COVID-19 Tracheostomy Outcomes.

OBJECTIVES: (1) Assess overall COVID-19 mortality in ventilated patients with and without tracheostomy. (2) Determine the impact of tracheostomy on mechanical ventilation duration, overall length of stay (LOS), and intensive care unit (ICU) LOS for patients with COVID-19. STUDY DESIGN: Case series with planned chart review. SETTING: Single-institution tertiary care center. METHODS: Patients with COVID-19 who were ≥18 years old and requiring invasive positive pressure ventilation (IPPV) met inclusion criteria. Patients were stratified into 2 cohorts: IPPV with tracheostomy and IPPV with intubation only. Cohorts were analyzed for the following primary outcome measures: mortality, LOS, ICU LOS, and IPPV duration. RESULTS: An overall 258 patients with IPPV met inclusion criteria: 46 (18%) with tracheostomy and 212 (82%) without (66% male; median age, 63 years [interquartile range, 18.75]). Average LOS, time in ICU, and time receiving IPPV were longer in the tracheostomy cohort (P < .01). Ability to wean from IPPV was similar between cohorts (P > .05). The number of deaths in the nontracheostomy cohort (54%) was significantly higher than the tracheostomy cohort (29%, P < .01). CONCLUSIONS: While tracheostomy placement in patients with COVID-19 did not shorten overall LOS, mechanical ventilation duration, or ICU LOS, patients with a tracheostomy experienced a significantly lower number of deaths vs those without. One goal for tracheostomy is improved pulmonary toilet with associated shortened IPPV requirements. Our study did not identify this advantage among the COVID-19 population. However, this study demonstrates that the need for tracheostomy in the COVID-19 setting does not portent a poor prognostic factor, as patients with a tracheostomy experienced a significantly higher survival rate than their nontracheostomy counterparts.

An Investigation into the Aging of Disposable Face Masks in Landfill Leachate

Due to the excessive use of disposable face masks during the Covid-19 pandemic, their accumulation has posed a great threat to the environment. In this study, we explored the fate of masks after being disposed in landfill. We simulated the possible process that masks would experience, including the exposure to sunlight before being covered and the contact with landfill leachate. After exposure to UV radiation, all three mask layers exhibited abrasions and fractures on the surface and became unstable with the increased UV radiation duration showed aging process. The alterations in chemical groups of masks as well as the lower mechanical strength of masks after UV weathering were detected to prove the happened aging process. Then it was found that the aging of masks in landfill leachate was further accelerated compared to these processes occurring in deionized water. Furthermore, the carbonyl index and isotacticity of the mask samples after aging for 30 days in leachate were higher than those of pristine materials, especially for those endured longer UV radiation. Similarly, the weight and tensile strength of the aged masks were also found lower than the original samples. Masks were likely to release more microparticles and high concentration of metal elements into leachate than deionized water after UV radiation and aging. After being exposed to UV radiation for 48h, the concentration of released particles in leachate was 39.45μL/L after 1 day and then grew to 309.45μL/L after 30 days of aging. Seven elements (Al, Cr, Cu, Zn, Cd, Sb and Pb) were detected in leachate and the concentration of this metal elements increased with the longer aging time. The findings of this study can advance our understanding of the fate of disposable masks in the landfill and develop the strategy to address this challenge in waste management.

Effect of adding high-intensity interval training to diet and carboxytherapy on metabolic cardiovascular risk factors in women with metabolic syndrome.

Introduction: Metabolic syndrome has traditionally been associated with cardiovascular diseases and has recently been linked to increased susceptibility to COVID-19 infection, thus highlighting the need for multimodal interventions to optimize management of this condition. Aim: To assess the effects of high-intensity interval training (HIIT) alongside a low-fat diet and carboxytherapy on metabolic syndrome features. Material and methods: Sixty women (50-60 years old) diagnosed with metabolic syndrome were assigned to a 4-week intervention of either HIIT in combination with a low-fat diet and carboxytherapy (experimental group: n1 = 30, age = 54.17 ±2.82 years, body mass index (BMI) = 32.10 ±0.91), or a low-fat diet and carboxytherapy only (active control group: n2 = 30, age = 54.10 ±2.64 years, BMI = 32.12 ±1.19). Exclusion criteria were uncontrolled hypertension, diabetes mellitus, coronary artery disease, smoking, contraindications to carboxytherapy, and contraindications to exercise testing/training. Outcome measures were waist circumference (WC), BMI, serum triglycerides (TG), systolic blood pressure (SBP), diastolic blood pressure (DBP), high-density lipoproteins (HDL), and fasting blood glucose (FBG). Results: Both groups showed significant improvements in all outcome measures compared to baseline values (p < 0.05). The experimental group showed significantly greater improvements in mean values of WC, BMI, TG, SBP, DBP, and FBG (p < 0.05), as well as a tendency for a significant difference in HDL (p = 0.075) compared to the control group. Conclusions: The addition of HIIT to a low-fat diet and carboxytherapy could lead to greater improvements in metabolic cardiovascular risk factors in women with metabolic syndrome than a low-fat diet and carboxytherapy alone. This could suggest a good rationale for the inclusion of HIIT in the multimodal interventions rendered to women with metabolic syndrome.

