Clinical Features Predicting COVID-19 Severity Risk at the Time of Hospitalization.

The global spread of COVID-19 has led to significant mortality and morbidity worldwide. Early identification of COVID-19 patients who are at high risk of developing severe disease can help in improved patient management, care, and treatment, as well as in the effective allocation of hospital resources. The severity prediction at the time of hospitalization can be extremely helpful in deciding the treatment of COVID-19 patients. To this end, this study presents an interpretable artificial intelligence (AI) model, named COVID-19 severity predictor (CoSP) that predicts COVID-19 severity using the clinical features at the time of hospital admission. We utilized a dataset comprising 64 demographic and laboratory features of 7,416 confirmed COVID-19 patients that were collected at the time of hospital admission. The proposed hierarchical CoSP model performs four-class COVID severity risk prediction into asymptomatic, mild, moderate, and severe categories. CoSP yielded better performance with good interpretability, as observed via Shapley analysis on COVID severity prediction compared to the other popular ML methods, with an area under the received operating characteristic curve (AUC-ROC) of 0.95, an area under the precision-recall curve (AUPRC) of 0.91, and a weighted F1-score of 0.83. Out of 64 initial features, 19 features were inferred as predictive of the severity of COVID-19 disease by the CoSP model. Therefore, an AI model predicting COVID-19 severity may be helpful for early intervention, optimizing resource allocation, and guiding personalized treatments, potentially enabling healthcare professionals to save lives and allocate resources effectively in the fight against the pandemic.

The multimodality cell segmentation challenge: toward universal solutions.

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimental settings. Here, we present a multimodality cell segmentation benchmark, comprising more than 1,500 labeled images derived from more than 50 diverse biological experiments. The top participants developed a Transformer-based deep-learning algorithm that not only exceeds existing methods but can also be applied to diverse microscopy images across imaging platforms and tissue types without manual parameter adjustments. This benchmark and the improved algorithm offer promising avenues for more accurate and versatile cell analysis in microscopy imaging.

Anti-GM-CSF otilimab versus tofacitinib or placebo in patients with active rheumatoid arthritis and an inadequate response to conventional or biologic DMARDs: two phase 3 randomised trials (contRAst 1 and contRAst 2).

OBJECTIVES: To investigate the efficacy and safety of otilimab, an antigranulocyte-macrophage colony-stimulating factor antibody, in patients with active rheumatoid arthritis. METHODS: Two phase 3, double-blind randomised controlled trials including patients with inadequate responses to methotrexate (contRAst 1) or conventional synthetic/biologic disease-modifying antirheumatic drugs (cs/bDMARDs; contRAst 2). Patients received background csDMARDs. Through a testing hierarchy, subcutaneous otilimab (90/150 mg once weekly) was compared with placebo for week 12 endpoints (after which, patients receiving placebo switched to active interventions) or oral tofacitinib (5 mg two times per day) for week 24 endpoints. PRIMARY ENDPOINT: proportion of patients achieving an American College of Rheumatology response ≥20% (ACR20) at week 12. RESULTS: The intention-to-treat populations comprised 1537 (contRAst 1) and 1625 (contRAst 2) patients. PRIMARY ENDPOINT: proportions of ACR20 responders were statistically significantly greater with otilimab 90 mg and 150 mg vs placebo in contRAst 1 (54.7% (p=0.0023) and 50.9% (p=0.0362) vs 41.7%) and contRAst 2 (54.9% (p<0.0001) and 54.5% (p<0.0001) vs 32.5%). Secondary endpoints: in both trials, compared with placebo, otilimab increased the proportion of Clinical Disease Activity Index (CDAI) low disease activity (LDA) responders (not significant for otilimab 150 mg in contRAst 1), and reduced Health Assessment Questionnaire-Disability Index (HAQ-DI) scores. Benefits with tofacitinib were consistently greater than with otilimab across multiple endpoints. Safety outcomes were similar across treatment groups. CONCLUSIONS: Although otilimab demonstrated superiority to placebo in ACR20, CDAI LDA and HAQ-DI, improved symptoms, and had an acceptable safety profile, it was inferior to tofacitinib. TRIAL REGISTRATION NUMBERS: NCT03980483, NCT03970837.

