Diagnosis of COVID-19 Using Machine Learning and Deep Learning: A Review

Evaluation of an enhanced ResNet-18 classification model for rapid On-site diagnosis in respiratory cytology

OBJECTIVE

Rapid on-site evaluation (ROSE) of respiratory cytology specimens is a critical technique for accurate and timely diagnosis of lung cancer. However, in China, limited familiarity with the Diff-Quik staining method and a shortage of trained cytopathologists hamper utilization of ROSE. Therefore, developing an improved deep learning model to assist clinicians in promptly and accurately evaluating Diff-Quik stained cytology samples during ROSE has important clinical value.

METHODS

Retrospectively, 116 digital images of Diff-Quik stained cytology samples were obtained from whole slide scans. These included 6 diagnostic categories - carcinoid, normal cells, adenocarcinoma, squamous cell carcinoma, non-small cell carcinoma, and small cell carcinoma. All malignant diagnoses were confirmed by histopathology and immunohistochemistry. The test image set was presented to 3 cytopathologists from different hospitals with varying levels of experience, as well as an artificial intelligence system, as single-choice questions.

RESULTS

The diagnostic accuracy of the cytopathologists correlated with their years of practice and hospital setting. The AI model demonstrated proficiency comparable to the humans. Importantly, all combinations of AI assistance and human cytopathologist increased diagnostic efficiency to varying degrees.

CONCLUSIONS

This deep learning model shows promising capability as an aid for on-site diagnosis of respiratory cytology samples. However, human expertise remains essential to the diagnostic process.

Development and validation of a hybrid deep learning-machine learning approach for severity assessment of COVID-19 and other pneumonias

The Coronavirus Disease 2019 (COVID-19) is transitioning into the endemic phase. Nonetheless, it is crucial to remain mindful that pandemics related to infectious respiratory diseases (IRDs) can emerge unpredictably. Therefore, we aimed to develop and validate a severity assessment model for IRDs, including COVID-19, influenza, and novel influenza, using CT images on a multi-centre data set. Of the 805 COVID-19 patients collected from a single centre, 649 were used for training and 156 were used for internal validation (D1). Additionally, three external validation sets were obtained from 7 cohorts: 1138 patients with COVID-19 (D2), and 233 patients with influenza and novel influenza (D3). A hybrid model, referred to as Hybrid-DDM, was constructed by combining two deep learning models and a machine learning model. Across datasets D1, D2, and D3, the Hybrid-DDM exhibited significantly improved performance compared to the baseline model. The areas under the receiver operating curves (AUCs) were 0.830 versus 0.767 (p = 0.036) in D1, 0.801 versus 0.753 (p < 0.001) in D2, and 0.774 versus 0.668 (p < 0.001) in D3. This study indicates that the Hybrid-DDM model, trained using COVID-19 patient data, is effective and can also be applicable to patients with other types of viral pneumonia.

Six-month follow-up after recovery of COVID-19 Delta variant survivors via CT-based deep learning

Purpose

Using computer-aided diagnosis (CAD) methods to analyze the discharge and 6-month follow-up data of COVID-19 Delta variant survivors, evaluate and summarize the recovery and prognosis, and improve people's awareness of this disease.

Methods

This study collected clinical data, SGRQ questionnaire results, and lung CT scans (at both discharge and 6-month follow-up) from 41 COVID-19 Delta variant survivors. Two senior radiologists evaluated the CT scans before in-depth analysis. Deep lung parenchyma enhancing (DLPE) method was used to accurately segment conventional lesions and sub-visual lesions in CT images, and then quantitatively analyze lung injury and recovery. Patient recovery was also measured using the SGRQ questionnaire. The follow-up examination results from this study were combined with those of the original COVID-19 for further comparison.

Results

The participants include 13 males (31.7%) and 28 females (68.3%), with an average age of 42.2 ± 17.7 years and an average BMI of 25.2 ± 4.4 kg/m². Compared discharged CT and follow-up CT, 48.8% of survivors had pulmonary fibrosis, mainly including irregular lines (34.1%), punctuate calcification (12.2%) and nodules (12.2%). Compared with discharged CT, the ground-glass opacity basically dissipates at follow-up. The mean SGRQ score was 0.041 (0-0.104). The sequelae of survivors mainly included impaired sleep quality (17.1%), memory decline (26.8%), and anxiety (21.9%). After DLPE process, the lesion volume ratio decreased from 0.0018 (0.0003, 0.0353) at discharge to 0.0004 (0, 0.0032) at follow-up, p < 0.05, and the absorption ratio of lesion was 0.7147 (-1.0303, 0.9945).