Development of spiro-3-indolin-2-one containing compounds of antiproliferative and anti-SARS-CoV-2 properties.

A series of 1″-(alkylsulfonyl)-dispiro[indoline-3,2'-pyrrolidine-3',3″-piperidine]-2,4″-diones 6a‒o has been synthesized through regioselective multi-component azomethine dipolar cycloaddition reaction of 1-(alkylsulfonyl)-3,5-bis(ylidene)-piperidin-4-ones 3a‒h. X-ray diffraction studies (6b‒d,h) confirmed the structures. The majority of the synthesized analogs reveal promising antiproliferation properties against a variety of human cancer cell lines (MCF7, HCT116, A431 and PaCa2) with good selectivity index towards normal cell (RPE1). Some of the synthesized agents exhibit potent inhibitory properties against the tested cell lines with higher efficacies than the standard references (sunitinib and 5-fluorouracil). Compound 6m is the most potent. Multi-targeted inhibitory properties against EGFR and VEGFR-2 have been observed for the synthesized agents. Flow cytometry supports the antiproliferation properties and shows the tested agents as apoptosis and necrosis forming. Vero cell viral infection model demonstrates the anti-SARS-CoV-2 properties of the synthesized agents. Compound 6f is the most promising (about 3.3 and 4.8 times the potency of the standard references, chloroquine and hydroxychloroquine). QSAR models explain and support the observed biological properties.

COVID-19 telehealth preparedness: a cross-sectional assessment of cardiology practices in the USA.

Aim: The COVID-19 pandemic forced medical practices to augment healthcare delivery to remote and virtual services. We describe the results of a nationwide survey of cardiovascular professionals regarding telehealth perspectives. Materials & methods: A 31-question survey was sent early in the pandemic to assess the impact of COVID-19 on telehealth adoption & reimbursement. Results: A total of 342 clinicians across 42 states participated. 77% were using telehealth, with the majority initiating usage 2 months after the COVID-19 shutdown. A variety of video-based systems were used. Telehealth integration requirements differed, with electronic medical record integration being mandated in more urban than rural practices (70 vs 59%; p < 0.005). Many implementation barriers surfaced, with over 75% of respondents emphasizing reimbursement uncertainty and concerns for telehealth generalizability given the complexity of cardiovascular diseases. Conclusion: Substantial variation exists in telehealth practices. Further studies and legislation are needed to improve access, reimbursement and the quality of telehealth-based cardiovascular care.

As the COVID-19 pandemic was just beginning, the American College of Cardiology administered a survey to cardiology professionals across the USA regarding their preparedness for telehealth and video-visits. The results demonstrated rapid adoption of video based telehealth services, however revealed uncertainty for how to best use these services in different practice settings. Many providers expressed concerns about how these visits will be compensated, but fortunately federal agencies have dramatically changed the way telehealth is reimbursed as the pandemic has progressed. Further studies are needed to explore the impact of telehealth on healthcare inequality, however we hope that rather it serves to increase healthcare access to all.

Impact of endometriosis on women's life decisions and goal attainment: a cross-sectional survey of members of an online patient community.

