Author Correction: CCR5AS lncRNA variation differentially regulates CCR5, influencing HIV disease outcome.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

CCR5AS lncRNA variation differentially regulates CCR5, influencing HIV disease outcome.

Multiple genome-wide studies have identified associations between outcome of human immunodeficiency virus (HIV) infection and polymorphisms in and around the gene encoding the HIV co-receptor CCR5, but the functional basis for the strongest of these associations, rs1015164A/G, is unknown. We found that rs1015164 marks variation in an activating transcription factor 1 binding site that controls expression of the antisense long noncoding RNA (lncRNA) CCR5AS. Knockdown or enhancement of CCR5AS expression resulted in a corresponding change in CCR5 expression on CD4+ T cells. CCR5AS interfered with interactions between the RNA-binding protein Raly and the CCR5 3' untranslated region, protecting CCR5 messenger RNA from Raly-mediated degradation. Reduction in CCR5 expression through inhibition of CCR5AS diminished infection of CD4+ T cells with CCR5-tropic HIV in vitro. These data represent a rare determination of the functional importance of a genome-wide disease association where expression of a lncRNA affects HIV infection and disease progression.

Localization of infection in neonatal rhesus macaques after oral viral challenge.

Vertical transmission of human immunodeficiency virus (HIV) can occur in utero, during delivery, and through breastfeeding. We utilized Positron Emission Tomography (PET) imaging coupled with fluorescent microscopy of 64Cu-labeled photoactivatable-GFP-HIV (PA-GFP-BaL) to determine how HIV virions distribute and localize in neonatal rhesus macaques two and four hours after oral viral challenge. Our results show that by four hours after oral viral exposure, HIV virions localize to and penetrate the rectal mucosa. We also used a dual viral challenge with a non-replicative viral vector and a replication competent SHIV-1157ipd3N4 to examine viral transduction and dissemination at 96 hours. Our data show that while SHIV-1157ipd3N4 infection can be found in the oral cavity and upper gastrointestinal (GI) tract, the small and large intestine contained the largest number of infected cells. Moreover, we found that T cells were the biggest population of infected immune cells. Thus, thanks to these novel technologies, we are able to visualize and delineate of viral distribution and infection throughout the entire neonatal GI tract during acute viral infection.

A deep learning approach for automated diagnosis of pulmonary embolism on computed tomographic pulmonary angiography.

BACKGROUND: Computed tomographic pulmonary angiography (CTPA) is the diagnostic standard for confirming pulmonary embolism (PE). Since PE is a life-threatening condition, early diagnosis and treatment are critical to avoid PE-associated morbidity and mortality. However, PE remains subject to misdiagnosis. METHODS: We retrospectively identified 251 CTPAs performed at a tertiary care hospital between January 2018 to January 2021. The scans were classified as positive (n = 55) and negative (n = 196) for PE based on the annotations made by board-certified radiologists. A fully anonymized CT slice served as input for the detection of PE by the 2D segmentation model comprising U-Net architecture with Xception encoder. The diagnostic performance of the model was calculated at both the scan and the slice levels. RESULTS: The model correctly identified 44 out of 55 scans as positive for PE and 146 out of 196 scans as negative for PE with a sensitivity of 0.80 [95% CI 0.68, 0.89], a specificity of 0.74 [95% CI 0.68, 0.80], and an accuracy of 0.76 [95% CI 0.70, 0.81]. On slice level, 4817 out of 5183 slices were marked as positive for the presence of emboli with a specificity of 0.89 [95% CI 0.88, 0.89], a sensitivity of 0.93 [95% CI 0.92, 0.94], and an accuracy of 0.89 [95% CI 0.887, 0.890]. The model also achieved an AUROC of 0.85 [0.78, 0.90] and 0.94 [0.936, 0.941] at scan level and slice level, respectively for the detection of PE. CONCLUSION: The development of an AI model and its use for the identification of pulmonary embolism will support healthcare workers by reducing the rate of missed findings and minimizing the time required to screen the scans.

Posttranscriptional Regulation of HLA-A Protein Expression by Alternative Polyadenylation Signals Involving the RNA-Binding Protein Syncrip.