Anti-GM-CSF otilimab versus sarilumab or placebo in patients with rheumatoid arthritis and inadequate response to targeted therapies: a phase III randomised trial (contRAst 3).

OBJECTIVES: To investigate the efficacy and safety of otilimab, an anti-granulocyte-macrophage colony-stimulating factor antibody, in patients with active rheumatoid arthritis and an inadequate response to conventional synthetic (cs) and biologic disease-modifying antirheumatic drugs (DMARDs) and/or Janus kinase inhibitors. METHODS: ContRAst 3 was a 24-week, phase III, multicentre, randomised controlled trial. Patients received subcutaneous otilimab (90/150 mg once weekly), subcutaneous sarilumab (200 mg every 2 weeks) or placebo for 12 weeks, in addition to csDMARDs. Patients receiving placebo were switched to active interventions at week 12 and treatment continued to week 24. The primary end point was the proportion of patients achieving an American College of Rheumatology ≥20% response (ACR20) at week 12. RESULTS: Overall, 549 patients received treatment. At week 12, there was no significant difference in the proportion of ACR20 responders with otilimab 90 mg and 150 mg versus placebo (45% (p=0.2868) and 51% (p=0.0596) vs 38%, respectively). There were no significant differences in Clinical Disease Activity Index, Health Assessment Questionnaire-Disability Index, pain Visual Analogue Scale or Functional Assessment of Chronic Illness Therapy-Fatigue scores with otilimab versus placebo at week 12. Sarilumab demonstrated superiority to otilimab in ACR20 response and secondary end points. The incidence of adverse or serious adverse events was similar across treatment groups. CONCLUSIONS: Otilimab demonstrated an acceptable safety profile but failed to achieve the primary end point of ACR20 and improve secondary end points versus placebo or demonstrate non-inferiority to sarilumab in this patient population. TRIAL REGISTRATION NUMBER: NCT04134728.

Evaluation of the Role of Preoperative Oral Amisulpride as Part of a Multimodal Antiemetic Prophylaxis Regime on Postoperative Nausea and Vomiting in Patients Undergoing Craniotomy: A Prospective, Double-Blind, Randomized, Placebo-controlled Study.

BACKGROUND: Patients undergoing craniotomy are at high risk for postoperative nausea and vomiting (PONV) despite the use of prophylactic antiemetics. We hypothesized that a single preoperative oral dose of amisulpride as part of a multimodal antiemetic regimen would decrease the incidence of PONV in patients undergoing craniotomy for intracranial tumor surgery. METHODS: Adult patients scheduled for elective craniotomy requiring general anesthesia were enrolled and randomized to receive either oral amisulpride 25 mg or placebo 2 hours before surgery in addition to our institution's usual antiemetic regimen. The primary outcome of the study was the incidence of nausea and/or vomiting during the first 24 hours postoperatively. Secondary outcomes included severity of nausea, use of rescue antiemetic medications, and treatment-related adverse events. RESULTS: A total of 100 patients were included in the analysis. More patients in the amisulpride group had no episodes of nausea (90% vs. 40%; P<0.001) and no episodes of vomiting (94% vs. 46%; P<0.001) compared with the placebo group. The severity of nausea was lower in the amisulpride group than in the control group in the first 4 hours after surgery (P<0.05), and fewer patients receiving amisulpride required rescue antiemetics (P<0.001). The incidence of treatment-related adverse events was similar between groups. CONCLUSIONS: A single preoperative oral dose of amisulpride 25 mg as a component of a multimodal antiemetic regimen decreased the incidence and severity of PONV in patients undergoing craniotomy for intracranial tumor surgery, with no adverse effects.

BDL-SP: A Bio-inspired DL model for the identification of altered Signaling Pathways in Multiple Myeloma using WES data.