OBJECTIVES: To examine women's perceptions of endometriosis-associated disease burden and its impact on life decisions and goal attainment. DESIGN: An anonymous online survey was distributed in October 2018 through the social media network MyEndometriosisTeam.com. PARTICIPANTS: Women aged 19 years and older living in several English-speaking countries who self-identified as having endometriosis. OUTCOME MEASURES: Patients' perspectives on how endometriosis has affected their work, education, relationships, overall life decisions and attainment of goals. Subanalyses were performed for women who identified as 'less positive about the future' (LPAF) or had 'not reached their full potential' (NRFP) due to endometriosis. RESULTS: 743 women completed the survey. Women reported high levels of pain when pain was at its worst (mean score, 8.9 on severity scale of 0 (no pain) to 10 (worst imaginable pain)) and most (56%, n=415) experienced pain daily. Women reported other negative experiences attributed to endometriosis, including emergency department visits (66%, n=485), multiple surgeries (55%, n=406) and prescription treatments for symptoms of endometriosis (72%, n=529). Women indicated that they believed endometriosis had a negative impact on their educational and professional achievements, social lives/relationships and overall physical health. Most women 'somewhat agreed'/'strongly agreed' that endometriosis caused them to lose time in life (81%, n=601), feel LPAF (80%, n=589) and feel they had NRFP (75%, n=556). Women who identified as LPAF or NRFP generally reported more negative experiences than those who were non-LPAF or non-NRFP. CONCLUSIONS: Women who completed this survey reported pain and negative experiences related to endometriosis that were perceived to negatively impact major life-course decisions and attainment of goals. Greater practitioner awareness of the impact that endometriosis has on a woman's life course and the importance of meaningful dialogue with patients may be important for improving long-term management of the disease and help identify women who are most vulnerable.

The Role of 3D CT Imaging in the Accurate Diagnosis of Lung Function in Coronavirus Patients.

Early grading of coronavirus disease 2019 (COVID-19), as well as ventilator support machines, are prime ways to help the world fight this virus and reduce the mortality rate. To reduce the burden on physicians, we developed an automatic Computer-Aided Diagnostic (CAD) system to grade COVID-19 from Computed Tomography (CT) images. This system segments the lung region from chest CT scans using an unsupervised approach based on an appearance model, followed by 3D rotation invariant Markov-Gibbs Random Field (MGRF)-based morphological constraints. This system analyzes the segmented lung and generates precise, analytical imaging markers by estimating the MGRF-based analytical potentials. Three Gibbs energy markers were extracted from each CT scan by tuning the MGRF parameters on each lesion separately. The latter were healthy/mild, moderate, and severe lesions. To represent these markers more reliably, a Cumulative Distribution Function (CDF) was generated, then statistical markers were extracted from it, namely, 10th through 90th CDF percentiles with 10% increments. Subsequently, the three extracted markers were combined together and fed into a backpropagation neural network to make the diagnosis. The developed system was assessed on 76 COVID-19-infected patients using two metrics, namely, accuracy and Kappa. In this paper, the proposed system was trained and tested by three approaches. In the first approach, the MGRF model was trained and tested on the lungs. This approach achieved 95.83% accuracy and 93.39% kappa. In the second approach, we trained the MGRF model on the lesions and tested it on the lungs. This approach achieved 91.67% accuracy and 86.67% kappa. Finally, we trained and tested the MGRF model on lesions. It achieved 100% accuracy and 100% kappa. The results reported in this paper show the ability of the developed system to accurately grade COVID-19 lesions compared to other machine learning classifiers, such as k-Nearest Neighbor (KNN), decision tree, naïve Bayes, and random forest.

SAR and QSAR of COVID-19 Main Protease-Inhibitor Interactions of Recently X-ray Crystalized Complexes.

COVID-19 is still widespread worldwide and up to now there is no established antiviral able to control the disease. Main protease is responsible for the viral replication and transcription; thus, its inhibition is a promising route to control virus proliferation. The present study aims to examine detail interactions between main protease and recently reported ninety-seven inhibitors with available X-ray crystallography to define factors enhance inhibition activity; thirty-two of most potent inhibitors were examined to identify sites and types of interaction. The study showed formation of covalent bond, H-bond and hydrophobic interaction with key residues in the active side. Covalent bond is observed in seventeen complexes, all of them by attack of the 145Cys thiol group on Michael acceptor, aldehyde or its hydrate, α-ketoamide, double bond or acetamide methyl group; the latter type requires H-bonding between acetamide carbonyl oxygen and at least one of 143Gly, 144Ser or 145Cys. Potent inhibitors, disulfiram and ebselen docked in the same binding site. Accordingly, factors identify inhibition include forming covalent bond and existing terminal hydrophobic groups and amidic or peptidomimetic structure. Binding affinity was found correlated with topological diameter up to 24 bond, molecular size, branching, polar surface area up to 199 Å2 and hydrophilicity. Supplementary Information: The online version contains supplementary material available at 10.1007/s40011-021-01338-8.