Genomic variation in the untranslated region (UTR) has been shown to influence HLA class I expression level and associate with disease outcomes. Sequencing of the 3'UTR of common HLA-A alleles indicated the presence of two polyadenylation signals (PAS). The proximal PAS is conserved, whereas the distal PAS is disrupted within certain alleles by sequence variants. Using 3'RACE, we confirmed expression of two distinct forms of the HLA-A 3'UTR based on use of either the proximal or the distal PAS, which differ in length by 100 bp. Specific HLA-A alleles varied in the usage of the proximal versus distal PAS, with some alleles using only the proximal PAS, and others using both the proximal and distal PAS to differing degrees. We show that the short and the long 3'UTR produced similar mRNA expression levels. However, the long 3'UTR conferred lower luciferase activity as compared with the short form, indicating translation inhibition of the long 3'UTR. RNA affinity pull-down followed by mass spectrometry analysis as well as RNA coimmunoprecipitation indicated differential binding of Syncrip to the long versus short 3'UTR. Depletion of Syncrip by small interfering RNA increased surface expression of an HLA-A allotype that uses primarily the long 3'UTR, whereas an allotype expressing only the short form was unaffected. Furthermore, specific blocking of the proximal 3'UTR reduced surface expression without decreasing mRNA expression. These data demonstrate HLA-A allele-specific variation in PAS usage, which modulates their cell surface expression posttranscriptionally.

DNA Prime-Boost Vaccine Regimen To Increase Breadth, Magnitude, and Cytotoxicity of the Cellular Immune Responses to Subdominant Gag Epitopes of Simian Immunodeficiency Virus and HIV.

HIV sequence diversity and the propensity of eliciting immunodominant responses targeting variable regions of the HIV proteome are hurdles in the development of an effective AIDS vaccine. An HIV-derived conserved element (CE) p24gag plasmid DNA (pDNA) vaccine is able to redirect immunodominant responses to otherwise subdominant and often more vulnerable viral targets. By homology to the HIV immunogen, seven CE were identified in SIV p27Gag Analysis of 31 rhesus macaques vaccinated with full-length SIV gag pDNA showed inefficient induction (58% response rate) of cellular responses targeting these CE. In contrast, all 14 macaques immunized with SIV p27CE pDNA developed robust T cell responses recognizing CE. Vaccination with p27CE pDNA was also critical for the efficient induction and increased the frequency of Ag-specific T cells with cytotoxic potential (granzyme B+ CD107a+) targeting subdominant CE epitopes, compared with the responses elicited by the p57gag pDNA vaccine. Following p27CE pDNA priming, two booster regimens, gag pDNA or codelivery of p27CE+gag pDNA, significantly increased the levels of CE-specific T cells. However, the CE+gag pDNA booster vaccination elicited significantly broader CE epitope recognition, and thus, a more profound alteration of the immunodominance hierarchy. Vaccination with HIV molecules showed that CE+gag pDNA booster regimen further expanded the breadth of HIV CE responses. Hence, SIV/HIV vaccine regimens comprising CE pDNA prime and CE+gag pDNA booster vaccination significantly increased cytotoxic T cell responses to subdominant highly conserved Gag epitopes and maximized response breadth.

DNA and virus particle vaccination protects against acquisition and confers control of viremia upon heterologous simian immunodeficiency virus challenge.

We have previously shown that macaques vaccinated with DNA vectors expressing SIVmac239 antigens developed potent immune responses able to reduce viremia upon high-dose SIVmac251 challenge. To further improve vaccine-induced immunity and protection, we combined the SIVmac239 DNA vaccine with protein immunization using inactivated SIVmac239 viral particles as protein source. Twenty-six weeks after the last vaccination, the animals were challenged intrarectally at weekly intervals with a titrated dose of the heterologous SIVsmE660. Two of DNA-protein coimmunized macaques did not become infected after 14 challenges, but all controls were infected by 11 challenges. Vaccinated macaques showed modest protection from SIVsmE660 acquisition compared with naïve controls (P = 0.050; stratified for TRIM5α genotype). Vaccinees had significantly lower peak (1.6 log, P = 0.0048) and chronic phase viremia (P = 0.044), with 73% of the vaccinees suppressing viral replication to levels below assay detection during the 40-wk follow-up. Vaccine-induced immune responses associated significantly with virus control: binding antibody titers and the presence of rectal IgG to SIVsmE660 Env correlated with delayed SIVsmE660 acquisition; SIV-specific cytotoxic T cells, prechallenge CD4(+) effector memory, and postchallenge CD8(+) transitional memory cells correlated with control of viremia. Thus, SIVmac239 DNA and protein-based vaccine protocols were able to achieve high, persistent, broad, and effective cellular and humoral immune responses able to delay heterologous SIVsmE660 infection and to provide long-term control of viremia. These studies support a role of DNA and protein-based vaccines for development of an efficacious HIV/AIDS vaccine.

