Evaluating the Association Between Comorbidities and COVID-19 Severity Scoring on Chest CT Examinations Between the Two Waves of COVID-19: An Imaging Study Using Artificial Intelligence

Ajmera, Pranav; Kharat, Amit; Dhirawani, Satvik; Khaladkar, Sanjay M; Kulkarni, Viraj; Duddalwar, Vinay; Lamghare, Purnachandra; Rathi, Snehal

doi:10.7759/cureus.21656

Cited by 3 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To begin with, the encoder is the most adapted and most changeable component of the UNet architecture. Since it is practically not possible to study each of the architectural variations in the encoder, we have therefore listed here the 23 variations (E1 to E23, representing encoder changes) along with their references in a tabular format and it is as follows: (E1) conventional system (Ronneberger) [43][44][45][46][47][48][49][50][51][52]90]; (E2) cascade of convolutions [77,91,99,116,117]; (E3) parallel convolutions (multiple convolution network) [57]; (E4) convolution with dropout [70,76,86,95,101,102,134,138]; (E5) Residual network [76,78,105,129,135,138,[149][150][151]; (E6) Xception encoder [56,88,112]; (E7) encoder layers with independent inputs [104,140]; (E8) squeeze excitation (SE) network [92,103,138]; (E9) pooling types (max pooling, global average pooling) [95]; (E10) input image dimension change with changing filter (channe...…”

Section: A Encoder Variationsmentioning

confidence: 99%

“…The different fundamental blocks which were adapted for UNet modification were (Table 4): (1) residual block [75,76,78,84,88,105,129,135,138]; (2) classifier in encoder [145]; (3) Xception block [56,88]; (4) dense layer block [68,100,102,122,142]; (5) recurrent residual block ; (6) attention block [65, 66, 71, 75, 113, 125, 128, 129, 131-135, 139, 161]; (7) dropout layer [70,76,86,95,101,102,134,138]; (8) dilated convolution [67,76]; (9) transpose convolution [66,88,95,137,139]; (10) SE network [92,103,125,133,138], and (11) squeeze and excitation block [92,103,125,133,138].…”

Section: G Understanding Major Blocks Affecting For Unet Modificationmentioning

confidence: 99%

See 1 more Smart Citation

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

Suri¹,

Bhagawati

Agarwal³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Background & Motivation: Biomedical image segmentation (BIS) task is challenging due to the variations in organ types, position, shape, size, scale, orientation, and image contrast. Conventional methods lack accurate and automated designs. Artificial intelligence (AI)-based UNet has recently dominated BIS. This is the first review of its kind that microscopically addressed UNet types by complexity, stratification of UNet by its components, addressing UNet in vascular vs. non-vascular framework, the key to segmentation challenge vs. UNet-based architecture, and finally interfacing the three facets of AI, the pruning, the explainable AI (XAI), and the AI-bias. Methods: PRISMA was used to select 267 UNet-based studies. Five classes were identified and labeled as conventional UNet, superior UNet, attention-channel UNet, hybrid UNet, and ensemble UNet. We discovered 81 variations of UNet by considering six kinds of components, namely encoder, decoder, skip connection, bridge network, loss function, and their combination. Vascular vs. non-vascular UNet architecture was compared. AP(ai)Bias 2.0-UNet was identified in these UNet classes based on (i) attributes of UNet architecture and its performance, (ii) explainable AI (XAI), and, (iii) pruning (compression). Five bias methods such as (i) ranking, (ii) radial, (iii) regional area, (iv) PROBAST, and (v) ROBINS-I were applied and compared using a Venn diagram. Findings and Conclusions: Vascular and non-vascular UNet systems dominated with sUNet classes with attention. The majority of the studies suffered from low interest in XAI and pruning strategies. None of the UNet models qualified to be bias-free. There is a need to move from paper-to-practice paradigms for clinical evaluation and settings. INDEX TERMS Image segmentation; vascular; non-vascular; UNet classes; UNet variations; UNetcomponents; explainable AI; pruning; bias.

