Applications of Machine Learning and High-Performance Computing in the Era of COVID-19

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.

A Clinical Update on SARS-CoV-2: Pathology and Development of Potential Inhibitors

SARS-CoV-2 (severe acute respiratory syndrome) is highly infectious and causes severe acute respiratory distress syndrome (SARD), immune suppression, and multi-organ failure. For SARS-CoV-2, only supportive treatment options are available, such as oxygen supportive therapy, ventilator support, antibiotics for secondary infections, mineral and fluid treatment, and a significant subset of repurposed effective drugs. Viral targeted inhibitors are the most suitable molecules, such as ACE2 (angiotensin-converting enzyme-2) and RBD (receptor-binding domain) protein-based inhibitors, inhibitors of host proteases, inhibitors of viral proteases 3CLpro (3C-like proteinase) and PLpro (papain-like protease), inhibitors of replicative enzymes, inhibitors of viral attachment of SARS-CoV-2 to the ACE2 receptor and TMPRSS2 (transmembrane serine proteinase 2), inhibitors of HR1 (Heptad Repeat 1)-HR2 (Heptad Repeat 2) interaction at the S2 protein of the coronavirus, etc. Targeting the cathepsin L proteinase, peptide analogues, monoclonal antibodies, and protein chimaeras as RBD inhibitors interferes with the spike protein's ability to fuse to the membrane. Targeting the cathepsin L proteinase, peptide analogues, monoclonal antibodies, and protein chimaeras as RBD inhibitors interferes with the spike protein's ability to fuse to the membrane. Even with the tremendous progress made, creating effective drugs remains difficult. To develop COVID-19 treatment alternatives, clinical studies are examining a variety of therapy categories, including antibodies, antivirals, cell-based therapy, repurposed diagnostic medicines, and more. In this article, we discuss recent clinical updates on SARS-CoV-2 infection, clinical characteristics, diagnosis, immunopathology, the new emergence of variant, SARS-CoV-2, various approaches to drug development and treatment options. The development of therapies has been complicated by the global occurrence of many SARS-CoV-2 mutations. Discussion of this manuscript will provide new insight into drug pathophysiology and drug development.

Domain Shifts in Machine Learning Based Covid-19 Diagnosis From Blood Tests

Many previous studies claim to have developed machine learning models that diagnose COVID-19 from blood tests. However, we hypothesize that changes in the underlying distribution of the data, so called domain shifts, affect the predictive performance and reliability and are a reason for the failure of such machine learning models in clinical application. Domain shifts can be caused, e.g., by changes in the disease prevalence (spreading or tested population), by refined RT-PCR testing procedures (way of taking samples, laboratory procedures), or by virus mutations. Therefore, machine learning models for diagnosing COVID-19 or other diseases may not be reliable and degrade in performance over time. We investigate whether domain shifts are present in COVID-19 datasets and how they affect machine learning methods. We further set out to estimate the mortality risk based on routinely acquired blood tests in a hospital setting throughout pandemics and under domain shifts. We reveal domain shifts by evaluating the models on a large-scale dataset with different assessment strategies, such as temporal validation. We present the novel finding that domain shifts strongly affect machine learning models for COVID-19 diagnosis and deteriorate their predictive performance and credibility. Therefore, frequent re-training and re-assessment are indispensable for robust models enabling clinical utility.

Domain Shifts in Machine Learning Based Covid-19 Diagnosis From Blood Tests

Many previous studies claim to have developed machine learning models that diagnose COVID-19 from blood tests. However, we hypothesize that changes in the underlying distribution of the data, so called domain shifts, affect the predictive performance and reliability and are a reason for the failure of such machine learning models in clinical application. Domain shifts can be caused, e.g., by changes in the disease prevalence (spreading or tested population), by refined RT-PCR testing procedures (way of taking samples, laboratory procedures), or by virus mutations. Therefore, machine learning models for diagnosing COVID-19 or other diseases may not be reliable and degrade in performance over time. We investigate whether domain shifts are present in COVID-19 datasets and how they affect machine learning methods. We further set out to estimate the mortality risk based on routinely acquired blood tests in a hospital setting throughout pandemics and under domain shifts. We reveal domain shifts by evaluating the models on a large-scale dataset with different assessment strategies, such as temporal validation. We present the novel finding that domain shifts strongly affect machine learning models for COVID-19 diagnosis and deteriorate their predictive performance and credibility. Therefore, frequent re-training and re-assessment are indispensable for robust models enabling clinical utility.

Acting Instead of Reacting—Ensuring Employee Retention during Successful Introduction of i4.0

The increasing implementation of digital technologies has various positive impacts on companies. However, many companies often rush into such an implementation of technological trends without sufficient preparation and pay insufficient attention to the human factors involved in digitization. This phenomenon can be exacerbated when these technologies become highly dependent, as during the COVID-19 pandemic. This study aims to better understand challenges and to propose solutions for a successful implementation of digitized technology. A literature review is combined with survey results and specific consulting strategies. Data from the first wave of the COVID-19 pandemic in Germany were collected by means of an online survey, with a representative sample of the German population. However, we did not reveal any correlation between home office and suffering, mental health, and physical health (indicators of digitization usage to cope with COVID-19 pandemic), but rather that younger workers are more prone to using digitized technology. Based on previous findings that older individuals tend to have negative attitudes toward digital transformation, appropriate countermeasures are needed to help them become more tech-savvy. Accordingly, a software tool is proposed. The tool can help the management team to manage digitization efficiently. Employee well-being can be increased as companies are made aware of necessary measures such as training for individuals and groups at an early stage.

Opportunities and Challenges of Smartglass-Assisted Interactive Telementoring

The widespread adoption of wearables, extended reality, and metaverses has accelerated the diverse configurations of remote collaboration and telementoring systems. This paper explores the opportunities and challenges of interactive telementoring, especially for wearers of smartglasses. In particular, recent relevant studies are reviewed to derive the needs and trends of telementoring technology. Based on this analysis, we define what can be integrated into smartglass-enabled interactive telementoring. To further illustrate this type of special use case for telementoring, we present five illustrative and descriptive scenarios. We expect our specialized use case to support various telementoring applications beyond medical and surgical telementoring, while harmoniously fostering cooperation using the smart devices of mentors and mentees at different scales for collocated, distributed, and remote collaboration.