Review on the Evaluation and Development of Artificial Intelligence for COVID-19 Containment

Optimizing vitiligo diagnosis with ResNet and Swin transformer deep learning models: a study on performance and interpretability

Vitiligo is a hypopigmented skin disease characterized by the loss of melanin. The progressive nature and widespread incidence of vitiligo necessitate timely and accurate detection. Usually, a single diagnostic test often falls short of providing definitive confirmation of the condition, necessitating the assessment by dermatologists who specialize in vitiligo. However, the current scarcity of such specialized medical professionals presents a significant challenge. To mitigate this issue and enhance diagnostic accuracy, it is essential to build deep learning models that can support and expedite the detection process. This study endeavors to establish a deep learning framework to enhance the diagnostic accuracy of vitiligo. To this end, a comparative analysis of five models including ResNet (ResNet34, ResNet50, and ResNet101 models) and Swin Transformer series (Swin Transformer Base, and Swin Transformer Large models), were conducted under the uniform condition to identify the model with superior classification capabilities. Moreover, the study sought to augment the interpretability of these models by selecting one that not only provides accurate diagnostic outcomes but also offers visual cues highlighting the regions pertinent to vitiligo. The empirical findings reveal that the Swin Transformer Large model achieved the best performance in classification, whose AUC, accuracy, sensitivity, and specificity are 0.94, 93.82%, 94.02%, and 93.5%, respectively. In terms of interpretability, the highlighted regions in the class activation map correspond to the lesion regions of the vitiligo images, which shows that it effectively indicates the specific category regions associated with the decision-making of dermatological diagnosis. Additionally, the visualization of feature maps generated in the middle layer of the deep learning model provides insights into the internal mechanisms of the model, which is valuable for improving the interpretability of the model, tuning performance, and enhancing clinical applicability. The outcomes of this study underscore the significant potential of deep learning models to revolutionize medical diagnosis by improving diagnostic accuracy and operational efficiency. The research highlights the necessity for ongoing exploration in this domain to fully leverage the capabilities of deep learning technologies in medical diagnostics.

Application of artificial intelligence for the classification of the clinical outcome and therapy in patients with viral infections: The case of COVID-19

BACKGROUND

With the end of the coronavirus disease 2019 (COVID-19) pandemic, it becomes intriguing to observe the impact of innovative digital technologies on the diagnosis and management of diseases, in order to improve clinical outcomes for patients.

OBJECTIVE

The research aims to enhance diagnostics, prediction, and personalized treatment for patients across three classes of clinical severity (mild, moderate, and severe). What sets this study apart is its innovative approach, wherein classification extends beyond mere disease presence, encompassing the classification of disease severity. This novel perspective lays the foundation for a crucial decision support system during patient triage.

METHODS

An artificial neural network, as a deep learning technique, enabled the development of a complex model based on the analysis of data collected during the process of diagnosing and treating 1000 patients at the Tešanj General Hospital, Bosnia and Herzegovina.

RESULTS

The final model achieved a classification accuracy of 82.4% on the validation data set, which testifies to the successful application of the artificial neural network in the classification of clinical outcomes and therapy in patients infected with viral infections.

CONCLUSION

The results obtained show that expert systems are valuable tools for decision support in healthcare in communities with limited resources and increased demands. The research has the potential to improve patient care for future epidemics and pandemics.

Medical Data Analysis Meets Artificial Intelligence (AI) and Internet of Medical Things (IoMT)

AI is a contemporary methodology rooted in the field of computer science [...].

COVID-19 and beyond: leveraging artificial intelligence for enhanced outbreak control

COVID-19 has brought significant changes to our political, social, and technological landscape. This paper explores the emergence and global spread of the disease and focuses on the role of Artificial Intelligence (AI) in containing its transmission. To the best of our knowledge, there has been no scientific presentation of the early pictorial representation of the disease's spread. Additionally, we outline various domains where AI has made a significant impact during the pandemic. Our methodology involves searching relevant articles on COVID-19 and AI in leading databases such as PubMed and Scopus to identify the ways AI has addressed pandemic-related challenges and its potential for further assistance. While research suggests that AI has not fully realized its potential against COVID-19, likely due to data quality and diversity limitations, we review and identify key areas where AI has been crucial in preparing the fight against any sudden outbreak of the pandemic. We also propose ways to maximize the utilization of AI's capabilities in this regard.

Using artificial intelligence to improve public health: a narrative review

Artificial intelligence (AI) is a rapidly evolving tool revolutionizing many aspects of healthcare. AI has been predominantly employed in medicine and healthcare administration. However, in public health, the widespread employment of AI only began recently, with the advent of COVID-19. This review examines the advances of AI in public health and the potential challenges that lie ahead. Some of the ways AI has aided public health delivery are via spatial modeling, risk prediction, misinformation control, public health surveillance, disease forecasting, pandemic/epidemic modeling, and health diagnosis. However, the implementation of AI in public health is not universal due to factors including limited infrastructure, lack of technical understanding, data paucity, and ethical/privacy issues.

