Information and communication technologies (ICTs) have transformed global connectivity, offering significant support to underserved populations and small businesses in developing nations. The integration of social media into the ICT landscape has further revolutionized communication and information sharing worldwide. However, despite its widespread adoption, the precise impact of social media on biomedical research remains uncertain. This manuscript seeks to examine the multifaceted roles of social media in healthcare, focusing on its applications in patient care, professional networking, education, organizational promotion, and public health programs. Additionally, it investigates social media’s significance in research, particularly its potential for data collection and analysis. A comprehensive literature review was undertaken to consolidate existing knowledge on social media’s utilization in healthcare and research. Various platforms, including social networking sites and academic networking sites, were assessed, along with their respective applications and consequences. Social media platforms have become essential tools in healthcare, facilitating professional networking, patient education, organizational promotion, and public health initiatives. In the realm of research, social media provides extensive opportunities for data collection, analysis, and collaboration, although challenges persist regarding privacy, data accuracy, and ethical considerations. The pervasive influence of social media in healthcare and research highlights its potential to enhance communication, engagement, and knowledge dissemination. However, careful adherence to ethical guidelines and privacy concerns is essential to maximize its benefits while minimizing risks. As social media continues to evolve, its role in shaping biomedical research and healthcare practices is anticipated to grow, necessitating ongoing exploration and adaptation by stakeholders.
Epithelial dysplasia is a condition characterized by a spectrum of architectural and cytological alterations to the epithelium, resulting from the accumulation of genetic alterations. It is associated with an increased risk of cancer progression in a variety of organs. However, the variability of different grading systems, as well as inter- and intra-examiner variability, gives rise to concerns regarding the reliability of the results. Histopathology represents the gold standard for the diagnosis of epithelial dysplasia. The combination of big data in pathology and artificial intelligence (AI) will facilitate the achievement of accurate diagnoses and treatments, providing objective and efficient methods to integrate and refine diverse morphological, molecular, and multi-omics information. This perspective provides a summary of the existing research and prospects for the application of AI to epithelial dysplasia in multiple organs. A number of studies have been conducted with the aim of developing a grading system and prognostic identification method for epithelial dysplasia in the oral cavity, larynx, esophagus, and stomach. Digital pathology-based AI may prove useful in facilitating the clinical management of epithelial dysplasia in multiple organs. In summary, digital pathology images obtained by scanning hematoxylin & eosin-stained slides, identifying image features, and building AI models using deep learning combined with machine learning algorithms, validated with real-world data from multicenter cohorts could provide AI as a promising clinical application in the future.
Healthcare strives to ensure overall physical, mental, and emotional well-being for individuals while managing limited resources efficiently. Digital technologies can offer cost reduction, improved user experience, and expanded capacity. In addition, modern automation technologies, which were implemented in industrial control systems or industrial automation control systems, are essential for ensuring the availability of societies’ critical cyber-physical systems (CPSs) and the services they provide, such as healthcare. This narrative literature review produces information that can be applied when planning and implementing an interdisciplinary biomedical and health informatics (BMHI) master’s education focused on the challenges of digitalization in the health sector. The review results that virtual human twins (VHTs) are revolutionizing healthcare by addressing people’s complex medical problems with real-time monitoring and precision care while digital twin (DT) technology can make the hospital’s operational processes resilient and efficient. Thus, future BMHI education must address these technologies with a multidisciplinary approach, including computer science, information science, engineering, basic sciences, health sciences, socio-behavioral sciences, and ethical, legal, and policy aspects. Collected and cumulative data is essential for cognitive DTs. A prerequisite for this data is information sharing between different CPSs. Better information sharing and the development of scalable cognitive DTs and VHTs, the provision of critical services, quality, and cost-effectiveness, as well as health, safety, and resilience, will improve. Similarities between peoples’ health information exchange and information needed for ensuring the resilience of CPSs exist. Since humans are in many ways more complex than CPSs, security engineers have a lot to learn from VHTs in maintaining the resilience of CPSs. Cross-sectoral research and cooperation with different disciplines are essential for the progress of both human health and the resilience of CPSs. Along with interdisciplinary research cooperation, educational cooperation should also be intensified.
Aim: COVID-19 has affected more than 223 countries worldwide and in the post-COVID era, there is a pressing need for non-invasive, low-cost, and highly scalable solutions to detect COVID-19. This study focuses on the analysis of voice features and machine learning models in the automatic detection of COVID-19.
Methods: We develop a deep learning model to identify COVID-19 from voice recording data. The novelty of this work is in the development of deep learning models for COVID-19 identification from only voice recordings. We use the Cambridge COVID-19 Sound database which contains 893 speech samples, crowd-sourced from 4,352 participants via a COVID-19 Sounds app. Voice features including Mel-spectrograms and Mel-frequency cepstral coefficients (MFCC) and convolutional neural network (CNN) Encoder features are extracted. Based on the voice data, we develop deep learning classification models to detect COVID-19 cases. These models include long short-term memory (LSTM), CNN and Hidden-Unit BERT (HuBERT).
Results: We compare their predictive power to baseline machine learning models. HuBERT achieves the highest accuracy of 86% and the highest AUC of 0.93.
Conclusions:The results achieved with the proposed models suggest promising results in COVID-19 diagnosis from voice recordings when compared to the results obtained from the state-of-the-art.
Aim: This study represents preliminary research for testing the effectiveness of the Self-Aware Deep Learning (SAL) methodology in the context of medical diagnostics using various types of attributes. By enhancing traditional AI models with self-aware capabilities, this approach seeks to improve diagnostic accuracy and patient outcomes in medical settings.
Methods: This research discusses an introduction of SAL methodology into the medical field. SAL incorporates continuous self-assessment, allowing the AI to adjust its parameters and structure autonomously in response to changing inputs and performance metrics. The methodology is applied to medical diagnostics, utilizing real medical datasets available in the public domain. These datasets encompass a partial range of medical conditions and diagnostic scenarios, providing an initial test background for a preliminary evaluation of the effectiveness of SAL in a real-world context.
Results: The study shows encouraging results in enhancing diagnostic accuracy and patient outcomes. Through continuous assessment and autonomous adjustments of its own neural network architecture, self-aware AI systems show improvements in adaptability, in the classification of real datasets and diagnostic process. Additional experiments on expanded data sets are necessary for validating these preliminary results.
Conclusions: Tests on real data show that Self-Aware Deep Neural Networks present promising potential for improving medical diagnostic capabilities. They offer advantages such as enhanced adaptability to varying data qualities, improved error detection, efficient resource allocation, and increased transparency in AI-assisted diagnoses. However, considering the limited size of the test data set used in this research, further validation is required through additional experiments on larger data sets.