Identification of the genomic features responsible for the progression of Multiple Myeloma (MM) cancer from its precancerous stage MGUS can improve the understanding of the disease pathogenesis and, in devising suitable preventive and treatment measures. We have designed an innovative AI-based model, namely, the Bio-inspired Deep Learning architecture for the identification of altered Signaling Pathways (BDL-SP) to discover pivotal genomic biomarkers that can potentially distinguish MM from MGUS. The proposed BDL-SP model comprehends gene-gene interactions using the PPI network and analyzes genomic features using a deep learning (DL) architecture to identify significantly altered genes and signaling pathways in MM and MGUS. For this, whole exome sequencing data of 1174 MM and 61 MGUS patients were analyzed. In the quantitative benchmarking with the other popular machine learning models, BDL-SP performed almost similar to the two other best performing predictive ML models of Random Forest and CatBoost. However, an extensive post-hoc explainability analysis, capturing the application specific nuances, clearly established the significance of the BDL-SP model. This analysis revealed that BDL-SP identified a maximum number of previously reported oncogenes, tumor-suppressor genes, and actionable genes of high relevance in MM as the top significantly altered genes. Further, the post-hoc analysis revealed a significant contribution of the total number of single nucleotide variants (SNVs) and genomic features associated with synonymous SNVs in disease stage classification. Finally, the pathway enrichment analysis of the top significantly altered genes showed that many cancer pathways are selectively and significantly dysregulated in MM compared to its precursor stage of MGUS, while a few that lost their significance with disease progression from MGUS to MM were actually related to the other disease types. These observations may pave the way for appropriate therapeutic interventions to halt the progression to overt MM in the future.

Graded Depth of Response and Neoplastic Plasma Cell Index as Indicators of Survival Outcomes in Patients With Multiple Myeloma Following Autologous Stem Cell Transplant.

OBJECTIVES: With a substantial number of patients with multiple myeloma (MM) experiencing disease relapse, the quest for more sensitive methods to assess deeper responses indicative of cure continues. METHODS: In this prospective analysis of 170 patients with MM at day 100 after autologous stem cell transplant, we evaluated the predictive value of conventional response, measurable residual disease (MRDTOTAL: the aberrant percentage of plasma cells [PC%] among total bone marrow cells), and neoplastic plasma cell index scores (NPCI: the aberrant PC% of total PCs). RESULTS: Significantly better progression-free survival (PFS) and overall survival (OS) were observed with deepening conventional response. Conventional response-based stratification within the MRD-positive and MRD-negative subgroups showed a significantly higher PFS (hazard ratio [HR], 3.11; P < .005) and OS (HR, 3.08; P = .01) in the conventional response-positive/MRD-positive group compared with the conventional response-negative/MRD-positive group. Using K-adaptive partitioning to find the optimum threshold for MRD, patients achieving less than 0.001% MRDTOTAL had superior PFS (MRDTOTAL 0.001% to <0.1%: HR, 6.66, P < .005; MRDTOTAL ≥0.1%: HR, 11.52, P < .005) and OS (MRDTOTAL 0.001% to <0.1%: HR, 5.3, P < .05; MRDTOTAL ≥0.1%: HR = 9.21, P < .005). The C index and Akaike information criterion metrics demonstrated the superior performance of the NPCI compared with MRDTOTAL in predicting treatment outcome. CONCLUSIONS: Progressive deepening of response, conventional as well as MRD, correlates with superior survival outcomes. The NPCI proved to be a superior determinant of survival and can be explored as a better statistic than MRD.

SegPC-2021: A challenge & dataset on segmentation of Multiple Myeloma plasma cells from microscopic images.

