ABSTRACT
Objective:To explore the differences in laboratory indicators test results of coronavirus disease 2019 (COVID-19) and influenza A and to establish a differential diagnosis model for the two diseases, and to clarify the clinical significance of the model for distinguishing the two diseases. Methods :A total of 56 common COVID-19 patients and 54 influenza A patients were enrolled , and 24 common COVID-19 patients and 30 influenza A patients were used for model validation. The average values of the laboratory indicators of the patients 5 d after admission were calculated,and the elastic network model and the stepwise Logistic regression model were used to screen the indicators for identifying COVID-19 and influenza A. Elastic network models were used for the first round of selection,in which the optimal cutoff of lambda was chosen by performing 10-fold cross validations. With different random seeds,the elastic net models were fit for 200 times to select the high-frequency indexes ( frequency>90% ). A Logistic regression model with AIC as the selection criterions was used in the second round of screening uses;a nomogram was used to represent the final model;an independent data were used as an external validation set,and the area under the curve (AUC) of the validation set were calculate to evaluate the predictive the performance of the model. Results:After the first round of screening, 16 laboratory indicators were selected as the high-frequency indicators. After the second round of screening,albumin/ globulin (A/G),total bilirubin (TBIL) and erythrocyte volume (HCT) were identified as the final indicators. The model had good predictive performance , and the AUC of the verification set was 0. 844 (95% CI:0. 747-0. 941). Conclusion:A differential diagnosis model for COVID-19 and influenza A based on laboratory indicators is successfully established,and it will help clinical and timely diagnosis of both diseases.Copyright © 2022 Jilin University Press. All rights reserved.
ABSTRACT
Percentage of body fat, age, weight, height, and 14 circumference measurements (e.g., waist) are given for 184 women aged 18–25. Body fat, one measure of health, was accurately determined by an underwater weighing technique which requires special equipment and training of the individuals conducting the process. Modeling body fat percentage using multiple regression provides a convenient method of estimating body fat percentage using measures collected using only a measuring tape and a scale. This dataset can be used to show students the utility of multiple regression and to provide practice in model building.
ABSTRACT
Objectives: This study investigated the risk factors of developing COVID Syndrome and identified potential disease profiles that may exist among those who have contracted COVID-19. Method(s): Data on 13,953 adults who had experienced COVID-19 at any time were analyzed from the 2022 US National Health and Wellness Survey. XGBoost binary classification with 10-fold cross-validation was used to predict long COVID among those who reported experiencing COVID-19 and to extract feature importance. Synthetic minority oversampling technique (SMOTE) was used to address class imbalance in the outcome variable. Variable selection was conducted based on SHAP values. Fifty variables including demographic characteristics, COVID-19 symptoms, comorbidities, and health characteristics were used in the final model. Parameters were tuned using AUC. Among the 2,665 respondents who were diagnosed with long COVID, k-medoids clustering with t-SNE dimensionality reduction was implemented to determine whether distinct symptom profiles exist. Average silhouette score was used to determine the optimal number of clusters. Result(s): The XGBoost binary classification for predicting long COVID among those with COVID-19 had an AUC of 0.9145, accuracy of 0.9072, sensitivity of 0.9630, specificity of 0.8328, and Brier score of 0.0928. The most important features in predicting long COVID were age, smoking habits, COVID-19 vaccination status, certain COVID-19 symptoms experienced, and certain comorbidities. Among those diagnosed with long COVID, the clustering analysis found nine unique clusters of symptoms. The cluster that experienced the most severe symptoms was older, female, lower income, lower vaccination rate, and had more comorbidities like asthma, chronic bronchitis, and allergies. Conclusion(s): In a broadly representative US adult population, XGBoost model identified a selection of risk factors for developing long COVID. K-medoids clustering identified clusters of patients that were at risk for developing severe symptoms.Copyright © 2023
ABSTRACT
To minimize the rate of death from COVID-19 and stop the disease from spreading early detection is vital. The normal RT-PCR tests for COVID-19 detection take a long time to complete. In contrast to this test, Covid-19 can be quickly detected using various machine-learning technologies. Previous studies only had access to smaller datasets, as COVID-19 data was not readily available back then. Since COVID-19 is a dangerous virus, the model needs to be robust and trustworthy, and the model must be trained on a large and diverse dataset. To overcome that problem, this study combines six publicly available Chest X-ray datasets to produce a larger and more diverse balanced dataset with a total of 68,424 images. In this study, we develop a CNN model that primarily entails two steps: (a) feature extraction and (b) classification, which are used to identify COVID-19 positive cases from X-ray images. The accuracy of this proposed model is 97.58%, which is higher than most state-of-the-art models. © 2022 IEEE.