A human immune data-informed vaccine concept elicits strong and broad T-cell specificities associated with HIV-1 control in mice and macaques.

BACKGROUND: None of the HIV T-cell vaccine candidates that have reached advanced clinical testing have been able to induce protective T cell immunity. A major reason for these failures may have been suboptimal T cell immunogen designs. METHODS: To overcome this problem, we used a novel immunogen design approach that is based on functional T cell response data from more than 1,000 HIV-1 clade B and C infected individuals and which aims to direct the T cell response to the most vulnerable sites of HIV-1. RESULTS: Our approach identified 16 regions in Gag, Pol, Vif and Nef that were relatively conserved and predominantly targeted by individuals with reduced viral loads. These regions formed the basis of the HIVACAT T-cell Immunogen (HTI) sequence which is 529 amino acids in length, includes more than 50 optimally defined CD4(+) and CD8(+) T-cell epitopes restricted by a wide range of HLA class I and II molecules and covers viral sites where mutations led to a dramatic reduction in viral replicative fitness. In both, C57BL/6 mice and Indian rhesus macaques immunized with an HTI-expressing DNA plasmid (DNA.HTI) induced broad and balanced T-cell responses to several segments within Gag, Pol, and Vif. DNA.HTI induced robust CD4(+) and CD8(+) T cell responses that were increased by a booster vaccination using modified virus Ankara (MVA.HTI), expanding the DNA.HTI induced response to up to 3.2% IFN-γ T-cells in macaques. HTI-specific T cells showed a central and effector memory phenotype with a significant fraction of the IFN-γ(+) CD8(+) T cells being Granzyme B(+) and able to degranulate (CD107a(+)). CONCLUSIONS: These data demonstrate the immunogenicity of a novel HIV-1 T cell vaccine concept that induced broadly balanced responses to vulnerable sites of HIV-1 while avoiding the induction of responses to potential decoy targets that may divert effective T-cell responses towards variable and less protective viral determinants.

The p40 subunit of interleukin (IL)-12 promotes stabilization and export of the p35 subunit: implications for improved IL-12 cytokine production.

IL-12 is a 70-kDa heterodimeric cytokine composed of the p35 and p40 subunits. To maximize cytokine production from plasmid DNA, molecular steps controlling IL-12p70 biosynthesis at the posttranscriptional and posttranslational levels were investigated. We show that the combination of RNA/codon-optimized gene sequences and fine-tuning of the relative expression levels of the two subunits within a cell resulted in increased production of the IL-12p70 heterodimer. We found that the p40 subunit plays a critical role in enhancing the stability, intracellular trafficking, and export of the p35 subunit. This posttranslational regulation mediated by the p40 subunit is conserved in mammals. Based on these findings, dual gene expression vectors were generated, producing an optimal ratio of the two subunits, resulting in a ~1 log increase in human, rhesus, and murine IL-12p70 production compared with vectors expressing the wild type sequences. Such optimized DNA plasmids also produced significantly higher levels of systemic bioactive IL-12 upon in vivo DNA delivery in mice compared with plasmids expressing the wild type sequences. A single therapeutic injection of an optimized murine IL-12 DNA plasmid showed significantly more potent control of tumor development in the B16 melanoma cancer model in mice. Therefore, the improved IL-12p70 DNA vectors have promising potential for in vivo use as molecular vaccine adjuvants and in cancer immunotherapy.

Comparative analysis of SIV-specific cellular immune responses induced by different vaccine platforms in rhesus macaques.

To identify the most promising vaccine candidates for combinatorial strategies, we compared five SIV vaccine platforms including recombinant canary pox virus ALVAC, replication-competent adenovirus type 5 host range mutant RepAd, DNA, modified vaccinia Ankara (MVA), peptides and protein in distinct combinations. Three regimens used viral vectors (prime or boost) and two regimens used plasmid DNA. Analysis at necropsy showed that the DNA-based vaccine regimens elicited significantly higher cellular responses against Gag and Env than any of the other vaccine platforms. The T cell responses induced by most vaccine regimens disseminated systemically into secondary lymphoid tissues (lymph nodes, spleen) and effector anatomical sites (including liver, vaginal tissue), indicative of their role in viral containment at the portal of entry. The cellular and reported humoral immune response data suggest that combination of DNA and viral vectors elicits a balanced immunity with strong and durable responses able to disseminate into relevant mucosal sites.

