SHAP-Driven Ensemble Learning for Explainable COVID-19 Detection

SHAP-Driven Ensemble Learning for Explainable COVID-19 Detection | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article SHAP-Driven Ensemble Learning for Explainable COVID-19 Detection Varun Sapra, Ankit Vishnoi, Neelu Jyoti Ahuja, Luxmi Sapra, Parul Madan, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6769397/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract The COVID-19 pandemic had a disastrous impact on the global community and challenged healthcare systems worldwide. The progress of the disease also has disastrous effects on the heart, kidney, and liver of an individual. The only way to save mankind from this minacious disease is its accurate and explainable detection. In this study, we propose a SHAP-driven ensemble learning framework using an optimized XGBoost algorithm ensemble with Random Forest for COVID-19 detection while providing interpretable insights into model predictions. We employ different ML models on the same dataset to evaluate the performance of these ML techniques with the proposed framework. The study also integrates Shapley additive explanations (SHAP) to improve feature selection, model interpretability, and prediction reliability. The proposed framework identifies key biomarkers that have a significant impact on COVID-19 thus improving transparency and trust in AI applications. Experimental results showed that the proposed ensemble model outperformed all other models and achieved an accuracy of 96.7%. The integration of SHAP not only enhances the model’s performance but also helps in understanding the critical factors that have a significant impact on the detection of COVID-19. Biological sciences/Computational biology and bioinformatics/Predictive medicine Health sciences/Diseases Health sciences/Medical research Physical sciences/Engineering XGBoost Random Forest Ensemble Learning COVID-19 SHAP Machine Learning Explainable AI (XAI) Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 1. Introduction The COVID-19 pandemic has had a global impact, influencing not only public health but also hindering the productivity and developmental progress of nations. The rapid spread of the disease led to severe consequences worldwide and was declared a global pandemic by the WHO [ 1 ] [ 2 ]. The major symptoms found in the suspects of COVID-19 were flu-like symptoms that include fatigue, headache, dry cough, fever, and, respiratory problems [ 3 ]. Early diagnosis is critical in controlling the disease and ensuring timely medical intervention. With the advancements in technology and prices plummeting medical sector is increasingly adopting automated processes, leading to vast data generation. COVID-19 diagnosis primarily relies on reverse transcription-polymerase chain reaction (RT-PCR) tests, which are considered the gold standard [ 4 ]. The RT-PCR test requires a sophisticated lab and well-trained medical practitioners to carry out the tests which makes the test less accessible in resource-limited settings. At the testing centers, the swab samples from suspected patients are collected and referred to the laboratories for the final diagnosis. The test can take anything from a few hours to a couple of days to get results [ 5 ]. The prolonged stay at the collection centers with the suspected victims of COVID-19 also increases the exposure risk of COVID-19. RT-PCR tests can also yield false negative results due to improper sample collection, or if the viral load is low [ 6 ]. This can lead to misdiagnoses and potential disease spread. Considering the situation, the need for a non-invasive and interpretable AI-driven diagnostics test based on clinical symptoms is required so that one can compute the results in real time, particularly in rural and underserved areas where access to sophisticated labs is limited. The system can be used to diagnose the disease and can refer the highly suspected victims for further medical examination [ 7 ]. Such systems will help in reducing the mortality rate in rural areas due to COVID-19. To address this challenge, this paper proposes a SHAP-aware ensemble learning model for COVID-19 detection. The proposed model integrates Random Forest and XGBoost, leveraging the strengths of both methods to enhance predictive performance. Ensemble learning techniques improve accuracy by combining multiple classifiers, but they often function as "black-box" models, lacking interpretability. To overcome this limitation, we incorporate ‘SHapley Additive exPlanations’ (SHAP), an advanced explainability technique that assigns important scores to each feature, thereby providing insights into the decision-making process of the model. SHAP not only enhances transparency but also facilitates feature selection, improving the model’s efficiency while maintaining high predictive power [ 8 ]. The integration of SHAP-aware modeling ensures that the system remains interpretable and trustworthy, making it suitable for clinical decision support and real-time COVID-19 screening. This study article is divided into four sections, the first of which provides an overview of the usage of AI approaches, the current state of COVID-19, and its effects. An important study in a related field of COVID-19 illness prediction based on the categorization of numerical and visual data is presented in the second section. Section three follows, in which the study methodology and the data and techniques utilized to produce the suggested method are presented. Section four presents a discussion of the results based on the various performance parameters, concluding with potential avenues for future research. 