Multiple Myeloma (MM) is an emerging ailment of global concern. Its diagnosis at the early stages is critical for recovery. Therefore, efforts are underway to produce digital pathology tools with human-level intelligence that are efficient, scalable, accessible, and cost-effective. Following the trend, a medical imaging challenge on "Segmentation of Multiple Myeloma Plasma Cells in Microscopic Images (SegPC-2021)" was organized at the IEEE International Symposium on Biomedical Imaging (ISBI), 2021, France. The challenge addressed the problem of cell segmentation in microscopic images captured from the slides prepared from the bone marrow aspirate of patients diagnosed with Multiple Myeloma. The challenge released a total of 775 images with 690 and 85 images of sizes 2040×1536 and 1920×2560 pixels, respectively, captured from two different (microscope and camera) setups. The participants had to segment the plasma cells with a separate label on each cell's nucleus and cytoplasm. This problem comprises many challenges, including a reduced color contrast between the cytoplasm and the background, and the clustering of cells with a feeble boundary separation of individual cells. To our knowledge, the SegPC-2021 challenge dataset is the largest publicly available annotated data on plasma cell segmentation in MM so far. The challenge targets a semi-automated tool to ensure the supervision of medical experts. It was conducted for a span of five months, from November 2020 to April 2021. Initially, the data was shared with 696 people from 52 teams, of which 41 teams submitted the results of their models on the evaluation portal in the validation phase. Similarly, 20 teams qualified for the last round, of which 16 teams submitted the results in the final test phase. All the top-5 teams employed DL-based approaches, and the best mIoU obtained on the final test set of 277 microscopic images was 0.9389. All these five models have been analyzed and discussed in detail. This challenge task is a step towards the target of creating an automated MM diagnostic tool.

A randomised trial of anti-GM-CSF otilimab in severe COVID-19 pneumonia (OSCAR).

BACKGROUND: Granulocyte-macrophage colony-stimulating factor (GM-CSF) and dysregulated myeloid cell responses are implicated in the pathophysiology and severity of COVID-19. METHODS: In this randomised, sequential, multicentre, placebo-controlled, double-blind study, adults aged 18-79 years (Part 1) or ≥70 years (Part 2) with severe COVID-19, respiratory failure and systemic inflammation (elevated C-reactive protein/ferritin) received a single intravenous infusion of otilimab 90 mg (human anti-GM-CSF monoclonal antibody) plus standard care (NCT04376684). The primary outcome was the proportion of patients alive and free of respiratory failure at Day 28. RESULTS: In Part 1 (n=806 randomised 1:1 otilimab:placebo), 71% of otilimab-treated patients were alive and free of respiratory failure at Day 28 versus 67% who received placebo; the model-adjusted difference of 5.3% was not statistically significant (95% CI -0.8-11.4%, p=0.09). A nominally significant model-adjusted difference of 19.1% (95% CI 5.2-33.1%, p=0.009) was observed in the predefined 70-79 years subgroup, but this was not confirmed in Part 2 (n=350 randomised) where the model-adjusted difference was 0.9% (95% CI -9.3-11.2%, p=0.86). Compared with placebo, otilimab resulted in lower serum concentrations of key inflammatory markers, including the putative pharmacodynamic biomarker CC chemokine ligand 17, indicative of GM-CSF pathway blockade. Adverse events were comparable between groups and consistent with severe COVID-19. CONCLUSIONS: There was no significant difference in the proportion of patients alive and free of respiratory failure at Day 28. However, despite the lack of clinical benefit, a reduction in inflammatory markers was observed with otilimab, in addition to an acceptable safety profile.

CSR-PERT: Joint framework for MRI and HARDI data reconstruction using perturbed radial trajectory estimated from compressively sensed measurements.

Radial sampling pattern is an important signal acquisition strategy in magnetic resonance imaging (MRI) owing to better immunity to motion-induced artifacts and less pronounced aliasing due to undersampling compared to the Cartesian sampling. These advantages of radial sampling can be exploited in acquisition of multidimensional signals such as High Angular Resolution Diffusion Imaging (HARDI), with tremendous scope of acceleration. Despite such benefits, gradient delays lead to samples being acquired from unknown miscentered radial trajectories, severely degrading the image reconstruction quality. In the present work, we propose Csr-Pert that is a joint framework, wherein these perturbed radial trajectories are estimated and utilized for image reconstruction from the compressively sensed measurements of (i) MRI data and (ii) HARDI data. The proposed Csr-Pert method is tested on one real MRI dataset with trajectory deviations and is observed to perform better than the existing state-of-the-art method at high acceleration factors up to 8. To the best of our knowledge, this is the first work to address the problem of estimating perturbed trajectories using the compressively sensed MRI and HARDI data. The method is also tested for varying combinations of trajectory deviations and sampling proportions. It is observed to yield very good quality HARDI reconstruction for a wide variety of scenarios. We have also demonstrated the robustness of the proposed method on real datasets in clinical settings assuming perturbed as well as noisy trajectories.