Conclusion

The ground-glass opacity of survivors had dissipated when they were discharged from hospital, and a little fibrosis was seen in CT after 6-month, mainly manifested as irregular lines, punctuate calcification and nodules. After DLPE and quantitative calculations, we found that the degree of fibrosis in the lungs of most survivors was mild, which basically did not affect lung function. However, there are a small number of patients with unabsorbed or increased fibrosis. Survivors mainly had non-pulmonary sequelae such as impaired sleep quality and memory decline. Pulmonary prognosis of Delta variant patients was better than original COVID-19, with fewer and milder sequelae.

LDDNet: A Deep Learning Framework for the Diagnosis of Infectious Lung Diseases

This paper proposes a new deep learning (DL) framework for the analysis of lung diseases, including COVID-19 and pneumonia, from chest CT scans and X-ray (CXR) images. This framework is termed optimized DenseNet201 for lung diseases (LDDNet). The proposed LDDNet was developed using additional layers of 2D global average pooling, dense and dropout layers, and batch normalization to the base DenseNet201 model. There are 1024 Relu-activated dense layers and 256 dense layers using the sigmoid activation method. The hyper-parameters of the model, including the learning rate, batch size, epochs, and dropout rate, were tuned for the model. Next, three datasets of lung diseases were formed from separate open-access sources. One was a CT scan dataset containing 1043 images. Two X-ray datasets comprising images of COVID-19-affected lungs, pneumonia-affected lungs, and healthy lungs exist, with one being an imbalanced dataset with 5935 images and the other being a balanced dataset with 5002 images. The performance of each model was analyzed using the Adam, Nadam, and SGD optimizers. The best results have been obtained for both the CT scan and CXR datasets using the Nadam optimizer. For the CT scan images, LDDNet showed a COVID-19-positive classification accuracy of 99.36%, a 100% precision recall of 98%, and an F1 score of 99%. For the X-ray dataset of 5935 images, LDDNet provides a 99.55% accuracy, 73% recall, 100% precision, and 85% F1 score using the Nadam optimizer in detecting COVID-19-affected patients. For the balanced X-ray dataset, LDDNet provides a 97.07% classification accuracy. For a given set of parameters, the performance results of LDDNet are better than the existing algorithms of ResNet152V2 and XceptionNet.

Machine-learning models utilizing CYP3A4*1G show improved prediction of hypoglycemic medication in Type 2 diabetes

The effectiveness and side effects of Type 2 diabetes (T2D) medication are related to individual genetic background. SNPs CYP3A4 and CYP2C19 were introduced to machine-learning models to improve the performance of T2D medication prediction. Two multilabel classification models, ML-KNN and WRank-SVM, trained with clinical data and CYP3A4/ CYP2C19 SNPs were evaluated. Prediction performance was evaluated with Hamming loss, one-error, coverage, ranking loss and average precision. The average precision of ML-KNN and WRank-SVM using clinical data was 92.74% and 92.9%, respectively. Combined with CYP2C19*2*3, the average precision dropped to 88.84% and 89.93%, respectively. While combined with CYP3A4*1G, the average precision was enhanced to 97.96% and 97.82%, respectively. Results suggest that CYP3A4*1G can improve the performance of ML-KNN and WRank-SVM models in predicting T2D medication performance.

Mental Disorder Diagnosis from EEG Signals Employing Automated Leaning Procedures Based on Radial Basis Functions

Purpose

In this paper, a new automated procedure based on deep learning methods for schizophrenia diagnosis is presented.

Methods

To this aim, electroencephalogram signals obtained using a 32-channel helmet are prominently used to analyze high temporal resolution information from the brain. By these means, the data collected is employed to evaluate the class likelihoods using a neuronal network based on radial basis functions and a fuzzy means algorithm.

Results

The results obtained with real datasets validate the high accuracy of the proposed classification method. Thus, effectively characterizing the changes in EEG signals acquired from schizophrenia patients and healthy volunteers. More specifically, values of accuracy better than 93% has been obtained in the present research. Additionally, a comparative study with other approaches based on well-knows machine learning methods shows that the proposed method provides better results than recently proposed algorithms in schizophrenia detection.

