Managing demand volatility of pharmaceutical products in times of disruption through news sentiment analysis

Unplanned events such as epidemic outbreaks, natural disasters, or major scandals are usually accompanied by supply chain disruption and highly volatile demand. Besides, authors have recently outlined the need for new applications of artificial intelligence to provide decision support in times of crisis. In particular, natural language processing allows for deriving an understanding from unstructured data in human languages, such as online news content, which can provide valuable information during disruptive events. This article contributes to this research strand as it aims to leverage textual data from news through sentiment analysis and predict demand volatility of pharmaceutical products in times of crisis. As a result, (1) a deep-learning-based sentiment analysis model was developed to extract and structure information from medicines-related news;(2) a framework allowing for combining extracted information from unstructured data with structured data of medicines demand was defined;and (3) an approach combining efficient artificial intelligence techniques with existing forecasting models was proposed to enhance demand forecasting in times of disruption. Additionally, the framework was applied to two examples of disruptive events in France: a pharmaceutical scandal and the COVID-19 pandemic. Findings outlined that using sentiment analysis allowed for enhancing demand forecasting accuracy.

Using Deep Learning Techniques for Diagnosis & Treatment with COVID-19 & AI Technology

The COVID-19 epidemic has caused an unprecedented level of difficulty for the entire world, stopping life and taking thousands of lives. Since COVID-19 has spread to 212 countries and territories and has resulted in 5,212,172 infected cases and 334,915 fatalities, it continues to pose a serious threat to public health. This study proposes a solution to battle the infection using Artificial Intelligence. It has been shown that some Deep Learning techniques, including Long-Short Term Memory, Extreme Learning Machines, and Generative Adversarial Networks, can accomplish this goal. It is informatics techniques in various informational facets from numerous structured & unstructured Data-Sources are combined to produce user-friendly platforms for medical professionals & researchers. The primary benefit of these AI-based platforms is that they speed up the process of diagnosing and treating COVID-19 illness. The most recent related publications and medical reports were examined in order to identify network sources & objectives that might assist in the construction of a feasible Artificial Neural Network based solution for COVID-19 issues. © 2022 IEEE.

One schema to rule them all: How Schema.org models the world of search

Several industry-specific metadata initiatives have historically facilitated structured data modeling for the web in domains such as commerce, publishing, social media, and so forth. The metadata vocabularies produced by these initiatives allow developers to "wrap” information on the web to provide machine-readable signals for search engines, advertisers, and user-facing content on apps and websites, thus assisting with surfacing facts about people, places, and products. A universal iteration of such a project called Schema.org started in 2011, resulting from a partnership between Google, Microsoft, Yahoo, and Yandex to collaborate on a single structured data model across domains. Yet, few studies have explored the metadata vocabulary terms in this significant web resource. What terms are included, upon what subject domains do they focus, and how does Schema.org represent knowledge in its conceptual model? This article presents findings from our extraction and analysis of the documented release history and complete hierarchy on Schema.org's developer pages. We provide a semantic network visualization of Schema.org, including an analysis of its modularity and domains, and discuss its global significance concerning fact-checking and COVID-19. We end by theorizing Schema.org as a gatekeeper of data on the web that authors vocabulary that everyday web users encounter in their searches. © 2023 The Authors. Journal of the Association for Information Science and Technology published by Wiley Periodicals LLC on behalf of Association for Information Science and Technology.

Comparison Between ResNet 16 and Inception V4 Network for COVID-19 Prediction

COVID-19 claimed 5 million lives worldwide so far, and the count is continuing. It also affected socio-economic life of almost everybody in the world. Due to COVID-19, mortality and morbidity are continuing, and it is necessary to find new methods and techniques to contain the infection. Every government is trying hard to implement a new strategy to minimize the spread of the virus. COVID-19 infection occurs due to the virus strain SARS-COV-2. Generally, death occurs due to COVID-19 because of suppurative pulmonary infection and subsequent septic shock or multiorgan failure. In the literature, there are some computational techniques which use deep learning models and reported fairly good performance. This paper proposes a new deep learning architecture inception v4 to automatically detect COVID-19 using the chart X-ray images. The proposed methodology provided improved performance of 98.7 and 94.8% of training and validation accuracy. The developed technology can be used to detect COVID-19 with a high performance;the same may be deployed by the various governments in the detection and the management of COVID-19 in an efficient manner. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Covid Vaccine Adverse Side-Effects Prediction with Sequence-to-Sequence Model

COVID-19 caused more than 5 million deaths in the world. After lot of efforts and hard work of many scientists, few vaccines are discovered and are approved for use. It is necessary to understand and to evaluate systematically with the potential side effects due to the vaccine itself. This work proposed a sequence-to-sequence learning (Seq2Seq) model to predict the adverse effects due to COVID-19 vaccine. Seq2Seq model is used to convert sequences of one domain to another domain. In this work, a structured data such as Vaccine Adverse Event Reposting System (VAERS) data are used to predict the adverse side effects of COVID-19 vaccination. The data formulated for Seq2Seq model architecture and trying to predict the adverse side effects of vaccination with age and gender attribute as input and obtained the result of 88% as average accuracy using long short-term memory-based (LSTM) deep learning model in adverse effect prediction. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Designing a Sustainable Data Structure for Exploring Student Well-Being Patterns in Albemarle County Public Schools Throughout COVID-19

Student well-being has been affected by the COVID-19 pandemic. Albemarle County Public Schools (ACPS) has collected a significant and varied amount of K-12 student data throughout COVID-19. Researchers seek to utilize the student data to drive evidence-based policy changes with regard to ACPS student well-being. A structured data system for performing school-related research associated with the well-being of students throughout the pandemic does not exist. We have designed a sustainable, relational data structure for data consolidation and to advance the ongoing research initiatives related to COVID-19 student well-being in collaboration with ACPS. The data structure aims to play an important role in promoting student well-being policies through simplifying data collection, enhancing analysis, and acting as an ongoing tool that can support future phases of research. The design architecture includes a relational database populated with de-identified student data to be hosted in the cloud. Design implementation includes data cleaning, data preprocessing, populating the database, and querying data for validation. Specialized queries are utilized to answer the early questions posed to the data. Validation testing is performed to confirm the database is working as expected. Details of the data pipeline, validation, best data practices, and database design are discussed in the paper. © 2022 IEEE.