Efficacy and safety of risankizumab for active psoriatic arthritis: 24-week results from the randomised, double-blind, phase 3 KEEPsAKE 2 trial.

OBJECTIVES: Risankizumab is an interleukin-23 inhibitor under study for the treatment of patients with psoriatic arthritis (PsA). The phase 3 KEEPsAKE 2 trial investigated the efficacy and safety of risankizumab versus placebo in patients with active PsA who had previous inadequate response or intolerance to ≤2 biological therapies (Bio-IR) and/or ≥1 conventional synthetic disease-modifying antirheumatic drug (csDMARD-IR). Results through week 24 are reported here. METHODS: Adults with PsA who were Bio-IR and/or csDMARD-IR were randomised to receive subcutaneously administered risankizumab 150 mg or placebo at weeks 0, 4 and 16 during a 24-week, double-blind treatment period. The primary endpoint was the proportion of patients who achieved ≥20% improvement in American College of Rheumatology score (ACR20) at week 24. Secondary endpoints assessed key domains of PsA and patient-reported outcomes. RESULTS: A total of 444 patients (median age 53 years, range 23-84 years) were randomised to risankizumab (n=224) or placebo (n=220); 206 patients (46.5%) were Bio-IR. At week 24, a significantly greater proportion of patients receiving risankizumab achieved the primary endpoint of ACR20 (51.3% vs 26.5%, p<0.001) and all secondary endpoints (p<0.05) compared with placebo. Serious adverse events were reported for 4.0% and 5.5% of risankizumab-treated and placebo-treated patients, respectively; serious infections were reported for 0.9% and 2.3%, respectively. CONCLUSION: Treatment with risankizumab resulted in significant improvements versus placebo in key disease outcomes and was well tolerated in patients with PsA who were Bio-IR and/or csDMARD-IR. TRIAL REGISTRATION NUMBER: NCT03671148.

Efficacy and safety of risankizumab for active psoriatic arthritis: 24-week results from the randomised, double-blind, phase 3 KEEPsAKE 1 trial.

OBJECTIVE: To evaluate risankizumab, a biological therapy that inhibits interleukin 23, in patients with active psoriatic arthritis (PsA) who have responded inadequately or are intolerant to ≥1 conventional synthetic disease-modifying antirheumatic drug (csDMARD). METHODS: In the randomised, placebo-controlled, double-blind KEEPsAKE 1 trial, 964 patients with active PsA were randomised (1:1) to receive risankizumab 150 mg or placebo at weeks 0, 4 and 16. The primary endpoint was the proportion of patients achieving ≥20% improvement in American College of Rheumatology criteria (ACR20) at week 24. Here, we report the results from the 24-week double-blind period; the open-label period with all patients receiving risankizumab is ongoing. RESULTS: At week 24, a significantly greater proportion of patients receiving risankizumab achieved the primary endpoint of ACR20 (57.3% vs placebo, 33.5%; p<0.001). Significant differences were also observed for risankizumab versus placebo for the first eight ranked secondary endpoints, including skin and nail psoriasis endpoints, minimal disease activity and resolution of enthesitis and dactylitis (p<0.001). Adverse events and serious adverse events were reported at similar rates in the risankizumab and placebo groups. Serious infections were reported for 1.0% and 1.2% of patients receiving risankizumab and placebo, respectively. There was one death in the risankizumab group (urosepsis deemed unrelated to the study drug). CONCLUSIONS: Risankizumab treatment results in significantly greater improvement of signs and symptoms of PsA compared with placebo and is well tolerated in patients with active PsA who have responded inadequately or are intolerant to ≥1 csDMARD. TRIAL REGISTRATION NUMBER: NCT03675308.

Synthesis of aspirin-curcumin mimic conjugates of potential antitumor and anti-SARS-CoV-2 properties.