Conclusion

The proposed method can be used as a diagnostic tool in the detection of the schizophrenia, helping for early diagnosis and treatment.

Model Building in Forensic Psychiatry: A Machine Learning Approach to Screening Offender Patients with SSD

Today’s extensive availability of medical data enables the development of predictive models, but this requires suitable statistical methods, such as machine learning (ML). Especially in forensic psychiatry, a complex and cost-intensive field with risk assessments and predictions of treatment outcomes as central tasks, there is a need for such predictive tools, for example, to anticipate complex treatment courses and to be able to offer appropriate therapy on an individualized basis. This study aimed to develop a first basic model for the anticipation of adverse treatment courses based on prior compulsory admission and/or conviction as simple and easily objectifiable parameters in offender patients with a schizophrenia spectrum disorder (SSD). With a balanced accuracy of 67% and an AUC of 0.72, gradient boosting proved to be the optimal ML algorithm. Antisocial behavior, physical violence against staff, rule breaking, hyperactivity, delusions of grandeur, fewer feelings of guilt, the need for compulsory isolation, cannabis abuse/dependence, a higher dose of antipsychotics (measured by the olanzapine half-life) and an unfavorable legal prognosis emerged as the ten most influential variables out of a dataset with 209 parameters. Our findings could demonstrate an example of the use of ML in the development of an easy-to-use predictive model based on few objectifiable factors.

AI-Assisted Tuberculosis Detection and Classification from Chest X-Rays Using a Deep Learning Normalization-Free Network Model

Tuberculosis (TB) is an airborne disease caused by Mycobacterium tuberculosis. It is imperative to detect cases of TB as early as possible because if left untreated, there is a 70% chance of a patient dying within 10 years. The necessity for supplementary tools has increased in mid to low-income countries due to the rise of automation in healthcare sectors. The already limited resources are being heavily allocated towards controlling other dangerous diseases. Modern digital radiography (DR) machines, used for screening chest X-rays of potential TB victims are very practical. Coupled with computer-aided detection (CAD) with the aid of artificial intelligence, radiologists working in this field can really help potential patients. In this study, progressive resizing is introduced for training models to perform automatic inference of TB using chest X-ray images. ImageNet fine-tuned Normalization-Free Networks (NFNets) are trained for classification and the Score-Cam algorithm is utilized to highlight the regions in the chest X-Rays for detailed inference on the diagnosis. The proposed method is engineered to provide accurate diagnostics for both binary and multiclass classification. The models trained with this method have achieved 96.91% accuracy, 99.38% AUC, 91.81% sensitivity, and 98.42% specificity on a multiclass classification dataset. Moreover, models have also achieved top-1 inference metrics of 96% accuracy and 98% AUC for binary classification. The results obtained demonstrate that the proposed method can be used as a secondary decision tool in a clinical setting for assisting radiologists.

Performance of Machine Learning Algorithms for Predicting Adverse Outcomes in Community-Acquired Pneumonia

Background: The ability to assess adverse outcomes in patients with community-acquired pneumonia (CAP) could improve clinical decision-making to enhance clinical practice, but the studies remain insufficient, and similarly, few machine learning (ML) models have been developed.

Objective: We aimed to explore the effectiveness of predicting adverse outcomes in CAP through ML models.

Methods: A total of 2,302 adults with CAP who were prospectively recruited between January 2012 and March 2015 across three cities in South America were extracted from DryadData. After a 70:30 training set: test set split of the data, nine ML algorithms were executed and their diagnostic accuracy was measured mainly by the area under the curve (AUC). The nine ML algorithms included decision trees, random forests, extreme gradient boosting (XGBoost), support vector machines, Naïve Bayes, K-nearest neighbors, ridge regression, logistic regression without regularization, and neural networks. The adverse outcomes included hospital admission, mortality, ICU admission, and one-year post-enrollment status.

Results: The XGBoost algorithm had the best performance in predicting hospital admission. Its AUC reached 0.921, and accuracy, precision, recall, and F1-score were better than those of other models. In the prediction of ICU admission, a model trained with the XGBoost algorithm showed the best performance with AUC 0.801. XGBoost algorithm also did a good job at predicting one-year post-enrollment status. The results of AUC, accuracy, precision, recall, and F1-score indicated the algorithm had high accuracy and precision. In addition, the best performance was seen by the neural network algorithm when predicting death (AUC 0.831).