ABSTRACT
Background: COVID-19 is a disease that attacks the respiratory system and is highly contagious, so cases of the spread of COVID-19 are increasing every day. The increase in COVID-19 cases cannot be predicted accurately, resulting in a shortage of services, facilities and medical personnel. This number will always increase if the community is not vigilant and actively reduces the rate of adding confirmed cases. Therefore, public awareness and vigilance need to be increased by presenting information on predictions of confirmed cases, recovered cases, and cases of death of COVID-19 so that it can be used as a reference for the government in taking and establishing a policy to overcome the spread of COVID-19. Objective: This research predicts COVID-19 in confirmed cases, recovered cases, and death cases in Lampung Province Method: This study uses the ANN method to determine the best network architecture for predicting confirmed cases, recovered cases, and deaths from COVID-19 using the k-fold cross-validation method to measure predictive model performance. Results: The method used has a good predictive ability with an accuracy value of 98.22% for confirmed cases, 98.08% for cured cases, and 99.05% for death cases. Conclusion: The ANN method with k-fold cross-validation to predict confirmed cases, recovered cases, and COVID-19 deaths in Lampung Province decreased from October 27, 2021, to January 24, 2022. © 2023 The Authors. Published by Universitas Airlangga.
ABSTRACT
Background: Recent findings from the UK Biobank revealed that healthy adults who later became infected with SARS-CoV-2 had lower brain volumes in regions involved in risk-taking behavior and olfaction compared to individuals who did not become infected. We examined if similar pre-existing differences in brain regions correspond to SARS-CoV-2 infection among people with HIV (PWH) receiving suppressive ART. Method(s): Participants included adult Thai MSM enrolled in the acute HIV (AHI) cohort (RV254/SEARCH010) in Bangkok, Thailand. Participants underwent 3T MRI and clinical assessments (i.e., HIV disease metrics, cognitive testing, and self-reported mood and substance use). ART initiation occurred within 5 days of the MRI (median=same day). Regional brain volumes were summed across hemispheres and corrected for head size. Brain volumes and clinical indices were compared between participants with laboratory confirmed SARS-CoV-2 and those without a diagnosis of SARS-CoV-2 following ART initiation. Machine learning was utilized to identify variables at the time of enrollment into the cohort that predicted subsequent SARS-CoV-2 infection status. Result(s): 112 participants were included in the analysis. All study participants achieved viral suppression after ART and received SARS-CoV-2 vaccinations. Fifty-four participants became infected with SARS-CoV-2 during the observation period (median=79 weeks from ART initiation). Study participants who became infected with SARS-CoV-2 after ART had lower volumes at the time of enrollment in several subcortical brain regions with the most pronounced effect in the pallidum (p=.025). There were no associations between brain volumes and ratings of mood, demographics, or HIV disease indices. SARS-CoV-2 infection was two-fold higher among individuals who reported use of amyl nitrites (i.e., poppers) during chemsex. Machine learning with repeated cross validation revealed that lower orbital and medial frontal lobe, anterior cingulate, pallidum, vermis, and olfactory volumes, worse motor function, and higher education collectively predicted co-infection status (average AUC of 85%). Conclusion(s): Study findings point toward a risk phenotype for SARS-CoV-2 infection among PWH defined by pre-existing differences in brain volumes relevant to risk-taking behavior, emotion, and neuroHIV as well as behavioral factors such as inhalant use and lack of social distancing during chemsex. (Table Presented).
