Towards Predicting Length of Stay and Identification of Cohort Risk Factors Using Self-Attention-Based Transformers and Association Mining: COVID-19 as a Phenotype.

Predicting length of stay (LoS) and understanding its underlying factors is essential to minimizing the risk of hospital-acquired conditions, improving financial, operational, and clinical outcomes, and better managing future pandemics. The purpose of this study was to forecast patients' LoS using a deep learning model and to analyze cohorts of risk factors reducing or prolonging LoS. We employed various preprocessing techniques, SMOTE-N to balance data, and a TabTransformer model to forecast LoS. Finally, the Apriori algorithm was applied to analyze cohorts of risk factors influencing hospital LoS. The TabTransformer outperformed the base machine learning models in terms of F1 score (0.92), precision (0.83), recall (0.93), and accuracy (0.73) for the discharged dataset and F1 score (0.84), precision (0.75), recall (0.98), and accuracy (0.77) for the deceased dataset. The association mining algorithm was able to identify significant risk factors/indicators belonging to laboratory, X-ray, and clinical data, such as elevated LDH and D-dimer levels, lymphocyte count, and comorbidities such as hypertension and diabetes. It also reveals what treatments have reduced the symptoms of COVID-19 patients, leading to a reduction in LoS, particularly when no vaccines or medication, such as Paxlovid, were available.

Prognosis Prediction in COVID-19 Patients through Deep Feature Space Reasoning.

The COVID-19 pandemic has presented a unique challenge for physicians worldwide, as they grapple with limited data and uncertainty in diagnosing and predicting disease outcomes. In such dire circumstances, the need for innovative methods that can aid in making informed decisions with limited data is more critical than ever before. To allow prediction with limited COVID-19 data as a case study, we present a complete framework for progression and prognosis prediction in chest X-rays (CXR) through reasoning in a COVID-specific deep feature space. The proposed approach relies on a pre-trained deep learning model that has been fine-tuned specifically for COVID-19 CXRs to identify infection-sensitive features from chest radiographs. Using a neuronal attention-based mechanism, the proposed method determines dominant neural activations that lead to a feature subspace where neurons are more sensitive to COVID-related abnormalities. This process allows the input CXRs to be projected into a high-dimensional feature space where age and clinical attributes like comorbidities are associated with each CXR. The proposed method can accurately retrieve relevant cases from electronic health records (EHRs) using visual similarity, age group, and comorbidity similarities. These cases are then analyzed to gather evidence for reasoning, including diagnosis and treatment. By using a two-stage reasoning process based on the Dempster-Shafer theory of evidence, the proposed method can accurately predict the severity, progression, and prognosis of a COVID-19 patient when sufficient evidence is available. Experimental results on two large datasets show that the proposed method achieves 88% precision, 79% recall, and 83.7% F-score on the test sets.

Efficient-ECGNet framework for COVID-19 classification and correlation prediction with the cardio disease through electrocardiogram medical imaging.

In the last 2 years, we have witnessed multiple waves of coronavirus that affected millions of people around the globe. The proper cure for COVID-19 has not been diagnosed as vaccinated people also got infected with this disease. Precise and timely detection of COVID-19 can save human lives and protect them from complicated treatment procedures. Researchers have employed several medical imaging modalities like CT-Scan and X-ray for COVID-19 detection, however, little concentration is invested in the ECG imaging analysis. ECGs are quickly available image modality in comparison to CT-Scan and X-ray, therefore, we use them for diagnosing COVID-19. Efficient and effective detection of COVID-19 from the ECG signal is a complex and time-taking task, as researchers usually convert them into numeric values before applying any method which ultimately increases the computational burden. In this work, we tried to overcome these challenges by directly employing the ECG images in a deep-learning (DL)-based approach. More specifically, we introduce an Efficient-ECGNet method that presents an improved version of the EfficientNetV2-B4 model with additional dense layers and is capable of accurately classifying the ECG images into healthy, COVID-19, myocardial infarction (MI), abnormal heartbeats (AHB), and patients with Previous History of Myocardial Infarction (PMI) classes. Moreover, we introduce a module to measure the similarity of COVID-19-affected ECG images with the rest of the diseases. To the best of our knowledge, this is the first effort to approximate the correlation of COVID-19 patients with those having any previous or current history of cardio or respiratory disease. Further, we generate the heatmaps to demonstrate the accurate key-points computation ability of our method. We have performed extensive experimentation on a publicly available dataset to show the robustness of the proposed approach and confirmed that the Efficient-ECGNet framework is reliable to classify the ECG-based COVID-19 samples.