2. Related Work In the last couple of years, many researchers have continuously worked in the areas of ML for the early identification of COVID-19 at an early stage. Elaziz et al. [ 9 ] in their research introduced a machine learning approach for accurately diagnosing the disease using X-ray images, leveraging Fractional Multichannel Exponent Moments. The method demonstrated high performance, achieving accuracy rates of 96.09% and 98.09%, respectively. Brinati et al [ 10 ] designed classification models based on hematochemical values from routine blood tests from San Raffaele Hospital, Italy for 279 patients, out of which 177 tested positive. A three-way model was proposed comprising of random forest and decision tree for the identification of the disease. They were able to achieve accuracy between 82% and 86% with a sensitivity of 92 to 95%. Another research work was carried out by Barstugan et al [ 11 ] on abdominal computed tomography (CT) images. They have implemented different algorithms for feature extraction to increase classification performance. Further, the authors applied a support vector machine with 2-fold, 5-fold, and 10-fold cross-validation and the proposed method was able to achieve 99.68% accuracy. Today, one in four persons over the age of 25 will experience a stroke. Particularly this year, when a stroke was discovered in about 13.7 million people for the first time, the greatest number ever. According to a WHO report, there were 5.5 million fatalities out of 13.7 million. If nothing is done, it is predicted that there will be 6.7 million fatalities annually. The increased death rate from strokes will be significantly influenced by the COVID-19 pandemic situation. Even adults and patients with moderate risk factors are now more likely than ever to get a stroke. Premisha et al. (2022) created an ensemble model by merging the different classifiers that each performed well on their own to predict the impact level of stroke. The dataset includes information on 5110 patients as well as 12 variables that were examined in this study. Their model had an accuracy of 95.76% [ 12 ]. Federico et al [ 13 ] performed research on the hematochemical values of 1624 patients, the data of whom were collected from San Raphel Hospital (OSR). Five different ML models have been implemented on the dataset and the performance of each was evaluated. Random forest outperformed all other techniques and achieved a higher accuracy of 93%. Further, they have implemented the same techniques on two other datasets CBC dataset and the COVID-specific dataset where KNN outshines all other techniques. Oleviera et al [ 14 ] implemented various ML techniques for identifying COVID-19 suspected patients. They also proposed another model for classifying hospitalized patients with COVID-19. The suggested models achieved a high accuracy of more than 96%. A framework consisting of a pipelined image preprocessing method was proposed by Olaide et al [ 15 ] for the detection of coronavirus infection. They implemented the model on an X-ray dataset obtained from the National Institute of Health (NIH) and also used the COVID-19 radiography dataset. Their proposed model was able to achieve an accuracy of 0.1 with 0.85 and 0.9 precision and F-measure respectively. Breast cancer is among the most dangerous diseases and stands as a primary cause of mortality in women aged 40 to 55. To support accurate classification, there is a need for developing computer-aided diagnostic systems. A recent study utilized the Wisconsin Diagnostic Breast Cancer (WDBC) dataset for breast cancer detection and identified the random forest algorithm, an ensemble learning technique, as one of the most effective classifiers. Additionally, we discovered that the random forest with recursive feature elimination (RFE) is more effective at classifying breast cancer than XGBoost and LightGBM, two other ensemble learning techniques (LGBM). The RFE is a technique for choosing features. However, there was no comparison with the principal component analysis's feature extraction in the trials by Ono et al. (2022). (PCA). This study uses the WDBC dataset to give an evaluation of feature extraction techniques with ensemble learning for breast cancer classification [ 16 ]. Xie et al. [ 17 ]analyzed the chest CT findings and RT-PCR reports of the 167 patients and analyzed that a combination of both reports is a much more efficient way of detecting COVID-19. Gomes and Oliveira [ 18 ] in their research developed a tool for analyzing epidemiological data for predicting the Covid-19 dynamic spread. They have used a machine-learning approach with the integration of a Kalman filter for adaptive tracking. Ahmed and Zeinab [ 19 ] proposed a model COVIDetection-Net using a chest radiography images dataset with 1200 images. They used a Multiclass support vector machine for classification. Their model was able to achieve accuracy of 100%, 99.72%, and 94.44% for all three different pairs of classes. Raihan et al. [ 20 ] in their