A Unified Computational Framework for a Robust, Reliable, and Reproducible Identification of Novel miRNAs From the RNA Sequencing Data.

In eukaryotic cells, miRNAs regulate a plethora of cellular functionalities ranging from cellular metabolisms, and development to the regulation of biological networks and pathways, both under homeostatic and pathological states like cancer.Despite their immense importance as key regulators of cellular processes, accurate and reliable estimation of miRNAs using Next Generation Sequencing is challenging, largely due to the limited availability of robust computational tools/methods/pipelines. Here, we introduce miRPipe, an end-to-end computational framework for the identification, characterization, and expression estimation of small RNAs, including the known and novel miRNAs and previously annotated pi-RNAs from small-RNA sequencing profiles. Our workflow detects unique novel miRNAs by incorporating the sequence information of seed and non-seed regions, concomitant with clustering analysis. This approach allows reliable and reproducible detection of unique novel miRNAs and functionally same miRNAs (paralogues). We validated the performance of miRPipe with the available state-of-the-art pipelines using both synthetic datasets generated using the newly developed miRSim tool and three cancer datasets (Chronic Lymphocytic Leukemia, Lung cancer, and breast cancer). In the experiment over the synthetic dataset, miRPipe is observed to outperform the existing state-of-the-art pipelines (accuracy: 95.23% and F 1-score: 94.17%). Analysis on all the three cancer datasets shows that miRPipe is able to extract more number of known dysregulated miRNAs or piRNAs from the datasets as compared to the existing pipelines.

GCRS: A hybrid graph convolutional network for risk stratification in multiple myeloma cancer patients.

In this study, we present an efficient Graph Convolutional Network based Risk Stratification system (GCRS) for cancer risk-stage prediction of newly diagnosed multiple myeloma (NDMM) patients. GCRS is a hybrid graph convolutional network consisting of a fusion of multiple connectivity graphs that are used to learn the latent representation of topological structures among patients. This proposed risk stratification system integrates these connectivity graphs prepared from the clinical and laboratory characteristics of NDMM cancer patients for partitioning them into three cancer risk groups: low, intermediate, and high. Extensive experiments demonstrate that GCRS outperforms the existing state-of-the-art methods in terms of C-index and hazard ratio on two publicly available datasets of NDMM patients. We have statistically validated our results using the Cox Proportional-Hazards model, Kaplan-Meier analysis, and log-rank test on progression-free survival (PFS) and overall survival (OS). We have also evaluated the contribution of various clinical parameters as utilized by the GCRS risk stratification system using the SHapley Additive exPlanations (SHAP) analysis, an interpretability algorithm for validating AI methods. Our study reveals the utility of the deep learning approach in building a robust system for cancer risk stage prediction.

Correlation of changes in subclonal architecture with progression in the MMRF CoMMpass study.

Multiple myeloma (MM) is a heterogeneous plasma cell proliferative disorder that arises from its premalignant precursor stages through a complex cascade of interactions between clonal mutations and co-evolving microenvironment. The temporo-spatial evolutionary trajectories of MM are established early during myelomatogenesis in precursor stages and retained in MM. Such molecular events impact subsequent disease progression and clinical outcomes. Identification of clonal sweeps of actionable gene targets in MM could reveal potential vulnerabilities that may exist in early stages and thus potentiate prognostication and customization of early therapeutic interventions. We have evaluated clonal evolution at multiple time points in 76 MM patients enrolled in the MMRF CoMMpass study. The major findings of this study are (a) MM progresses predominantly through branching evolution, (b) there is a heterogeneous spectrum of mutational landscapes that include unique actionable gene targets at diagnosis compared to progression, (c) unique clonal gains/ losses of mutant driver genes can be identified in patients with different cytogenetic aberrations, (d) there is a significant correlation between co-occurring oncogenic mutations/ co-occurring subclones e.g., with mutated TP53+SYNE1, NRAS+MAGI3, and anticorrelative dependencies between FAT3+FCGBP gene pairs. Such co-trajectories may synchronize molecular events of drug response, myelomatogenesis and warrant future studies to explore their potential for early prognostication and development of risk stratified personalized therapies in MM.