COVID-19 Genome Sequence Analysis for New Variant Prediction and Generation

The new COVID-19 variants of concern are causing more infections and spreading much faster than their predecessors. Recent cases show that even vaccinated people are highly affected by these new variants. The proactive nucleotide sequence prediction of possible new variants of COVID-19 and developing better healthcare plans to address their spread require a unified framework for variant classification and early prediction. This paper attempts to answer the following research questions: can a convolutional neural network with self-attention by extracting discriminative features from nucleotide sequences be used to classify COVID-19 variants? Second, is it possible to employ uncertainty calculation in the predicted probability distribution to predict new variants? Finally, can synthetic approaches such as variational autoencoder-decoder networks be employed to generate a synthetic new variant from random noise? Experimental results show that the generated sequence is significantly similar to the original coronavirus and its variants, proving that our neural network can learn the mutation patterns from the old variants. Moreover, to our knowledge, we are the first to collect data for all COVID-19 variants for computational analysis. The proposed framework is extensively evaluated for classification, new variant prediction, and new variant generation tasks and achieves better performance for all tasks. Our code, data, and trained models are available on GitHub (https://github.com/Aminullah6264/COVID19, accessed on 16 September 2022).

Multi-Stage Temporal Convolution Network for COVID-19 Variant Classification.

The outbreak of the novel coronavirus disease COVID-19 (SARS-CoV-2) has developed into a global epidemic. Due to the pathogenic virus's high transmission rate, accurate identification and early prediction are required for subsequent therapy. Moreover, the virus's polymorphic nature allows it to evolve and adapt to various environments, making prediction difficult. However, other diseases, such as dengue, MERS-CoV, Ebola, SARS-CoV-1, and influenza, necessitate the employment of a predictor based on their genomic information. To alleviate the situation, we propose a deep learning-based mechanism for the classification of various SARS-CoV-2 virus variants, including the most recent, Omicron. Our model uses a neural network with a temporal convolution neural network to accurately identify different variants of COVID-19. The proposed model first encodes the sequences in the numerical descriptor, and then the convolution operation is applied for discriminative feature extraction from the encoded sequences. The sequential relations between the features are collected using a temporal convolution network to classify COVID-19 variants accurately. We collected recent data from the NCBI, on which the proposed method outperforms various baselines with a high margin.

Towards robust diagnosis of COVID-19 using vision self-attention transformer.

The outbreak of COVID-19, since its appearance, has affected about 200 countries and endangered millions of lives. COVID-19 is extremely contagious disease, and it can quickly incapacitate the healthcare systems if infected cases are not handled timely. Several Conventional Neural Networks (CNN) based techniques have been developed to diagnose the COVID-19. These techniques require a large, labelled dataset to train the algorithm fully, but there are not too many labelled datasets. To mitigate this problem and facilitate the diagnosis of COVID-19, we developed a self-attention transformer-based approach having self-attention mechanism using CT slices. The architecture of transformer can exploit the ample unlabelled datasets using pre-training. The paper aims to compare the performances of self-attention transformer-based approach with CNN and Ensemble classifiers for diagnosis of COVID-19 using binary Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection and multi-class Hybrid-learning for UnbiaSed predicTion of COVID-19 (HUST-19) CT scan dataset. To perform this comparison, we have tested Deep learning-based classifiers and ensemble classifiers with proposed approach using CT scan images. Proposed approach is more effective in detection of COVID-19 with an accuracy of 99.7% on multi-class HUST-19, whereas 98% on binary class SARS-CoV-2 dataset. Cross corpus evaluation achieves accuracy of 93% by training the model with Hust19 dataset and testing using Brazilian COVID dataset.

An Effective Strategy and Mathematical Model to Predict the Sustainable Evolution of the Impact of the Pandemic Lockdown.