Harnessing artificial intelligence in the post-COVID-19 era: A global health imperative

Despite the World Health Organization's declaration that the COVID-19 global emergency has ended, the threat of future pandemics remains a significant concern. This paper highlights the potential role of Artificial Intelligence (AI) in strengthening global health systems and mitigating future health crises. We discuss AI's proven utility throughout the COVID-19 pandemic, including disease surveillance, diagnostics, and drug discovery. AI's ability to rapidly analyze vast amounts of data to derive accurate trends and predictions underscores its superiority over traditional computer technology. However, the effective and ethical implementation of AI encounters significant challenges, including a pronounced digital divide, with applications mainly concentrated in high-income countries, thus exacerbating health inequities. We argue for international cooperation to enhance digital infrastructure in low- and middle-income countries, tailoring AI solutions to local needs, and addressing ethical and regulatory issues. The importance of maintaining evidence-based practice, rigorous evaluation of AI's impact, and investment in AI education and innovation are stressed. Ultimately, the potential of AI in global health systems is clear, and tackling these challenges will ensure its robust contribution to global health equity and resilience against future health crises.

Visual design of green information in urban environment based on global similarity calculation and multi-dimensional visualization technology

In recent years, the escalating prevalence of elevated consumption and carbon emissions within urban operations has reached a disconcerting extent. This surge in resource depletion and environmental pollution exerts an adverse influence on the well-being of individuals, while impeding societal progress and hindering the enhancement of overall quality of life. Within the domain of urban environmental design, the integration of visual displays emerges as a superior approach to facilitate the assimilation and analysis of green and low-carbon information. However, urban environmental data usually contains multiple dimensions, so it is a problem to realize the data representation of multiple dimensions while maintaining the correlation and interactivity between data. To surmount the challenge of visualizing such intricate information, this investigation initially employs a sophisticated memory-based clustering algorithm for information extraction, accompanied by a global similarity algorithm that meticulously computes attribute component quantities within specific dimensions of the vector. Furthermore, leveraging the inherent power of Vue's bidirectional data binding capabilities, the study adopts the esteemed MVVM (Model-View-View-Model) pattern, fostering seamless two-way interaction through the established logical relationship. As a result, the amalgamation of multidimensional visualization technology empowers comprehensive data mining through a captivating visual augmentation. Concurrently, the application of data visualization dimension control delivers tailored displays tailored to green and low-carbon scenarios within urban environmental design. Experimental results impeccably validate the effectiveness of the proposed algorithm, substantiated by a mere 1.77% false alarm rate for data stream difference detection and a clustering difference of 1.34%. The aforementioned algorithm accentuates the efficacy of visual displays, thus engendering a profound synergy between the industrial and supply chains. Moreover, it facilitates the design, production, and utilization of environmentally friendly products and energy sources. This, in turn, serves as a catalyst, propelling the widescale adoption of green and low-carbon practices throughout the entire industrial chain, fueled by the seamless integration of multimedia data.

Challenges and solutions in clinical research during the COVID-19 pandemic: A narrative review

BACKGROUND AND AIMS

The COVID-19 pandemic has presented significant challenges to clinical research, necessitating the adoption of innovative and remote methods to conduct studies. This study aimed to investigate these challenges and propose solutions for conducting clinical research during the pandemic.

METHODS

A narrative review was conducted (approval ID: IR.AMS.REC.1401.029), utilizing keyword searches in PubMed and Web of Science (WOS) citation index expanded (SCI-EXPANDED) from January 2020 to January 2023. Keywords included COVID-19, clinical research, barriers, obstacles, facilitators and enablers.

RESULTS

Out of 2508 records retrieved, 43 studies were reviewed, providing valuable insights into the challenges and corresponding solutions for conducting clinical research during the COVID-19 pandemic. The identified challenges were categorized into four main groups: issues related to researchers or investigators, issues related to participants and ethical concerns, administrative issues, and issues related to research implementation. To address these challenges, multiple strategies were proposed, including remote monitoring through phone or video visits, online data collection and interviews to minimize in-person contact, development of virtual platforms for participant interaction and questionnaire completion, consideration of financial incentives, adherence to essential criteria such as inclusion and exclusion parameters, participant compensation, and risk assessment for vulnerable patients.

CONCLUSION

The COVID-19 pandemic has significantly impacted clinical research, requiring the adaptation and enhancement of existing research structures. Although remote methods and electronic equipment have limitations, they hold promise as effective solutions during this challenging period.