Series of piperidone-salicylate conjugates were synthesized through the reaction of 3E,5E-bis(arylidene)-4-piperidones with the appropriate acid chloride of acetylsalicylate in the presence of triethylamine. All the synthesized conjugates reveal antiproliferative properties against A431 (squamous skin) cancer cell line with potency higher than that of 5-fluorouracil. Many of the synthesized agents also exhibit promising antiproliferative properties against HCT116 (colon) cancer cell line, of which 5o and 5c are the most effective with 12.9, 9.8 folds potency compared with Sunitinib. Promising activity is also shown against MCF7 (breast) cancer cell line with 1.19, 1.12 folds relative to 5-fluorouracil. PI-flow cytometry of compound 5c supports the arrest of cell cycle at G1-phase. However, compound 5o and Sunitinib arrest the cell cycle at S-phase. The synthesized conjugates can be considered as multi-targeted tyrosine kinase inhibitors due to the promising properties against VEGFR-2 and EGFR in MCF7 and HCT116. CDOCKER studies support the EGFR inhibitory properties. Compounds 5p and 5i possessing thienylidene heterocycle are anti-SARS-CoV-2 with high therapeutic indices. Many of the synthesized agents show enhanced COX-1/2 properties than aspirin with better selectivity index towards COX-2 relative to COX-1. The possible applicability of the potent candidates discovered as antitumor and anti-SARS-CoV-2 is supported by the safe profile against normal (non-cancer, RPE1 and VERO-E6) cells.

A Novel Pathway Network Analytics Method Based on Graph Theory.

A biological pathway is an ordered set of interactions between intracellular molecules having collective activity that impacts cellular function, for example, by controlling metabolite synthesis or by regulating the expression of sets of genes. They play a key role in advanced studies of genomics. However, existing pathway analytics methods are inadequate to extract meaningful biological structure underneath the network of pathways. They also lack automation. Given these circumstances, we have come up with a novel graph theoretic method to analyze disease-related genes through weighted network of biological pathways. The method automatically extracts biological structures, such as clusters of pathways and their relevance, significance of each pathway and gene, and so forth hidden in the complex network. We have demonstrated the effectiveness of the proposed method on a set of genes associated with coronavirus disease 2019.

Precise Segmentation of COVID-19 Infected Lung from CT Images Based on Adaptive First-Order Appearance Model with Morphological/Anatomical Constraints.

A new segmentation technique is introduced for delineating the lung region in 3D computed tomography (CT) images. To accurately model the distribution of Hounsfield scale values within both chest and lung regions, a new probabilistic model is developed that depends on a linear combination of Gaussian (LCG). Moreover, we modified the conventional expectation-maximization (EM) algorithm to be run in a sequential way to estimate both the dominant Gaussian components (one for the lung region and one for the chest region) and the subdominant Gaussian components, which are used to refine the final estimated joint density. To estimate the marginal density from the mixed density, a modified k-means clustering approach is employed to classify the Gaussian subdominant components to determine which components belong properly to a lung and which components belong to a chest. The initial segmentation, based on the LCG-model, is then refined by the imposition of 3D morphological constraints based on a 3D Markov-Gibbs random field (MGRF) with analytically estimated potentials. The proposed approach was tested on CT data from 32 coronavirus disease 2019 (COVID-19) patients. Segmentation quality was quantitatively evaluated using four metrics: Dice similarity coefficient (DSC), overlap coefficient, 95th-percentile bidirectional Hausdorff distance (BHD), and absolute lung volume difference (ALVD), and it achieved 95.67±1.83%, 91.76±3.29%, 4.86±5.01, and 2.93±2.39, respectively. The reported results showed the capability of the proposed approach to accurately segment healthy lung tissues in addition to pathological lung tissues caused by COVID-19, outperforming four current, state-of-the-art deep learning-based lung segmentation approaches.

Comparison of the clinical outcomes of non-invasive ventilation by helmet vs facemask in patients with acute respiratory distress syndrome.

ABSTRACT: The main aim of this study is to compare the use of non-invasive ventilation (NIV) via helmet versus face mask where different interfaces and masks can apply NIV. However, some of the limitations of the NIV face mask were air leak, face mask intolerance, and requirement of high positive end expiratory pressure, which could be resolved with the use of the helmet NIV. NIV facemask will be applied as per the facial contour of the patient. NIV helmet is a transparent hood and size will be measured as per the head size. Both groups will have a standard protocol for titration of NIV.Patients aged more than 18 years old and diagnosed with acute respiratory distress syndrome as per Berlin definition will be enrolled in the study after signing the informed consent. Subjects who met the inclusion criteria will receive 1 of the 2 interventions; blood gases, oxygenation status [Po2/Fio2] will be monitored in both groups. The time of intubation will be the main comparison factor among the 2 groups. The primary and secondary outcomes will be measured by the number of patients requiring endotracheal intubation after application of helmet device, Improvement of oxygenation defined as PaO2/FiO2 ≥ 200 or increase from baseline by 100, duration of mechanical ventilation via an endotracheal tube, intensive care unit length of stay, death from any cause during hospitalization at the time of enrolment, need for proning during the hospital stay, intensive care unit mortality, and the degree to which overt adverse effects of a drug can be tolerated by a patient including feeding tolerance. TRIAL REGISTRATION NUMBER: NCT04507802. PROTOCOL VERSION: May 2020.