Machine learning based model for risk prediction after ST-Elevation myocardial infarction: Insights from the North India ST elevation myocardial infarction (NORIN-STEMI) registry.

BACKGROUND: Risk prediction following ST-Elevation Myocardial Infarction (STEMI) in resource limited countries is critical to identify patients at an increased risk of mortality who might benefit from intensive management. METHODS: North India ST-Elevation Myocardial Infarction (NORIN-STEMI) is an ongoing registry that has prospectively enrolled 3,635 STEMI patients. Of these, 3191 patients with first STEMI were included. Patients were divided into two groups: development (n=2668) and validation (unseen) dataset (n=523). Various ML strategies were used to train and tune the model based on validation dataset results that included 31 clinical characteristics. These models were compared in sensitivity, specificity, F1-score, receiver operating characteristic area under the curve (AUC), and overall accuracy to predict mortality at 30 days. ML model decision making was analyzed using the Shapley Additive exPlanations (ShAP) summary plot. RESULTS: At 30 days, the mortality was 7.7%. On the validation dataset, Extra Tree ML model had the best predictive ability with sensitivity: 85%, AUC: 79.7%, and Accuracy: 75%. ShAP interpretable summary plot determined delay in time to revascularization, baseline cardiogenic shock, left ventricular ejection fraction <30%, age, serum creatinine, heart failure on presentation, female sex, and moderate-severe mitral regurgitation to be major predictors of all-cause mortality at 30 days (P<0.001 for all). CONCLUSION: ML models lead to an improved mortality prediction following STEMI. ShAP summary plot for the interpretability of the AI model helps to understand the model's decision in identifying high-risk individuals who may benefit from intensified follow-up and close monitoring.

Characterizing the mutational landscape of MM and its precursor MGUS.

Mutational Signatures and Tumor mutational burden (TMB) have emerged as prognostic biomarkers in cancer genomics. However, the association of TMB with overall survival (OS) is still unknown in newly diagnosed multiple myeloma (NDMM) patients. Further, the change in the mutational spectrum involving both synonymous and non-synonymous mutations as MGUS progresses to MM is unexplored. This study addresses both these aspects via extensive evaluation of the mutations in MGUS and NDMM. WES data of 1018 NDMM patients and 61 MGUS patients collected from three different global regions were analyzed in this study. Single base substitutions, mutational signatures and TMB were inferred from the variants identified in MGUS and MM patients. The cutoff value for TMB was estimated to divide patients into low TMB and high TMB (hypermutators) groups. This study finds a change in the mutational spectrum with a statistically significant increase from MGUS to MM. There was a statistically significant increase in the frequency of all the three categories of variants, non-synonymous (NS), synonymous (SYN), and others (OTH), from MGUS to MM (P<0.05). However, there was a statistically significant rise in the TMB values for TMB_NS and TMB_SYN only. We also observed that 3' and 5'UTR mutations were more frequent in MM and might be responsible for driving MGUS to MM via regulatory binding sites. NDMM patients were also examined separately along with their survival outcomes. The frequency of hypermutators was low in MM with poor OS and PFS outcome. We observed a statistically significant rise in the frequency of C>A and C>T substitutions and a statistically significant decline in T>G substitutions in the MM patients with poor outcomes. Additionally, there was a statistically significant increase in the TMB of the patients with poor outcome compared to patients with a superior outcome. A statistically significant association between the APOBEC activity and poor overall survival in MM was discovered. These findings have potential clinical relevance and can assist in designing risk-adapted therapies to inhibit the progression of MGUS to MM and prolong the overall survival in high-risk MM patients.