In Silico Prediction of Indonesian Herbs Compounds as Covid-19 Supportive Therapy using Support Vector Machine

Many kinds of research on drug discovery using computational or in silico methods have been carried out. In this era of the Covid-19 pandemic, this research was also carried out by utilizing a commonly used technique, namely using machine learning to predict the interaction of compounds and proteins. This technique is known as Drug Target Interaction (DTI). The compounds used are herbal originating from Indonesia, and the protein used is a potential Covid-19 protein, one of which is SARS-CoV-2. The prediction process with machine learning can only be done on structured data. The data on herbal and protein were processed in this research using the Fingerprint as a descriptor compound and Pseudo Amino Acid Composition (PseAAC) as a protein descriptor technique. The result is structured data processed with the Support Vector Machine algorithm to create an interaction prediction model. The result is that the prediction accuracy is 95.96%. Furthermore, this model can predict Indonesian herbal compounds as drug candidates for Covid-19 supportive therapy. © 2021 IEEE.

Creating accessible evidence bases: Opportunities through the integration of interactive tools into literature review synthesis.

The COVID-19 pandemic has shown that an immediate access to relevant information is key for timely interventions and forming of public opinion and discourse. In this regard, dashboards present themselves as invaluable tools for the democratization of data and for the creation of accessible evidence bases. Building on this momentum, it is proposed to integrate interactive means such as dashboards into academic literature review synthesis, in order to support the summarization, narration, and dissemination of findings, and furthermore, to increase transparency and support the transferability and comparability of findings. Exemplified for a systematic literature review on urban forests as nature-based solutions,•Key functionalities, requirements and design considerations for the development of dashboards for use in academic literature reviews synthesis are identified.•An application architecture that embeds dashboard development into an R workflow is presented, with emphasis on the steps needed to transform the data collected during the review process into a structured form.•Technical and methodological means for the actual dashboard implementation are highlighted, considering the identified key functionalities and requirements.

Using a Secure, Continually Updating, Web Source Processing Pipeline to Support the Real-Time Data Synthesis and Analysis of Scientific Literature: Development and Validation Study.

BACKGROUND: The scale and quality of the global scientific response to the COVID-19 pandemic have unquestionably saved lives. However, the COVID-19 pandemic has also triggered an unprecedented "infodemic"; the velocity and volume of data production have overwhelmed many key stakeholders such as clinicians and policy makers, as they have been unable to process structured and unstructured data for evidence-based decision making. Solutions that aim to alleviate this data synthesis-related challenge are unable to capture heterogeneous web data in real time for the production of concomitant answers and are not based on the high-quality information in responses to a free-text query. OBJECTIVE: The main objective of this project is to build a generic, real-time, continuously updating curation platform that can support the data synthesis and analysis of a scientific literature framework. Our secondary objective is to validate this platform and the curation methodology for COVID-19-related medical literature by expanding the COVID-19 Open Research Dataset via the addition of new, unstructured data. METHODS: To create an infrastructure that addresses our objectives, the PanSurg Collaborative at Imperial College London has developed a unique data pipeline based on a web crawler extraction methodology. This data pipeline uses a novel curation methodology that adopts a human-in-the-loop approach for the characterization of quality, relevance, and key evidence across a range of scientific literature sources. RESULTS: REDASA (Realtime Data Synthesis and Analysis) is now one of the world's largest and most up-to-date sources of COVID-19-related evidence; it consists of 104,000 documents. By capturing curators' critical appraisal methodologies through the discrete labeling and rating of information, REDASA rapidly developed a foundational, pooled, data science data set of over 1400 articles in under 2 weeks. These articles provide COVID-19-related information and represent around 10% of all papers about COVID-19. CONCLUSIONS: This data set can act as ground truth for the future implementation of a live, automated systematic review. The three benefits of REDASA's design are as follows: (1) it adopts a user-friendly, human-in-the-loop methodology by embedding an efficient, user-friendly curation platform into a natural language processing search engine; (2) it provides a curated data set in the JavaScript Object Notation format for experienced academic reviewers' critical appraisal choices and decision-making methodologies; and (3) due to the wide scope and depth of its web crawling method, REDASA has already captured one of the world's largest COVID-19-related data corpora for searches and curation.

Unreported Cases for Age Dependent COVID-19 Outbreak in Japan.

We investigate the age structured data for the COVID-19 outbreak in Japan. We consider a mathematical model for the epidemic with unreported infectious patient with and without age structure. In particular, we build a new mathematical model and a new computational method to fit the data by using age classes dependent exponential growth at the early stage of the epidemic. This allows to take into account differences in the response of patients to the disease according to their age. This model also allows for a heterogeneous response of the population to the social distancing measures taken by the local government. We fit this model to the observed data and obtain a snapshot of the effective transmissions occurring inside the population at different times, which indicates where and among whom the disease propagates after the start of public mitigation measures.