There have been considerable losses in terms of human and economic resources due to the current coronavirus pandemic. This work, which contributes to the prevention and control of COVID-19, proposes a novel modified epidemiological model that predicts the epidemic's evolution over time in India. A mathematical model was proposed to analyze the spread of COVID-19 in India during the lockdowns implemented by the government of India during the first and second waves. What makes this study unique, however, is that it develops a conceptual model with time-dependent characteristics, which is peculiar to India's diverse and homogeneous societies. The results demonstrate that governmental control policies and suitable public perception of risk in terms of social distancing and public health safety measures are required to control the spread of COVID-19 in India. The results also show that India's two strict consecutive lockdowns (21 days and 19 days, respectively) successfully helped delay the spread of the disease, buying time to pump up healthcare capacities and management skills during the first wave of COVID-19 in India. In addition, the second wave's severe lockdown put a lot of pressure on the sustainability of many Indian cities. Therefore, the data show that timely implementation of government control laws combined with a high risk perception among the Indian population will help to ensure sustainability. The proposed model is an effective strategy for constructing healthy cities and sustainable societies in India, which will help prevent such a crisis in the future.

Toward Realigning Automatic Speaker Verification in the Era of COVID-19

The use of face masks has increased dramatically since the COVID-19 pandemic started in order to to curb the spread of the disease. Additionally, breakthrough infections caused by the Delta and Omicron variants have further increased the importance of wearing a face mask, even for vaccinated individuals. However, the use of face masks also induces attenuation in speech signals, and this change may impact speech processing technologies, e.g., automated speaker verification (ASV) and speech to text conversion. In this paper we examine Automatic Speaker Verification (ASV) systems against the speech samples in the presence of three different types of face mask: surgical, cloth, and filtered N95, and analyze the impact on acoustics and other factors. In addition, we explore the effect of different microphones, and distance from the microphone, and the impact of face masks when speakers use ASV systems in real-world scenarios. Our analysis shows a significant deterioration in performance when an ASV system encounters different face masks, microphones, and variable distance between the subject and microphone. To address this problem, this paper proposes a novel framework to overcome performance degradation in these scenarios by realigning the ASV system. The novelty of the proposed ASV framework is as follows: first, we propose a fused feature descriptor by concatenating the novel Ternary Deviated overlapping Patterns (TDoP), Mel Frequency Cepstral Coefficients (MFCC), and Gammatone Cepstral Coefficients (GTCC), which are used by both the ensemble learning-based ASV and anomaly detection system in the proposed ASV architecture. Second, this paper proposes an anomaly detection model for identifying vocal samples produced in the presence of face masks. Next, it presents a Peak Norm (PN) filter to approximate the signal of the speaker without a face mask in order to boost the accuracy of ASV systems. Finally, the features of filtered samples utilizing the PN filter and samples without face masks are passed to the proposed ASV to test for improved accuracy. The proposed ASV system achieved an accuracy of 0.99 and 0.92, respectively, on samples recorded without a face mask and with different face masks. Although the use of face masks affects the ASV system, the PN filtering solution overcomes this deficiency up to 4%. Similarly, when exposed to different microphones and distances, the PN approach enhanced system accuracy by up to 7% and 9%, respectively. The results demonstrate the effectiveness of the presented framework against an in-house prepared, diverse Multi Speaker Face Masks (MSFM) dataset, (IRB No. FY2021-83), consisting of samples of subjects taken with a variety of face masks and microphones, and from different distances.

COVID-DAI: A novel framework for COVID-19 detection and infection growth estimation using computed tomography images.