ABSTRACT
Introduction: Acute kidney injury (AKI) is a frequent and severe complication of COVID-19 infection in ICU patients. We propose a structured data-driven methodology and develop a model to predict the use of renal replacement therapy for patients on respiratory support with Covid-19 in 126 ICUs from 42 Brazilian hospitals. Method(s): Adult ICU patients (March 2020-December 2021) with confirmed SARS-CoV-2 infection and need of ventilatory support at D1 admission in the ICU. Main outcome was the need of RRT. We estimated 3 prediction models: Logistic Regression (LR), Random Forest (RF) and XGB Boosting. Models were derived in the training set and evaluated in the test set following an 80/20 split ratio, and models' parameters were selected using fivefold cross-validation. We evaluated and selected the best model in terms of discrimination (AUC) and calibration (Brier's Score). Variable importance was estimated for each predictor variable. Result(s): 13,575 ICU patients with need of respiratory support, of which 1828 (14%) needed RRT. ICU and hospital mortality were respectively 15.7%, 20.3% (non-RRT) and 54.3%, 69% (RRT). Mean age was 63.9 and 55.3 years (RRT vs non-RRT). Mean ICU LOS was 27.8 vs. 12 days, in RRT vs non-RRT. RF and XGB models both showed higher discrimination performance compared to LR (95% confidence interval [95% CI]: 0.84 [0.81-0.85] and 0.83 [0.80-0.85] vs 0.78 [0.75-0.80]). RF and XGB models presented similar calibration (Brier's Score: ([95% CI]: 0.09 [0.09- 0.10] and 0.09 [0.09-0.10]), also better than in LR (0.11 [0.10-0.12]). The final model (RF) showed no sign of under or overestimation of predicted probabilities in calibration plots. Conclusion(s): The need of RRT among patients on respiratory support diagnosed with Covid-19 was accurately predicted through machine learning methods. RF and XGB based models using data from general intensive care databases provides an accurate and practical approach for the early prediction of use of RRT in COVID-19 patients.
ABSTRACT
A fundamental challenge in the fight against COVID-19 is the development of reliable and accurate tools to predict disease progression in a patient. This information can be extremely useful in distinguishing hospitalized patients at higher risk for needing UCI from patients with low severity. How SARS-CoV-2 infection will evolve is still unclear. Method(s): A novel pipeline was developed that can integrate RNA-Seq data from different databases to obtain a genetic biomarker COVID-19 severity index using an artificial intelligence algorithm. Our pipeline ensures robustness through multiple cross-validation processes in different steps. Result(s): CD93, RPS24, PSCA, and CD300E were identified as COVID-19 severity gene signatures. Furthermore, using the obtained gene signature, an effective multi-class classifier capable of discrimi-nating between control, outpatient, inpatient, and ICU COVID-19 patients was optimized, achieving an accuracy of 97.5%. Conclusion(s): In summary, during this research, a new intelligent pipeline was implemented to develop a specific gene signature that can detect the severity of patients suffering COVID-19. Our approach to clinical decision support systems achieved excellent results, even when processing unseen samples. Our system can be of great clinical utility for the strategy of planning, organizing and managing human and material resources, as well as for automatically classifying the severity of patients affected by COVID-19.Copyright © 2023 Bentham Science Publishers.
ABSTRACT
This research developed a multinomial classification model that predicts the prevalent mode of transmission of the coronavirus from person to person within a geographic area, using data from the World Health Organization (WHO). The WHO defines four transmission modes of the coronavirus disease 2019 (COVID-19);namely, community transmission, pending (unknown), sporadic cases, and clusters of cases. The logistic regression was deployed on the COVID-19 dataset to construct a multinomial model that can predict the prevalent transmission mode of coronavirus within a geographic area. The k-fold cross validation was employed to test predictive accuracy of the model, which yielded 73% accuracy. This model can be adopted by local authorities such as regional, state, local government, and cities, to predict the prevalent transmission mode of the virus within their territories. The outcome of the prediction will determine the appropriate strategies to put in place or re-enforced to curtail further transmission.Copyright © 2023 Inderscience Enterprises Ltd.
ABSTRACT
Identification of lung abnormalities indicated by Covid-19 (Corona Virus Disease 2019) requires thoroughness and accuracy in decision making. Because it is related to the determination of the next follow-up to take appropriate action or treatment for the patient being treated. The study was raised to identify the lungs seen from chest X-rays whether normal or affected by Covid-19. Identification is made consists of several processes, namely pre-processing, characteristic extraction, and identification. Identify by comparing GLCM (Gray-Level Co-occurrence Matrix) and Statistical feature extraction. Pre-processing is used to improve the quality of X-ray photos including in this study, namely resize and grayscale. The characteristic extraction process is used to obtain input data that will be used when used in the identification process. Extraction of features here using two methods, namely: GLCM and Statistics. The GLCM methods used are Contrast, Correlation, Energy, Homogenity. As for statistics the values sought include Mean, Deviation, Skewness, Energy, Entropy, Smoothness. Identification using the Artificial Neural Network Radial Basis Function (ANN-RBF). The latter process sought the accuracy levels of two characteristic extraction methods (GLCM and Statistics) identified with ANN-RBF. The level of accuracy sought by using K-Fold Cross Validation. The data used a total of 50 data, with details of 25 chest X-rays that have been identified as normal and 25 chest X-rays identified as Covid-19. The results showed that the extraction of traits using the GLCM method was better viewed from its accuracy rate when compared to statistical methods, with each accuracy rate for GLCM at 91.63% and Statistics at 87.08%. © 2023 International Journal of Artificial Intelligence.
