Artificial neural network based prediction of the lung tissue involvement as an independent in‐hospital mortality and mechanical ventilation risk factor in COVID‐19

Parczewski, Miłosz; Kufel, Jakub; Aksak‐Wąs, Bogusz; Piwnik, Joanna; Chober, Daniel; Puzio, Tomasz; Lesiewska, Laura; Białkowski, Sebastian; Rafalska‐Kosior, Milena; Wydra, Jacek; Awgul, Krystian; Grobelna, Milena; Majchrzak, Adam; Dunikowski, Kosma; Jurczyk, Krzysztof; Podyma, Marek; Serwin, Karol; Musiałek, Jakub

doi:10.1002/jmv.28787

Cited by 4 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other individuals had cold feeling and dysfunction of gustation or olfaction which were possibly temporary side effects of the immune response to vaccination 24 , 25 . Studies have shown that using artificial intelligence to interpret radiological findings provides high sensitivity and specificity for the diagnosis of COVID-19 as well as predicting severity 26 , 27 . Although currently, COVID-19 infection is no longer as serious as in previous periods the disease still appears seasonally in Vietnam as well as many other countries around the world.…”

Section: Discussionmentioning

confidence: 99%

Clinical characteristics of COVID-19 patients treated in emergency COVID-19 hospitals in Vietnam: Experience from Phutho province, Vietnam

Nguyen,

Tran,

Jong

et al. 2024

Int. J. Med. Sci.

View full text Add to dashboard Cite

Background: This study aimed to evaluate the clinical characteristics, patient's management approaches, and outcomes of the COVID-19 patients in Phu Tho Province, Vietnam. Methods: A retrospective, multicenter study of 2166 COVID-19 patients in 13 hospitals in Phutho Province, Vietnam. The subjects were divided into 3 groups based on vaccination status: unvaccinated group, 1 st dose of vaccine group, 2 nd dose of vaccine group. The clinical characteristics, management approaches, and outcomes were collected and compared between the 3 groups. Results: The hospitalization rate of the 3 groups decreased from the unvaccinated group, the 1 st dose of vaccinated group, to the 2 nd dose of vaccinated group, 42.61%; 30,24% and 27,15% respectively. The 19-40 years old group had the highest hospitalization rate (38,1%) together with the group that had not accepted the full COVID 19 vaccination dose (57,64%). The 2 nd dose of vaccinated group had the lowest percentages of high temperature, cough, dyspnea, chest pain and sore throat. The unvaccinated group had the highest heart rate, respiratory rate and SpO2 compared to the two other groups. The percentage needing Immunomodulation and Anticoagulant Therapy was highest (6.8% and 1.4 % respectively) in the unvaccinated group. The percentage receiving Antiviral Therapy was highest (42,5%) in those who had received the 2 nd dose of vaccine. Conclusions: COVID-19 vaccination improved the symptoms of the patients and should be accepted in all ages.

show abstract

Section: Discussionmentioning

confidence: 99%

Clinical characteristics of COVID-19 patients treated in emergency COVID-19 hospitals in Vietnam: Experience from Phutho province, Vietnam

Nguyen,

Tran,

Jong

et al. 2024

Int. J. Med. Sci.

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence (AI) is a popular topic in radiology such as for rapid disease (e.g., COVID-19) detection on various platforms including mobile devices [ 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 ]. Additionally, the number of AI research articles in radiology has grown exponentially over recent years [ 1 , 2 ].…”

Section: Introductionmentioning

confidence: 99%

Generative Adversarial Network (Generative Artificial Intelligence) in Pediatric Radiology: A Systematic Review

2023

Children

View full text Add to dashboard Cite

Generative artificial intelligence, especially with regard to the generative adversarial network (GAN), is an important research area in radiology as evidenced by a number of literature reviews on the role of GAN in radiology published in the last few years. However, no review article about GAN in pediatric radiology has been published yet. The purpose of this paper is to systematically review applications of GAN in pediatric radiology, their performances, and methods for their performance evaluation. Electronic databases were used for a literature search on 6 April 2023. Thirty-seven papers met the selection criteria and were included. This review reveals that the GAN can be applied to magnetic resonance imaging, X-ray, computed tomography, ultrasound and positron emission tomography for image translation, segmentation, reconstruction, quality assessment, synthesis and data augmentation, and disease diagnosis. About 80% of the included studies compared their GAN model performances with those of other approaches and indicated that their GAN models outperformed the others by 0.1–158.6%. However, these study findings should be used with caution because of a number of methodological weaknesses. For future GAN studies, more robust methods will be essential for addressing these issues. Otherwise, this would affect the clinical adoption of the GAN-based applications in pediatric radiology and the potential advantages of GAN could not be realized widely.

show abstract

Interferon‐responsive neutrophils and macrophages extricate SARS‐CoV‐2 Omicron critical patients from the nasty fate of sepsis

Wang,

Zhang,

Lei

et al. 2024

Journal of Medical Virology

View full text Add to dashboard Cite

The SARS‐CoV‐2 Omicron variant is characterized by its high transmissibility, which has caused a worldwide epidemiological event. Yet, it turns ominous once the disease progression degenerates into severe pneumonia and sepsis, presenting a horrendous lethality. To elucidate the alveolar immune or inflammatory landscapes of Omicron critical‐ill patients, we performed single‐cell RNA‐sequencing (scRNA‐seq) of bronchoalveolar lavage fluid (BALF) from the patients with critical pneumonia caused by Omicron infection, and analyzed the correlation between the clinical severity scores and different immune cell subpopulations. In the BALF of Omicron critical patients, the alveolar violent myeloid inflammatory environment was determined. ISG15+ neutrophils and CXCL10+ macrophages, both expressed the interferon‐stimulated genes (ISGs), were negatively correlated with clinical pulmonary infection score, while septic CST7+ neutrophils and inflammatory VCAN+ macrophages were positively correlated with sequential organ failure assessment. The percentages of ISG15+ neutrophils were associated with more protective alveolar epithelial cells, and may reshape CD4+ T cells to the exhaustive phenotype, thus preventing immune injuries. The CXCL10+ macrophages may promote plasmablast/plasma cell survival and activation as well as the production of specific antibodies. As compared to the previous BALF scRNA‐seq data from SARS‐CoV‐2 wild‐type/Alpha critical patients, the subsets of neutrophils and macrophages with pro‐inflammatory and immunoregulatory features presented obvious distinctions, suggesting an immune disparity in Omicron variants. Overall, this study provides a BALF single‐cell atlas of Omicron critical patients, and suggests that alveolar interferon‐responsive neutrophils and macrophages may extricate SARS‐CoV‐2 Omicron critical patients from the nasty fate of sepsis.

show abstract

Artificial neural network based prediction of the lung tissue involvement as an independent in‐hospital mortality and mechanical ventilation risk factor in COVID‐19

Cited by 4 publications

References 40 publications

Clinical characteristics of COVID-19 patients treated in emergency COVID-19 hospitals in Vietnam: Experience from Phutho province, Vietnam

Clinical characteristics of COVID-19 patients treated in emergency COVID-19 hospitals in Vietnam: Experience from Phutho province, Vietnam

Generative Adversarial Network (Generative Artificial Intelligence) in Pediatric Radiology: A Systematic Review

Interferon‐responsive neutrophils and macrophages extricate SARS‐CoV‐2 Omicron critical patients from the nasty fate of sepsis

Contact Info

Product

Resources

About