The COVID-19 pandemic is spreading at a fast pace around the world and has a high mortality rate. Since there is no proper treatment of COVID-19 and its multiple variants, for example, Alpha, Beta, Gamma, and Delta, being more infectious in nature are affecting millions of people, further complicates the detection process, so, victims are at the risk of death. However, timely and accurate diagnosis of this deadly virus can not only save the patients from life loss but can also prevent them from the complex treatment procedures. Accurate segmentation and classification of COVID-19 is a tedious job due to the extensive variations in its shape and similarity with other diseases like Pneumonia. Furthermore, the existing techniques have hardly focused on the infection growth estimation over time which can assist the doctors to better analyze the condition of COVID-19-affected patients. In this work, we tried to overcome the shortcomings of existing studies by proposing a model capable of segmenting, classifying the COVID-19 from computed tomography images, and predicting its behavior over a certain period. The framework comprises four main steps: (i) data preparation, (ii) segmentation, (iii) infection growth estimation, and (iv) classification. After performing the pre-processing step, we introduced the DenseNet-77 based UNET approach. Initially, the DenseNet-77 is used at the Encoder module of the UNET model to calculate the deep keypoints which are later segmented to show the coronavirus region. Then, the infection growth estimation of COVID-19 per patient is estimated using the blob analysis. Finally, we employed the DenseNet-77 framework as an end-to-end network to classify the input images into three classes namely healthy, COVID-19-affected, and pneumonia images. We evaluated the proposed model over the COVID-19-20 and COVIDx CT-2A datasets for segmentation and classification tasks, respectively. Furthermore, unlike existing techniques, we performed a cross-dataset evaluation to show the generalization ability of our method. The quantitative and qualitative evaluation confirms that our method is robust to both COVID-19 segmentation and classification and can accurately predict the infection growth in a certain time frame. RESEARCH HIGHLIGHTS: We present an improved UNET framework with a DenseNet-77-based encoder for deep keypoints extraction to enhance the identification and segmentation performance of the coronavirus while reducing the computational complexity as well. We propose a computationally robust approach for COVID-19 infection segmentation due to fewer model parameters. Robust segmentation of COVID-19 due to accurate feature computation power of DenseNet-77. A module is introduced to predict the infection growth of COVID-19 for a patient to analyze its severity over time. We present such a framework that can effectively classify the samples into several classes, that is, COVID-19, Pneumonia, and healthy samples. Rigorous experimentation was performed including the cross-dataset evaluation to prove the efficacy of the presented technique.

COVID-19 Related Sentiment Analysis Using State-of-the-Art Machine Learning and Deep Learning Techniques.

The coronavirus disease 2019 (COVID-19) pandemic has influenced the everyday life of people around the globe. In general and during lockdown phases, people worldwide use social media network to state their viewpoints and general feelings concerning the pandemic that has hampered their daily lives. Twitter is one of the most commonly used social media platforms, and it showed a massive increase in tweets related to coronavirus, including positive, negative, and neutral tweets, in a minimal period. The researchers move toward the sentiment analysis and analyze the various emotions of the public toward COVID-19 due to the diverse nature of tweets. Meanwhile, people have expressed their feelings regarding the vaccinations' safety and effectiveness on social networking sites such as Twitter. As an advanced step, in this paper, our proposed approach analyzes COVID-19 by focusing on Twitter users who share their opinions on this social media networking site. The proposed approach analyzes collected tweets' sentiments for sentiment classification using various feature sets and classifiers. The early detection of COVID-19 sentiments from collected tweets allow for a better understanding and handling of the pandemic. Tweets are categorized into positive, negative, and neutral sentiment classes. We evaluate the performance of machine learning (ML) and deep learning (DL) classifiers using evaluation metrics (i.e., accuracy, precision, recall, and F1-score). Experiments prove that the proposed approach provides better accuracy of 96.66, 95.22, 94.33, and 93.88% for COVISenti, COVIDSenti_A, COVIDSenti_B, and COVIDSenti_C, respectively, compared to all other methods used in this study as well as compared to the existing approaches and traditional ML and DL algorithms.

Disease Progression Detection via Deep Sequence Learning of Successive Radiographic Scans.

The highly rapid spread of the current pandemic has quickly overwhelmed hospitals all over the world and motivated extensive research to address a wide range of emerging problems. The unforeseen influx of COVID-19 patients to hospitals has made it inevitable to deploy a rapid and accurate triage system, monitor progression, and predict patients at higher risk of deterioration in order to make informed decisions regarding hospital resource management. Disease detection in radiographic scans, severity estimation, and progression and prognosis prediction have been extensively studied with the help of end-to-end methods based on deep learning. The majority of recent works have utilized a single scan to determine severity or predict progression of the disease. In this paper, we present a method based on deep sequence learning to predict improvement or deterioration in successive chest X-ray scans and build a mathematical model to determine individual patient disease progression profile using successive scans. A deep convolutional neural network pretrained on a diverse lung disease dataset was used as a feature extractor to generate the sequences. We devised three strategies for sequence modeling in order to obtain both fine-grained and coarse-grained features and construct sequences of different lengths. We also devised a strategy to quantify positive or negative change in successive scans, which was then combined with age-related risk factors to construct disease progression profile for COVID-19 patients. The age-related risk factors allowed us to model rapid deterioration and slower recovery in older patients. Experiments conducted on two large datasets showed that the proposed method could accurately predict disease progression. With the best feature extractor, the proposed method was able to achieve AUC of 0.98 with the features obtained from radiographs. Furthermore, the proposed patient profiling method accurately estimated the health profile of patients.