ABSTRACT
Purposes: Artificial Intelligence (AI) models are constantly developing to help clinicians in challenging tasks such as classification of images in radiological practice. The aim of this work was to compare the diagnostic performance of an AI classifier model developed in our hospital with the results obtained from the radiologists reading the CT images in discriminating different types of viral pneumonia. Material(s) and Method(s): Chest CT images of 1028 patients with positive swab for SARS-CoV-2 (n=646) and other respiratory viruses (n=382) were segmented automatically for lung extraction and Radiomic Features (RF) of first (n=18) and second (n=120) order were extracted using PyRadiomics tools. RF, together with patient age and sex, were used to develop a Multi-Layer Perceptron classifier to discriminate images of patients with COVID-19 and non-COVID-19 viral pneumonia. The model was trained with 808 CT images performing a LASSO regression (Least Absolute Shrinkage and Selection Operator), a hyper-parameter tuning and a final 4-fold cross validation. The remaining 220 CT images (n=151 COVID-19, n=69 non-COVID-19) were used as independent validation (IV) dataset. Four readers (three radiologists with >10 years of experience and one radiology resident with 3 years of experience) were recruited to blindly evaluate the IV dataset using the 5-points scale CO-RADS score. CT images with CO-RADS >=3 were considered "COVID-19". The same images were classified as "COVID-19" or "non-COVID-19" by applying the AI model with a threshold on the predicted values of 0.5. Diagnostic accuracy, specificity, sensibility and F1 score were calculated for human readers and AI model. Result(s): The AI model was trained using 24 relevant features while the Area under ROC curve values after 4-fold cross validation and its application to the IV dataset were, respectively, 0.89 and 0.85. Interreader agreement in assigning CO-RADS class, analyzed with Fleiss' kappa with ordinal weighting, was good (k=0.68;IC95% 0.63-0.72) and diagnostic performance were then averaged among readers. Diagnostic accuracy, specificity, sensibility and F1 score resulted 78.6%, 78.3%, 78.8% and 78.5% for AI model and 77.7%, 65.6%, 83.3% and 72.0% for human readers. The difference between specificity and sensitivity observed in human readers could be related to the higher rate of false positive due to the higher incidence of COVID-19 patients in comparison with other types of viral pneumonitis during the last 2 years. Conclusion(s): A model based on RF and artificial intelligence provides comparable results with human readers in terms of diagnostic performance in a classification task.Copyright © 2023 Southern Society for Clinical Investigation.
ABSTRACT
This study addressed the issue of determining multiple potential clusters with regularization approaches for the purpose of spatio-temporal clustering. The generalized lasso framework has flexibility to incorporate adjacencies between objects in the penalty matrix and to detect multiple clusters. A generalized lasso model with two L1 penalties is proposed, which can be separated into two generalized lasso models: trend filtering of temporal effect and fused lasso of spatial effect for each time point. To select the tuning parameters, the approximate leave-one-out cross-validation (ALOCV) and generalized cross-validation (GCV) are considered. A simulation study is conducted to evaluate the proposed method compared to other approaches in different problems and structures of multiple clusters. The generalized lasso with ALOCV and GCV provided smaller MSE in estimating the temporal and spatial effect compared to unpenalized method, ridge, lasso, and generalized ridge. In temporal effects detection, the generalized lasso with ALOCV and GCV provided relatively smaller and more stable MSE than other methods, for different structure of true risk values. In spatial effects detection, the generalized lasso with ALOCV provided higher index of edges detection accuracy. The simulation also suggested using a common tuning parameter over all time points in spatial clustering. Finally, the proposed method was applied to the weekly Covid-19 data in Japan form March 21, 2020, to September 11, 2021, along with the interpretation of dynamic behavior of multiple clusters.