Conclusions: ML algorithms, particularly the XGBoost algorithm, were feasible and effective in predicting adverse outcomes of CAP patients. The ML models based on available common clinical features had great potential to guide individual treatment and subsequent clinical decisions.

Detection of COVID-19 Patients Using Machine Learning Techniques: A Nationwide Chilean Study

Epivigila is a Chilean integrated epidemiological surveillance system with more than 17,000,000 Chilean patient records, making it an essential and unique source of information for the quantitative and qualitative analysis of the COVID-19 pandemic in Chile. Nevertheless, given the extensive volume of data controlled by Epivigila, it is difficult for health professionals to classify vast volumes of data to determine which symptoms and comorbidities are related to infected patients. This paper aims to compare machine learning techniques (such as support-vector machine, decision tree and random forest techniques) to determine whether a patient has COVID-19 or not based on the symptoms and comorbidities reported by Epivigila. From the group of patients with COVID-19, we selected a sample of 10% confirmed patients to execute and evaluate the techniques. We used precision, recall, accuracy, F1-score, and AUC to compare the techniques. The results suggest that the support-vector machine performs better than decision tree and random forest regarding the recall, accuracy, F1-score, and AUC. Machine learning techniques help process and classify large volumes of data more efficiently and effectively, speeding up healthcare decision making.

FLED-Block: Federated Learning Ensembled Deep Learning Blockchain Model for COVID-19 Prediction

With the SARS-CoV-2's exponential growth, intelligent and constructive practice is required to diagnose the COVID-19. The rapid spread of the virus and the shortage of reliable testing models are considered major issues in detecting COVID-19. This problem remains the peak burden for clinicians. With the advent of artificial intelligence (AI) in image processing, the burden of diagnosing the COVID-19 cases has been reduced to acceptable thresholds. But traditional AI techniques often require centralized data storage and training for the predictive model development which increases the computational complexity. The real-world challenge is to exchange data globally across hospitals while also taking into account of the organizations' privacy concerns. Collaborative model development and privacy protection are critical considerations while training a global deep learning model. To address these challenges, this paper proposes a novel framework based on blockchain and the federated learning model. The federated learning model takes care of reduced complexity, and blockchain helps in distributed data with privacy maintained. More precisely, the proposed federated learning ensembled deep five learning blockchain model (FLED-Block) framework collects the data from the different medical healthcare centers, develops the model with the hybrid capsule learning network, and performs the prediction accurately, while preserving the privacy and shares among authorized persons. Extensive experimentation has been carried out using the lung CT images and compared the performance of the proposed model with the existing VGG-16 and 19, Alexnets, Resnets-50 and 100, Inception V3, Densenets-121, 119, and 150, Mobilenets, SegCaps in terms of accuracy (98.2%), precision (97.3%), recall (96.5%), specificity (33.5%), and F1-score (97%) in predicting the COVID-19 with effectively preserving the privacy of the data among the heterogeneous users.

Optimal scale combination selection for inconsistent multi-scale decision tables

Hierarchical structured data are very common for data mining and other tasks in real-life world. How to select the optimal scale combination from a multi-scale decision table is critical for subsequent tasks. At present, the models for calculating the optimal scale combination mainly include lattice model, complement model and stepwise optimal scale selection model, which are mainly based on consistent multi-scale decision tables. The optimal scale selection model for inconsistent multi-scale decision tables has not been given. Based on this, firstly, this paper introduces the concept of complement and lattice model proposed by Li and Hu. Secondly, based on the concept of positive region consistency of inconsistent multi-scale decision tables, the paper proposes complement model and lattice model based on positive region consistent and gives the algorithm. Finally, some numerical experiments are employed to verify that the model has the same properties in processing inconsistent multi-scale decision tables as the complement model and lattice model in processing consistent multi-scale decision tables. And for the consistent multi-scale decision table, the same results can be obtained by using the model based on positive region consistent. However, the lattice model based on positive region consistent is more time-consuming and costly. The model proposed in this paper provides a new theoretical method for the optimal scale combination selection of the inconsistent multi-scale decision table.