show abstract

Section: A Encoder Variationsmentioning

confidence: 99%

Section: G Understanding Major Blocks Affecting For Unet Modificationmentioning

confidence: 99%

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

Suri¹,

Bhagawati

Agarwal³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, research has shown that the radiologic features of pneumonia attributed to COVID-19 were not found to differ significantly between the first wave of the pandemic and the subsequent ones. Accordingly, our results can be extrapolated to patients currently hospitalized in the ICU due to severe COVID-19, since the major characteristics of severe disease have not drastically altered [ 27 , 28 ].…”

Section: Study Limitationsmentioning

confidence: 99%

The Real Impact of Age on Mortality in Critically Ill COVID-19 Patients

Bakakos

Koukaki

Ampelioti

et al. 2023

JPM

View full text Add to dashboard Cite

Objective: The impact of severe infection from COVID-19 and the resulting need for life support in an ICU environment is a fact that caused immense pressure in healthcare systems around the globe. Accordingly, elderly people faced multiple challenges, especially after admission to the ICU. On this basis, we performed this study to assess the impact of age on COVID-19 mortality in critically ill patients. Materials and Methods: In this retrospective study, we collected data from 300 patients who were hospitalized in the ICU of a Greek respiratory hospital. We split patients into two age groups using a threshold of 65 years old. The primary objective of the study was the survival of patients in a follow up period of 60 days after their admission to the ICU. Secondary objectives were to determine whether mortality is affected by other factors, including sepsis and clinical and laboratory factors, Charlson Comorbidity Index (CCI), APACHE II and d-dimers, CRP, etc. Results: The survival of all patients in the ICU was 75.7%. Those in the <65 years old age group expressed a survival rate of 89.3%, whereas those in the ≥65 years old age group had a survival rate of 58% (p-value < 0.001). In the multivariate Cox regression, the presence of sepsis and an increased CCI were independent predictors of mortality in 60 days (p-value < 0.001), while the age group did not maintain its statistical significance (p-value = 0.320). Conclusions: Age alone as a simple number is not capable of predicting mortality in patients with severe COVID-19 in the ICU. We must use more composite clinical markers that may better reflect the biological age of patients, such as CCI. Moreover, the effective control of infections in the ICU is of utmost importance for the survival of patients, since avoiding septic complications can drastically improve the prognosis of all patients, regardless of age.

show abstract

“…Many published studies have focused on data spanning one or a couple of COVID-19 waves at a time [ 6 , 7 , 8 ], but data on the evolution of COVID-19 across waves are scarce [ 9 ]. Our study was set up to analyse the clinical characteristics and severity of patients hospitalised for COVID-19 during the COVID-19 pandemic in a Belgian university hospital.…”

Section: Introductionmentioning

confidence: 99%

Surfing the Waves: Differences in Hospitalised COVID-19 Patients across 4 Variant Waves in a Belgian University Hospital

Seyler

Nedervelde

Cock

et al. 2023

Viruses

View full text Add to dashboard Cite

The unprecedented COVID-19 pandemic took the form of successive variant waves, spreading across the globe. We wanted to investigate any shift in hospitalised patients’ profiles throughout the pandemic. For this study, we used a registry that collected data automatically from electronic patient health records. We compared clinical data and severity scores, using the National Institute of Health (NIH) severity scores, from all patients admitted for COVID-19 during four SARS-CoV-2 variant waves. Our study concluded that patients hospitalised for COVID-19 showed very different profiles across the four variant waves in Belgium. Patients were younger during the Alpha and Delta waves and frailer during the Omicron period. ‘Critical’ patients according to the NIH criteria formed the largest fraction among the Alpha wave patients (47.7%), while ‘severe’ patients formed the largest fraction among Omicron patients (61.6%). We discussed host factors, vaccination status, and other confounders to put this into perspective. High-quality real-life data remain crucial to inform stakeholders and policymakers that shifts in patients’ clinical profiles have an impact on clinical practice.

show abstract

Evaluating the Association Between Comorbidities and COVID-19 Severity Scoring on Chest CT Examinations Between the Two Waves of COVID-19: An Imaging Study Using Artificial Intelligence

Cited by 3 publications

References 26 publications

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

The Real Impact of Age on Mortality in Critically Ill COVID-19 Patients

Surfing the Waves: Differences in Hospitalised COVID-19 Patients across 4 Variant Waves in a Belgian University Hospital

Contact Info

Product

Resources

About