ECG-iCOVIDNet: Interpretable AI model to identify changes in the ECG signals of post-COVID subjects.

OBJECTIVE: Studies showed that many COVID-19 survivors develop sub-clinical to clinical heart damage, even if subjects did not have underlying heart disease before COVID. Since Electrocardiogram (ECG) is a reliable technique for cardiovascular disease diagnosis, this study analyzes the 12-lead ECG recordings of healthy and post-COVID (COVID-recovered) subjects to ascertain ECG changes after suffering from COVID-19. METHOD: We propose a shallow 1-D convolutional neural network (CNN) deep learning architecture, namely ECG-iCOVIDNet, to distinguish ECG data of post-COVID subjects and healthy subjects. Further, we employed ShAP technique to interpret ECG segments that are highlighted by the CNN model for the classification of ECG recordings into healthy and post-COVID subjects. RESULTS: ECG data of 427 healthy and 105 post-COVID subjects were analyzed. Results show that the proposed ECG-iCOVIDNet model could classify the ECG recordings of healthy and post-COVID subjects better than the state-of-the-art deep learning models. The proposed model yields an F1-score of 100%. CONCLUSION: So far, we have not come across any other study with an in-depth ECG signal analysis of the COVID-recovered subjects. In this study, it is shown that the shallow ECG-iCOVIDNet CNN model performed good for distinguishing ECG signals of COVID-recovered subjects from those of healthy subjects. In line with the literature, this study confirms changes in the ECG signals of COVID-recovered patients that could be captured by the proposed CNN model. Successful deployment of such systems can help the doctors identify the changes in the ECG of the post-COVID subjects on time that can save many lives.

C-NMC: B-lineage acute lymphoblastic leukaemia: A blood cancer dataset.

Development of computer-aided cancer diagnostic tools is an active research area owing to the advancements in deep-learning domain. Such technological solutions provide affordable and easily deployable diagnostic tools. Leukaemia, or blood cancer, is one of the leading cancers causing more than 0.3 million deaths every year. In order to aid the development of such an AI-enabled tool, we collected and curated a microscopic image dataset, namely C-NMC, of more than 15000 cancer cell images at a very high resolution of B-Lineage Acute Lymphoblastic Leukaemia (B-ALL). The dataset is prepared at the subject-level and contains images of both healthy and cancer patients. So far, this is the largest (as well as curated) dataset on B-ALL cancer in the public domain. C-NMC is available at The Cancer Imaging Archive (TCIA), USA and can be helpful for the research community worldwide for the development of B-ALL cancer diagnostic tools. This dataset was utilized in an international medical imaging challenge held at ISBI 2019 conference in Venice, Italy. In this paper, we present a detailed description and challenges of this dataset. We also present benchmarking results of all the methods applied so far on this dataset.

A comparative study for predictive monitoring of COVID-19 pandemic.

COVID-19 pandemic caused by novel coronavirus (SARS-CoV-2) crippled the world economy and engendered irreparable damages to the lives and health of millions. To control the spread of the disease, it is important to make appropriate policy decisions at the right time. This can be facilitated by a robust mathematical model that can forecast the prevalence and incidence of COVID-19 with greater accuracy. This study presents an optimized ARIMA model to forecast COVID-19 cases. The proposed method first obtains a trend of the COVID-19 data using a low-pass Gaussian filter and then predicts/forecasts data using the ARIMA model. We benchmarked the optimized ARIMA model for 7-days and 14-days forecasting against five forecasting strategies used recently on the COVID-19 data. These include the auto-regressive integrated moving average (ARIMA) model, susceptible-infected-removed (SIR) model, composite Gaussian growth model, composite Logistic growth model, and dictionary learning-based model. We have considered the daily infected cases, cumulative death cases, and cumulative recovered cases of the COVID-19 data of the ten most affected countries in the world, including India, USA, UK, Russia, Brazil, Germany, France, Italy, Turkey, and Colombia. The proposed algorithm outperforms the existing models on the data of most of the countries considered in this study.