Diabetes Detection Models in Mexican Patients by Combining Machine Learning Algorithms and Feature Selection Techniques for Clinical and Paraclinical Attributes: A Comparative Evaluation

The development of medical diagnostic models to support healthcare professionals has witnessed remarkable growth in recent years. Among the prevalent health conditions affecting the global population, diabetes stands out as a significant concern. In the domain of diabetes diagnosis, machine learning algorithms have been widely explored for generating disease detection models, leveraging diverse datasets primarily derived from clinical studies. The performance of these models heavily relies on the selection of the classifier algorithm and the quality of the dataset. Therefore, optimizing the input data by selecting relevant features becomes essential for accurate classification. This research presents a comprehensive investigation into diabetes detection models by integrating two feature selection techniques: the Akaike information criterion and genetic algorithms. These techniques are combined with six prominent classifier algorithms, including support vector machine, random forest, k-nearest neighbor, gradient boosting, extra trees, and naive Bayes. By leveraging clinical and paraclinical features, the generated models are evaluated and compared to existing approaches. The results demonstrate superior performance, surpassing accuracies of 94%. Furthermore, the use of feature selection techniques allows for working with a reduced dataset. The significance of feature selection is underscored in this study, showcasing its pivotal role in enhancing the performance of diabetes detection models. By judiciously selecting relevant features, this approach contributes to the advancement of medical diagnostic capabilities and empowers healthcare professionals in making informed decisions regarding diabetes diagnosis and treatment.

Evaluating the Brexit and COVID-19's influence on the UK economy: A data analysis

The economic landscape of the United Kingdom has been significantly shaped by the intertwined issues of Brexit, COVID-19, and their interconnected impacts. Despite the country's robust and diverse economy, the disruptions caused by Brexit and the COVID-19 pandemic have created uncertainty and upheaval for both businesses and individuals. Recognizing the magnitude of these challenges, academic literature has directed its attention toward conducting immediate research in this crucial area. This study sets out to investigate key economic factors that have influenced various sectors of the UK economy and have broader economic implications within the context of Brexit and COVID-19. The factors under scrutiny include the unemployment rate, GDP index, earnings, and trade. To accomplish this, a range of data analysis tools and techniques were employed, including the Box-Jenkins method, neural network modeling, Google Trend analysis, and Twitter-sentiment analysis. The analysis encompassed different periods: pre-Brexit (2011-2016), Brexit (2016-2020), the COVID-19 period, and post-Brexit (2020-2021). The findings of the analysis offer intriguing insights spanning the past decade. For instance, the unemployment rate displayed a downward trend until 2020 but experienced a spike in 2021, persisting for a six-month period. Meanwhile, total earnings per week exhibited a gradual increase over time, and the GDP index demonstrated an upward trajectory until 2020 but declined during the COVID-19 period. Notably, trade experienced the most significant decline following both Brexit and the COVID-19 pandemic. Furthermore, the impact of these events exhibited variations across the UK's four regions and twelve industries. Wales and Northern Ireland emerged as the regions most affected by Brexit and COVID-19, with industries such as accommodation, construction, and wholesale trade particularly impacted in terms of earnings and employment levels. Conversely, industries such as finance, science, and health demonstrated an increased contribution to the UK's total GDP in the post-Brexit period, indicating some positive outcomes. It is worth highlighting that the impact of these economic factors was more pronounced on men than on women. Among all the variables analyzed, trade suffered the most severe consequences in the UK. By early 2021, the macroeconomic situation in the country was characterized by a simple dynamic: economic demand rebounded at a faster pace than supply, leading to shortages, bottlenecks, and inflation. The findings of this research carry significant value for the UK government and businesses, empowering them to adapt and innovate based on forecasts to navigate the challenges posed by Brexit and COVID-19. By doing so, they can promote long-term economic growth and effectively address the disruptions caused by these interrelated issues.

A Hybrid Deep Neural Approach for Segmenting the COVID Affection Area from the Lungs X-Ray Images

Nowadays, COVID severity prediction has attracted widely in medical research because of the disease severity. Hence, the image processing application is also utilized to analyze COVID severity identification using lungs X-ray images. Thus, several intelligent schemes were employed to detect the COVID-affected part of the lungs X-ray images. However, the traditional neural approaches reported less severity classification accuracy due to the image complexity score. So, the present study has presented a novel chimp-based Adaboost Severity Analysis (CbASA) implemented in the MATLAB environment. Hence, the lung's X-ray images are utilized to test the working performance of the designed model. All public imaging data sources contain more noisy features, so the noise features are removed in the initial hidden layer of the novel CbASA then the noise-free data is imported into the classification phase. Feature extraction, segmentation, and severity specification have been performed in the classification layer. Finally, the performance of the classification score has been measured and compared with other models. Subsequently, the presented novel CbASA has earned the finest classification outcome.