Humoral immunity induced by mucosal and/or systemic SIV-specific vaccine platforms suggests novel combinatorial approaches for enhancing responses.

Combinatorial HIV/SIV vaccine approaches targeting multiple arms of the immune system might improve protective efficacy. We compared SIV-specific humoral immunity induced in rhesus macaques by five vaccine regimens. Systemic regimens included ALVAC-SIVenv priming and Env boosting (ALVAC/Env); DNA immunization; and DNA plus Env co-immunization (DNA&Env). RepAd/Env combined mucosal replication-competent Ad-env priming with systemic Env boosting. A Peptide/Env regimen, given solely intrarectally, included HIV/SIV peptides followed by MVA-env and Env boosts. Serum antibodies mediating neutralizing, phagocytic and ADCC activities were induced by ALVAC/Env, RepAd/Env and DNA&Env vaccines. Memory B cells and plasma cells were maintained in the bone marrow. RepAd/Env vaccination induced early SIV-specific IgA in rectal secretions before Env boosting, although mucosal IgA and IgG responses were readily detected at necropsy in ALVAC/Env, RepAd/Env, DNA&Env and DNA vaccinated animals. Our results suggest that combined RepAd priming with ALVAC/Env or DNA&Env regimen boosting might induce potent, functional, long-lasting systemic and mucosal SIV-specific antibodies.

DNA vaccination by intradermal electroporation induces long-lasting immune responses in rhesus macaques.

BACKGROUND: A desirable HIV vaccine should induce protective long-lasting humoral and cellular immune responses. METHODS: Macaques were immunized by env DNA, selected from a panel of recently transmitted SIVmac251 Env using intradermal electroporation as vaccine delivery method and magnitude, breadth and longevity of humoral and cellular immune responses. RESULTS: The macaques developed high, long-lasting humoral immune responses with neutralizing capacity against homologous and heterologous Env. The avidity of the antibody responses was also preserved over 1-year follow-up. Analysis of cellular immune responses demonstrated induction of Env-specific memory T cells harboring granzyme B, albeit their overall levels were low. Similar to the humoral responses, the cellular immunity was persistent over the ~1-year follow-up. CONCLUSION: These data show that vaccination by this intradermal DNA delivery regimen is able to induce potent and durable immune responses in macaques.

Age associated susceptibility to SARS-CoV-2 infection in the K18-hACE2 transgenic mouse model.

Coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is still an ongoing global health crisis. Clinical data indicate that the case fatality rate (CFR) is age dependent, with a higher CFR percentage in the elderly population. We compared the pathogenesis of SARS-CoV-2 in young and aged K18-hACE2 transgenic mice. We evaluated morbidity, mortality, viral titers, immune responses, and histopathology in SARS-CoV-2-infected young and old K18-hACE2 transgenic mice. Within the limitation of having a low number of mice per group, our results indicate that SARS-CoV-2 infection resulted in slightly higher morbidity, mortality, and viral replication in the lungs of old mice, which was associated with an impaired IgM response and altered cytokine and chemokine profiles. Results of this study increase our understanding of SARS-CoV-2 infectivity and immuno-pathogenesis in the elderly population.

Aid or Antagonize: Nuclear Long Noncoding RNAs Regulate Host Responses and Outcomes of Viral Infections.

Long noncoding RNAs (lncRNAs) are transcripts measuring >200 bp in length and devoid of protein-coding potential. LncRNAs exceed the number of protein-coding mRNAs and regulate cellular, developmental, and immune pathways through diverse molecular mechanisms. In recent years, lncRNAs have emerged as epigenetic regulators with prominent roles in health and disease. Many lncRNAs, either host or virus-encoded, have been implicated in critical cellular defense processes, such as cytokine and antiviral gene expression, the regulation of cell signaling pathways, and the activation of transcription factors. In addition, cellular and viral lncRNAs regulate virus gene expression. Viral infections and associated immune responses alter the expression of host lncRNAs regulating immune responses, host metabolism, and viral replication. The influence of lncRNAs on the pathogenesis and outcomes of viral infections is being widely explored because virus-induced lncRNAs can serve as diagnostic and therapeutic targets. Future studies should focus on thoroughly characterizing lncRNA expressions in virus-infected primary cells, investigating their role in disease prognosis, and developing biologically relevant animal or organoid models to determine their suitability for specific therapeutic targeting. Many cellular and viral lncRNAs localize in the nucleus and epigenetically modulate viral transcription, latency, and host responses to infection. In this review, we provide an overview of the role of nuclear lncRNAs in the pathogenesis and outcomes of viral infections, such as the Influenza A virus, Sendai Virus, Respiratory Syncytial Virus, Hepatitis C virus, Human Immunodeficiency Virus, and Herpes Simplex Virus. We also address significant advances and barriers in characterizing lncRNA function and explore the potential of lncRNAs as therapeutic targets.