Let AI Perform Better Next Time—A Systematic Review of Medical Imaging-Based Automated Diagnosis of COVID-19: 2020–2022

The pandemic of COVID-19 has caused millions of infections, which has led to a great loss all over the world, socially and economically. Due to the false-negative rate and the time-consuming characteristic of the Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests, diagnosing based on X-ray images and Computed Tomography (CT) images has been widely adopted to confirm positive COVID-19 RT-PCR tests. Since the very beginning of the pandemic, researchers in the artificial intelligence area have proposed a large number of automatic diagnosing models, hoping to assist radiologists and improve the diagnosing accuracy. However, after two years of development, there are still few models that can actually be applied in real-world scenarios. Numerous problems have emerged in the research of the automated diagnosis of COVID-19. In this paper, we present a systematic review of these diagnosing models. A total of 179 proposed models are involved. First, we compare the medical image modalities (CT or X-ray) for COVID-19 diagnosis from both the clinical perspective and the artificial intelligence perspective. Then, we classify existing methods into two types—image-level diagnosis (i.e., classification-based methods) and pixel-level diagnosis (i.e., segmentation-based models). For both types of methods, we define universal model pipelines and analyze the techniques that have been applied in each step of the pipeline in detail. In addition, we also review some commonly adopted public COVID-19 datasets. More importantly, we present an in-depth discussion of the existing automated diagnosis models and note a total of three significant problems: biased model performance evaluation; inappropriate implementation details; and a low reproducibility, reliability and explainability. For each point, we give corresponding recommendations on how we can avoid making the same mistakes and let AI perform better in the next pandemic.

A review on epidemiology, genomic characteristics, spread, and treatments of COVID-19

In December 2019, a new form of coronavirus named severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) started spreading in Wuhan, China. According to the situation report-95 published by the World Health Organization (WHO), the coronavirus disease spread rapidly to 213 countries and territories by April 24, 2020, with the number of confirmed cases and deaths of 26,26,321 and 1,81,938, respectively. The WHO declared coronavirus disease 2019 (COVID-19) as a pandemic on March 11, 2020. People living in many countries are in lockdown and staying at home because of this deadly virus. Patients of COVID-19 are reported to have single or multiple symptoms, while some patients do not have any remarkable symptom at all. Patients have reported symptoms of dry cough, sore throat, fever, fatigue, breathing problem, and gastrointestinal infection. COVID-19 may become very dangerous especially for aged people and people with any other disease such as diabetes, kidney problem, etc. In that case, the virus can cause acute respiratory distress syndrome and cytokine storm. The whole world is in lockdown because of this deadly virus. Currently, there is no particular cure for this disease; however, researchers are trying to find appropriate antiviral and repurposed drugs. This chapter provides a review on the different aspects of COVID-19 including the epidemiology, genomic sequence, and clinical characteristics; current medical treatment options; and development of vaccines and drugs.

CO-IRv2: Optimized InceptionResNetV2 for COVID-19 detection from chest CT images

This paper focuses on the application of deep learning (DL) in the diagnosis of coronavirus disease (COVID-19). The novelty of this work is in the introduction of optimized InceptionResNetV2 for COVID-19 (CO-IRv2) method. A part of the CO-IRv2 scheme is derived from the concepts of InceptionNet and ResNet with hyperparameter tuning, while the remaining part is a new architecture consisting of a global average pooling layer, batch normalization, dense layers, and dropout layers. The proposed CO-IRv2 is applied to a new dataset of 2481 computed tomography (CT) images formed by collecting two independent datasets. Data resizing and normalization are performed, and the evaluation is run up to 25 epochs. Various performance metrics, including precision, recall, accuracy, F1-score, area under the receiver operating characteristics (AUC) curve are used as performance metrics. The effectiveness of three optimizers known as Adam, Nadam and RMSProp are evaluated in classifying suspected COVID-19 patients and normal people. Results show that for CO-IRv2 and for CT images, the obtained accuracies of Adam, Nadam and RMSProp optimizers are 94.97%, 96.18% and 96.18%, respectively. Furthermore, it is shown here that for the case of CT images, CO-IRv2 with Nadam optimizer has better performance than existing DL algorithms in the diagnosis of COVID-19 patients. Finally, CO-IRv2 is applied to an X-ray dataset of 1662 images resulting in a classification accuracy of 99.40%.