this model lies in using a core I-RBAC ontology that is developed using real-world semantic business roles as occupational roles provided by Standard Occupational Classification (SOC), USA. It contains around 1400 business roles, from nearly all domains, along with their detailed task descriptions as well as hierarchical relationships among them. The semantic role mining process is performed through intelligent agents that use word embedding and a bidirectional LSTM deep neural network for automated population of organizational ontology from its unstructured text policy and, subsequently, matching this ontology with core I-RBAC ontology to extract unified business roles. The experimentation was performed on a large number of collaboration case scenarios of five multi-domain organizations and promising results were obtained regarding the accuracy of automatically derived RDF triples (Subject, Predicate, Object) from organizational text policies as well as the accuracy of extracted semantically meaningful roles.

An automated routine childhood immunization approach using openEHR.

This project studies a working but manual immunization system in place in Pakistan, subject to concerns such as poor record-keeping, reaching targeted children and unavailability of latest census. We propose an openEHR-based solution, called Light-weight Electronic Traceable and Updatable System (LETUS), which aims at increasing childhood immunization coverage and traceability. Two key modules of the solution include: (1) a service that collects the data from the immunization workers, computes population estimates for particular regions, and creates alerts if the ratio of vaccinations over population in a region falls outside a certain range (over or under), and (2) several "thin client" modules where workers can enter their collected data and receive feedback about the current coverage in their region. The proposed software system can be integrated into existing regional immunization registry systems, and run on the servers of a local health agency to ensure timely reporting. Within each immunization registry systems, children data is sharable by applying openEHR approach. This solution will gradually replace the current record keeping process by employing smart phone applications and web services.

Actualizing a mobile integrated system for geriatric care.

Population aging looms over countries all over the world. The social and economic implications of this phenomenon extend beyond the individual person and the immediate family, affecting broader society and the global community in profound ways. Aging populations increase pressure on already over-burdened public health care services and expenditures. To address this impending predicament, many health care providers and countries have turned to technological solutions. The near-ubiquity of mobile devices entails that mHealth will rapidly become a key component of technologically-enabled health care delivery services. This poster presents research and engineering challenges for a sustainable ICT solution that supports information exchange for mobile geriatric care.