Combating Covid-19 using machine learning and deep learning: Applications, challenges, and future perspectives

Paul, Showmick Guha; Saha, Arpa; Biswas, Al Amin; Zulfiker, Md Sabab; Arefin, Mohammad Shamsul; Rahman, Md. Mahfujur; Reza, Ahmed Wasif

doi:10.1016/j.array.2022.100271

Cited by 22 publications

(8 citation statements)

References 96 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods rely on diverse patient data types, including imaging data such as Chest X-ray, CT, MRI, ultrasound, and non-imaging data like RT-PCR, clinical records, epidemiological data, blood tests, and laboratory results. Additionally, remote video diagnostics and consultations are increasingly available in clinics and hospitals, with future advancements in AI and Natural Language Processing (NLP)-based technologies potentially leading to the development of remote video diagnostic programs, which could replace initial hospital visits for COVID-19 patients [152,153]. These approaches could be used for the early prediction of the long COVID.…”

Section: Discussion On the Evolving Diagnostic Criteria And Methodolo...mentioning

confidence: 99%

Are the Comorbidities Constitute an Intrinsic Factor for Long COVID?

Ashmawy,

Hammouda,

El-Maradny

et al. 2024

Preprint

View full text Add to dashboard Cite

Long COVID, a name often given to the persistent symptoms following acute SARS-CoV-2 infection, poses a multifaceted challenge for health. This review explores the intrinsic relationship between comorbidities and autoimmune responses in shaping the trajectory of long COVID. Autoantibodies have emerged as significant players in COVID-19 pathophysiology, with implications for disease severity and progression. Studies show immune dysregulation persisting months after infection, marked by activated innate immune cells and high cytokine levels. The presence of autoantibodies against various autoantigens suggests their potential as comorbid factors in long COVID. Additionally, the formation of immune complexes may lead to severe disease progression, highlighting the urgency for early detection and intervention. Furthermore, long COVID is highly linked to cardiovascular complications and neurological symptoms, posing challenges in diagnosis and management. Multidisciplinary approaches, including vaccination, tailored rehabilitation, and pharmacological interventions, are used for mitigating long COVID's burden. However, numerous challenges persist, from evolving diagnostic criteria to addressing the psychosocial impact and predicting disease outcomes. Leveraging AI-based applications holds promise in enhancing patient management and improving our understanding of long COVID. As research continues to unfold, unravelling the complexities of long COVID remains paramount for effective intervention and patient care.

show abstract

Section: Discussion On the Evolving Diagnostic Criteria And Methodolo...mentioning

confidence: 99%

Are the Comorbidities Constitute an Intrinsic Factor for Long COVID?

Ashmawy,

Hammouda,

El-Maradny

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…AI techniques are one of the techniques that have attracted the most attention in recent years, as they can monitor, track, and assess the spread of SARS-CoV-2. [ 31 ] Identifying effective diagnostic options for the early diagnosis of COVID-19 is one of the most researched areas. For the diagnosis of SARS-CoV-2, a 2-step technique was generally used, one of which was a laboratory technique and the other a medical imaging technique.…”

Section: Discussionmentioning

confidence: 99%

COVID-19 studies involving machine learning methods: A bibliometric study

Baygül Eden,

Bakir Kayi,

Erdem

et al. 2023

Medicine

View full text Add to dashboard Cite

Background: Machine learning (ML) and artificial intelligence (AI) techniques are gaining popularity as effective tools for coronavirus disease of 2019 (COVID-19) research. These strategies can be used in diagnosis, prognosis, therapy, and public health management. Bibliometric analysis quantifies the quality and impact of scholarly publications. ML in COVID-19 research is the focus of this bibliometric analysis. Methods: A comprehensive literature study found ML-based COVID-19 research. Web of Science (WoS) was used for the study. The searches included “machine learning,” “artificial intelligence,” and COVID-19. To find all relevant studies, 2 reviewers searched independently. The network visualization was analyzed using VOSviewer 1.6.19. Results: In the WoS Core, the average citation count was 13.6 ± 41.3. The main research areas were computer science, engineering, and science and technology. According to document count, Tao Huang wrote 14 studies, Fadi Al-Turjman wrote 11, and Imran Ashraf wrote 11. The US, China, and India produced the most studies and citations. The most prolific research institutions were Harvard Medical School, Huazhong University of Science and Technology, and King Abdulaziz University. In contrast, Nankai University, Oxford, and Imperial College London were the most mentioned organizations, reflecting their significant research contributions. First, “Covid-19” appeared 1983 times, followed by “machine learning” and “deep learning.” The US Department of Health and Human Services funded this topic most heavily. Huang Tao, Feng Kaiyan, and Ashraf Imran pioneered bibliographic coupling. Conclusion: This study provides useful insights for academics and clinicians studying COVID-19 using ML. Through bibliometric data analysis, scholars can learn about highly recognized and productive authors and countries, as well as the publications with the most citations and keywords. New data and methodologies from the pandemic are expected to advance ML and AI modeling. It is crucial to recognize that these studies will pioneer this subject.

show abstract

“…RF and XGboost have unique explanatory properties, and they are both integrated algorithms of the decision tree, which can improve the accuracy of the decision tree to a certain extent [[ 22 ]]. According to a previous study, for classification purposes, the RF and XGBoost classification models performed most optimally with clinical data [[ 23 ]]. In addition, compared with other algorithms, the features of multicollinearity do not affect the predictive ability of RF and XGboost models based on decision trees [[ 24 , 25 ]].…”

Section: Methodsmentioning

confidence: 99%