Validation of a Deep Learning Model for Detecting Chest Pathologies from Digital Chest Radiographs.

Purpose: Manual interpretation of chest radiographs is a challenging task and is prone to errors. An automated system capable of categorizing chest radiographs based on the pathologies identified could aid in the timely and efficient diagnosis of chest pathologies. Method: For this retrospective study, 4476 chest radiographs were collected between January and April 2021 from two tertiary care hospitals. Three expert radiologists established the ground truth, and all radiographs were analyzed using a deep-learning AI model to detect suspicious ROIs in the lungs, pleura, and cardiac regions. Three test readers (different from the radiologists who established the ground truth) independently reviewed all radiographs in two sessions (unaided and AI-aided mode) with a washout period of one month. Results: The model demonstrated an aggregate AUROC of 91.2% and a sensitivity of 88.4% in detecting suspicious ROIs in the lungs, pleura, and cardiac regions. These results outperform unaided human readers, who achieved an aggregate AUROC of 84.2% and sensitivity of 74.5% for the same task. When using AI, the aided readers obtained an aggregate AUROC of 87.9% and a sensitivity of 85.1%. The average time taken by the test readers to read a chest radiograph decreased by 21% (p < 0.01) when using AI. Conclusion: The model outperformed all three human readers and demonstrated high AUROC and sensitivity across two independent datasets. When compared to unaided interpretations, AI-aided interpretations were associated with significant improvements in reader performance and chest radiograph interpretation time.

Aerosolized sulfated hyaluronan derivatives prolong the survival of K18 ACE2 mice infected with a lethal dose of SARS-CoV-2.

Despite several vaccines that are currently approved for human use to control the pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), there is an urgent medical need for therapeutic and prophylactic options. SARS-CoV-2 binding and entry in human cells involves interactions of its spike (S) protein with several host cell surface factors, including heparan sulfate proteoglycans (HSPGs), transmembrane protease serine 2 (TMPRSS2), and angiotensin-converting enzyme 2 (ACE2). In this paper we investigated the potential of sulphated Hyaluronic Acid (sHA), a HSPG mimicking polymer, to inhibit the binding of SARS-CoV-2 S protein to human ACE2 receptor. After the assessment of different sulfation degree of sHA backbone, a series of sHA functionalized with different hydrophobic side chains were synthesized and screened. The compound showing the highest binding affinity to the viral S protein was further characterized by surface plasmon resonance (SPR) towards ACE2 and viral S protein binding domain. Selected compounds were formulated as solutions for nebulization and, after being characterized in terms of aerosolization performance and droplet size distribution, their efficacy was assessed in vivo using the K18 human (h)ACE2 transgenic mouse model of SARS-CoV-2 infection.

DNA vaccination in rhesus macaques induces potent immune responses and decreases acute and chronic viremia after SIVmac251 challenge.

Optimized plasmid DNAs encoding the majority of SIVmac239 proteins and delivered by electroporation (EP) elicited strong immune responses in rhesus macaques. Vaccination decreased viremia in both the acute and chronic phases of infection after challenge with pathogenic SIVmac251. Two groups of macaques were vaccinated with DNA plasmids producing different antigen forms, "native" and "modified," inducing distinct immune responses. Both groups showed significantly lower viremia during the acute phase of infection, whereas the group immunized with the native antigens showed better protection during the chronic phase (1.7 log decrease in virus load, P = 0.009). Both groups developed strong cellular and humoral responses against the DNA vaccine antigens, which included Gag, Pol, Env, Nef, and Tat. Vaccination induced both central memory and effector memory T cells that were maintained at the day of challenge, suggesting the potential for rapid mobilization upon virus challenge. The group receiving the native antigens developed higher and more durable anti-Env antibodies, including neutralizing antibodies at the day of challenge. These results demonstrate that DNA vaccination in the absence of any heterologous boost can provide protection from high viremia comparable to any other vaccine modalities tested in this macaque model.