3-Alkenyl-2-oxindoles: Synthesis, antiproliferative and antiviral properties against SARS-CoV-2.

Sets of 3-alkenyl-2-oxindoles (6,10,13) were synthesized in a facile synthetic pathway through acid dehydration (EtOH/HCl) of the corresponding 3-hydroxy-2-oxoindolines (5,9,12). Single crystal (10a,c) and powder (12a,26f) X-ray studies supported the structures. Compounds 6c and 10b are the most effective agents synthesized (about 3.4, 3.3 folds, respectively) against PaCa2 (pancreatic) cancer cell line relative to the standard reference used (Sunitinib). Additionally, compound 10b reveals antiproliferative properties against MCF7 (breast) cancer cell with IC50 close to that of Sunitinib. CAM testing reveals that compounds 6 and 10 demonstrated qualitative and quantitative decreases in blood vessel count and diameter with efficacy comparable to that of Sunitinib, supporting their anti-angiogenic properties. Kinase inhibitory properties support their multi-targeted inhibitory activities against VEGFR-2 and c-kit in similar behavior to that of Sunitinib. Cell cycle analysis studies utilizing MCF7 exhibit that compound 6b arrests the cell cycle at G1/S phase while, 10b reveals accumulation of the tested cell at S phase. Compounds 6a and 10b reveal potent antiviral properties against SARS-CoV-2 with high selectivity index relative to the standards (hydroxychloroquine, chloroquine). Safe profile of the potent synthesized agents, against normal cells (VERO-E6, RPE1), support the possible development of better hits based on the attained observations.

Early assessment of lung function in coronavirus patients using invariant markers from chest X-rays images.

The primary goal of this manuscript is to develop a computer assisted diagnostic (CAD) system to assess pulmonary function and risk of mortality in patients with coronavirus disease 2019 (COVID-19). The CAD system processes chest X-ray data and provides accurate, objective imaging markers to assist in the determination of patients with a higher risk of death and thus are more likely to require mechanical ventilation and/or more intensive clinical care.To obtain an accurate stochastic model that has the ability to detect the severity of lung infection, we develop a second-order Markov-Gibbs random field (MGRF) invariant under rigid transformation (translation or rotation of the image) as well as scale (i.e., pixel size). The parameters of the MGRF model are learned automatically, given a training set of X-ray images with affected lung regions labeled. An X-ray input to the system undergoes pre-processing to correct for non-uniformity of illumination and to delimit the boundary of the lung, using either a fully-automated segmentation routine or manual delineation provided by the radiologist, prior to the diagnosis. The steps of the proposed methodology are: (i) estimate the Gibbs energy at several different radii to describe the inhomogeneity in lung infection; (ii) compute the cumulative distribution function (CDF) as a new representation to describe the local inhomogeneity in the infected region of lung; and (iii) input the CDFs to a new neural network-based fusion system to determine whether the severity of lung infection is low or high. This approach is tested on 200 clinical X-rays from 200 COVID-19 positive patients, 100 of whom died and 100 who recovered using multiple training/testing processes including leave-one-subject-out (LOSO), tenfold, fourfold, and twofold cross-validation tests. The Gibbs energy for lung pathology was estimated at three concentric rings of increasing radii. The accuracy and Dice similarity coefficient (DSC) of the system steadily improved as the radius increased. The overall CAD system combined the estimated Gibbs energy information from all radii and achieved a sensitivity, specificity, accuracy, and DSC of 100%, 97% ± 3%, 98% ± 2%, and 98% ± 2%, respectively, by twofold cross validation. Alternative classification algorithms, including support vector machine, random forest, naive Bayes classifier, K-nearest neighbors, and decision trees all produced inferior results compared to the proposed neural network used in this CAD system. The experiments demonstrate the feasibility of the proposed system as a novel tool to objectively assess disease severity and predict mortality in COVID-19 patients. The proposed tool can assist physicians to determine which patients might require more intensive clinical care, such a mechanical respiratory support.