ABSTRACT
The term 'lung disease' covers a wide range of conditions that affect the lungs, including asthma, COPD, infections like the flu, pneumonia, tuberculosis, lung cancer, COVID, and numerous other breathing issues. Respiratory failure may result from several respiratory disorders. Recently, various methods have been proposed for lung disease detection, but they are not much more efficient. The proposed model has been tested on the COVID dataset. In this work, Littlewood-Paley Empirical Wavelet Transform (LPEWT) based technique is used to decompose images into their sub-bands. Using locally linear embedding (LLE), linear discriminative analysis (LDA), and principal component analysis (PCA), robust features are identified for lung disease detection after texture-based relevant Gabor features are extracted from images. LLE's outcomes inspire the development of new techniques. The Entropy, ROC, and Student's t-value methods provide ranks for robust features. Finally, LS-SVM is fed with t-value-based ranked features for classification using Morlet wavelet, Mexican-hat wavelet, and radial basis function. This model, which incorporated tenfold cross-validation, exhibited improved classification accuracy of 95.48%, specificity of 95.37%, sensitivity of 95.43%, and an F1 score of.95. The proposed diagnosis method can be a fast disease detection tool for imaging specialists using medical images.Copyright © 2023 Informa UK Limited, trading as Taylor & Francis Group.
ABSTRACT
Due to the COVID-19 global pandemic, computer-assisted diagnoses of medical images have gained much attention, and robust methods of semantic segmentation of Computed Tomography (CT) images have become highly desirable. In this work, we present a deeper analysis of how data augmentation techniques improve segmentation performance on this problem. We evaluate (Formula presented.) traditional augmentation techniques on five public datasets. Six different probabilities of applying each augmentation technique on an image were evaluated. We also assess a different training methodology where the training subsets are combined into a single larger set. All networks were evaluated through a (Formula presented.) -fold cross-validation strategy, resulting in over (Formula presented.) experiments. We also propose a novel data augmentation technique based on Generative Adversarial Networks (GANs) to create new healthy and unhealthy lung CT images, evaluating four variations of our approach with the same six probabilities of the traditional methods. Our findings show that GAN-based techniques and spatial-level transformations are the most promising for improving the learning of deep models on this problem, with the StarGAN v2 + F with a probability of (Formula presented.) achieving the highest F-score value on the Ricord1a dataset in the unified training strategy. Our code is publicly available at https://github.com/VRI-UFPR/DACov2022.Copyright © 2023 Informa UK Limited, trading as Taylor & Francis Group.
ABSTRACT
Currently, we are witnessing the emergence of big data in various fields including the biomedical and natural sciences. The size of chemoinformatics and bioinformatics databases is increasing every day. This gives us both challenges and opportunities. This chapter discusses the mathematical methods used in these fields both for the generation and analysis of such data. It is emphasized that proper use of robust statistical and machine learning methods in the analysis of the available big data may facilitate both hypothesis-driven and discovery-oriented research. © 2023 Elsevier Inc. All rights reserved.
ABSTRACT
Introduction: SARS-COV-2 is mainly transmitted through respiratory droplets. The standard diagnostic procedure is based on a reverse transcription polymerase chain reaction (RT-PCR). Aim(s): 1) To develop a safe and easy to perform breath test for the detection of COVID-19 in hospitalised patients based on the analysis of volatile organic compounds (VOCs) in exhaled breath. 2) To differentiate in hospitalised patients with respiratory symptoms those with and without COVID-19. Method(s): We performed a monocenter, cross-sectional, case-control study in 38 subjects (63% males, age 62+/-12.7 yrs) admitted at the pulmonology ward. Breath samples were taken using a home-made sampling system. Analysis of breath samples was performed by proton transfer high resolution mass spectrometry (PTR-HRMS). A lassoregression with leave-one-out cross-validation was performed to differentiate the groups and designate the most differentiating VOCs. Result(s): COVID-19 positive (n=22) and control respiratory patients (n=16) were similar with respect to baseline characteristics, except for lower blood neutrophil and lymphocyte counts and higher ferritin level in COVID+ve patients (p<0.05). Lasso-regression revealed 6 VOCs as potential biomarkers that differentiated between both groups with 84% accuracy, 100% specificity and 100% positive predictive value based on PTR-HRMS data. Conclusion(s): Breath analysis could identify a breathprint differentiating between hospitalised COVID-19 and nonCOVID-19 patients with respiratory symptoms with a good accuracy. Therefore, VOCs profiling could be integrated in sensors allowing a fast breathalyzer for COVID-19 for large-scale screening.