Levels of Autonomous Radiology.

Radiology, being one of the younger disciplines of medicine with a history of just over a century, has witnessed tremendous technological advancements and has revolutionized the way we practice medicine today. In the last few decades, medical imaging modalities have generated seismic amounts of medical data. The development and adoption of artificial intelligence applications using this data will lead to the next phase of evolution in radiology. It will include automating laborious manual tasks such as annotations, report generation, etc, along with the initial radiological assessment of patients and imaging features to aid radiologists in their diagnostic and treatment planning workflow. We propose a level-wise classification for the progression of automation in radiology, explaining artificial intelligence assistance at each level with the corresponding challenges and solutions. We hope that such discussions can help us address challenges in a structured way and take the necessary steps to ensure the smooth adoption of new technologies in radiology.

Observer performance evaluation of the feasibility of a deep learning model to detect cardiomegaly on chest radiographs.

Background: Cardiothoracic ratio (CTR) is the ratio of the diameter of the heart to the diameter of the thorax. An abnormal CTR (>0.55) is often an indicator of an underlying pathological condition. The accurate prediction of an abnormal CTR chest X-rays (CXRs) aids in the early diagnosis of clinical conditions. Purpose: We propose a deep learning (DL)-based model for automatic CTR calculation to assist radiologists with rapid diagnosis of cardiomegaly and thus optimise the radiology flow. Material and Methods: The study population included 1012 posteroanterior CXRs from a single institution. The Attention U-Net DL architecture was used for the automatic calculation of CTR. An observer performance test was conducted to assess the radiologist's performance in diagnosing cardiomegaly with and without artificial intelligence assistance. Results: U-Net model exhibited a sensitivity of 0.80 [95% CI: 0.75, 0.85], specificity >99%, precision of 0.99 [95% CI: 0.98, 1], and a F1 score of 0.88 [95% CI: 0.85, 0.91]. Furthermore, the sensitivity of the reviewing radiologist in identifying cardiomegaly increased from 40.50% to 88.4% when aided by the AI-generated CTR. Conclusion: Our segmentation-based AI model demonstrated high specificity (>99%) and sensitivity (80%) for CTR calculation. The performance of the radiologist on the observer performance test improved significantly with provision of AI assistance. A DL-based segmentation model for rapid quantification of CTR can therefore have significant potential to be used in clinical workflows by reducing radiologists' burden and alerting to an abnormal enlarged heart early on.

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.

Background Coronavirus disease 2019 (COVID-19) has accounted for over 352 million cases and five million deaths globally. Although it affects populations across all nations, developing or transitional, of all genders and ages, the extent of the specific involvement is not very well known. This study aimed to analyze and determine how different were the first and second waves of the COVID-19 pandemic by assessing computed tomography severity scores (CT-SS). Methodology This was a retrospective, cross-sectional, observational study performed at a tertiary care Institution. We included 301 patients who underwent CT of the chest between June and October 2020 and 1,001 patients who underwent CT of the chest between February and April 2021. All included patients were symptomatic and were confirmed to be COVID-19 positive. We compared the CT-SS between the two datasets. In addition, we analyzed the distribution of CT-SS concerning age, comorbidities, and gender, as well as their differences between the two waves of COVID-19. Analysis was performed using the SPSS version 22 (IBM Corp., Armonk, NY, USA). The artificial intelligence platform U-net architecture with Xception encoder was used in the analysis. Results The study data revealed that while the mean CT-SS did not differ statistically between the two waves of COVID-19, the age group most affected in the second wave was almost a decade younger. While overall the disease had a predilection toward affecting males, our findings showed that females were more afflicted in the second wave of COVID-19 compared to the first wave. In particular, the disease had an increased severity in cases with comorbidities such as hypertension, diabetes mellitus, bronchial asthma, and tuberculosis. Conclusions This assessment demonstrated no significant difference in radiological severity score between the two waves of COVID-19. The secondary objective revealed that the two waves showed demographical differences. Hence, we iterate that no demographical subset of the population should be considered low risk as the disease manifestation was heterogeneous.