ABSTRACT
While the world is still struggling to recover from the harm caused by the widespread COVID-19 pandemic, the monkeypox virus now poses a new threat of becoming a pandemic. Although it is not as dangerous or infectious as COVID-19, new cases of the disease are nevertheless being reported daily from many countries. In this study, we have used public datasets provided by the European Centre for Disease Prevention and Control for developing a prediction model for the spread of the monkeypox outbreak to and throughout the USA, Germany, the UK, France and Canada. We have used certain effective neural network models for this purpose. The novelty of this study is that a neural network model for a time series monkeypox dataset is developed and compared with LSTM and GRU models using an adaptive moment estimation (ADAM) optimizer. The Levenberg-Marquardt (LM) learning technique is used to develop and validate a single hidden layer artificial neural network (ANN) model. Different ANN model architectures with varying numbers of hidden layer neurons were trained, and the K-fold cross-validation early stopping validation approach was employed to identify the optimum structure with the best generalization potential. In the regression analysis, our ANN model gives a good R-value of almost 99%, the LSTM model gives almost 98% and the GRU model gives almost 98%. These three model fits demonstrated that there was a good agreement between the experimental data and the forecasted values. The results of our experiments show that the ANN model performs better than the other methods on the collected monkeypox dataset in all five countries. To the best of the authors' knowledge, this is the first report that has used ANN, LSTM and GRU to predict a monkeypox outbreak in all five countries.
ABSTRACT
Since 2019, the coronavirus disease-19 (COVID-19) has been spreading rapidly worldwide, posing an unignorable threat to the global economy and human health. It is a disease caused by severe acute respiratory syndrome coronavirus 2, a single-stranded RNA virus of the genus Betacoronavirus. This virus is highly infectious and relies on its angiotensin-converting enzyme 2-receptor to enter cells. With the increase in the number of confirmed COVID-19 diagnoses, the difficulty of diagnosis due to the lack of global healthcare resources becomes increasingly apparent. Deep learning-based computer-aided diagnosis models with high generalisability can effectively alleviate this pressure. Hyperparameter tuning is essential in training such models and significantly impacts their final performance and training speed. However, traditional hyperparameter tuning methods are usually time-consuming and unstable. To solve this issue, we introduce Particle Swarm Optimisation to build a PSO-guided Self-Tuning Convolution Neural Network (PSTCNN), allowing the model to tune hyperparameters automatically. Therefore, the proposed approach can reduce human involvement. Also, the optimisation algorithm can select the combination of hyperparameters in a targeted manner, thus stably achieving a solution closer to the global optimum. Experimentally, the PSTCNN can obtain quite excellent results, with a sensitivity of 93.65% ± 1.86%, a specificity of 94.32% ± 2.07%, a precision of 94.30% ± 2.04%, an accuracy of 93.99% ± 1.78%, an F1-score of 93.97% ± 1.78%, Matthews Correlation Coefficient of 87.99% ± 3.56%, and Fowlkes-Mallows Index of 93.97% ± 1.78%. Our experiments demonstrate that compared to traditional methods, hyperparameter tuning of the model using an optimisation algorithm is faster and more effective. © 2023 Centro Regional de Invest. Cientif. y Tecn.. All rights reserved.
ABSTRACT
The entire world is suffering from the corona pandemic (COVID-19) since December 2019. Deep convolutional neural networks (deep CNN) can be used to develop a rapid detection system of COVID-19. Among all the existing literature, ResNet50 is showing better performance, but with three main limitations, i.e.: 1) overfitting;2) computation cost;3) loss of feature information. To overcome these problems authors have proposed four different modifications on ResNet50, naming it as LightWeightResNet50. An image dataset containing chest X-ray images of coronavirus patients and normal persons is used for evaluation. Five-fold cross-validation is applied with transfer learning. Ten different performance measures (true positive, false negative, false positive, true negative, accuracy, recall, specificity, precision, F1-score and area under curve) are used for evaluation along with fold-wise performance measures comparison. The four proposed methods have an accuracy improvement of 4%, 13%, 14% and 7% respectively when compared with ResNet50.