research proposed a method to detect chronic kidney disease. They have used XGBoost ML classifier for the prediction of the disease. The dataset obtained from UCI contains 24 attributes and 400 records for both CKD and non-CKD pa tients. The significant features have been extracted using the Biogeography Based Optimization algorithm. They were able to achieve an accuracy of 99.16% using the full dataset and 98.33% using the reduced dataset. The study proposed by Wang et al [ 21 ] utilized XAI techniques to extract significant biomarkers for the successful detection of Erythemato-Squamous disease. The dataset was taken from the UCI machine repository with 34 attributes and 366 instances. The authors have implemented the CatBoost classifier for the detection of the disease and were able to achieve an accuracy of 99.07% with an F1-score of 98.97%. 3. Materials and Methods 3.1 Data Description For the experimental purpose the dataset entitled “COVID-19 symptoms and Presence” publicly available from Kaggle has been used. The dataset contains 20 attributes as shown in Table 1. Fig 1 shows some of the major symptoms of COVID-19 extracted from the literature. It is evident from the figure that breathing, fever, dry cough, and sore throat are among the major factors that affect the presence or absence of COVID-19 [22]. Table 1 : Attribute Description of the COVID-19 dataset The dimensionality of the dataset has been reduced by using a correlation-based feature subset evaluation method along with the PSO search method. 3.2 Methodology 3.2.1 Proposed Model For experimental purposes, the data has been taken from a public library Kaggle, and preprocessing of the data has been carried out. During the pre-processing phase, it has been observed that classes in the dataset under study have an imbalance of 4:1. To balance the dataset the Synthetic minority oversampling technique (SMOTE) has been applied. This method generates synthetic samples for the minority class by creating interpolations between existing instances within that class. To improve the performance of the classifier one needs to perform both oversampling as well as under-sampling of the majority of samples. The random under-sampling and over-sampling techniques have been applied for the selection of random majority samples and deleting them from the training dataset. After performing the under-sampling and over-sampling methods the updated balanced dataset contains 2102 records for positive COVID patients and 2102 for negative COVID records. Various models were then created on the updated dataset using various machine learning algorithms (Multi-layered Perceptron, Naïve Bayes, Random Forest, and Decision Tree) and their performance was evaluated. The proposed model shown in Fig 2, with random forest optimized with XGBoost, is then implemented on the same dataset and the performance of the model was evaluated and compared. The proposed method is explained in Table 2. Although random forest is considered a simpler technique as compared to gradient boosting, gradient boosting is preferred because of its performance. In this proposed model, we have used XGBoost Random Forest (XGBRF) instead of the normal gradient boosting technique as XGBoost handles the speed issues (training a model) of gradient boosting. XGBoost provides an effective execution of gradient boosting which is effective in training random forest ensembles [23] [24]. It also helps in handling sparse data and the issues related to regularization to reduce overfitting and improve the overall performance of the model. The basic idea behind XGBRF is to use XGBoost to build a strong model by combining the strengths of both XGBoost and Random Forest. To use XGBoost as a booster for Random Forest, the training process of the Random Forest is modified to use XGBoost models instead of decision trees. XGBRF involves optimizing the loss function by adjusting the weights of the XGBoost models and combining their predictions to make the final prediction. After each iteration of the boosting process, the predictions of the XGBoost models are combined to form a final prediction. This process is repeated until a satisfactory level of performance is achieved. The final prediction made by XGBRF is a weighted combination of the predictions made by the XGBoost models, and it is given by: Where m represents the number of XGBoost models, a_j is the weight assigned to the jth model, and f_j(x) is the prediction made by the jth model for the example x. For the experimental purpose, the dataset was divided in a ratio of 70:30, and models were compared. 4. Results The dataset has been implemented on different machine learning algorithms and a contingency table is produced to show the performance of the models. Table 3 shows the accuracy achieved by different techniques on the reduced dataset. Table 3 Comparative analysis of accuracy values of different techniques S.no Machine Learning Model Accuracy (%) 1. Multilayer Perceptron 94.06 2. Naïve Bayes 94.65 3. Random Forest 94.68 4. Decision Tree 94.7 5. Proposed Ensemble Method 96.7 Figure 3 shows the bar graph of accuracy achieved by the machine learning algorithm and Fig. 4 shows the average accuracy achieved by the proposed method. Table 4 Performance measures using Machine learning algorithms on COVID Dataset. Machine Learning Algorithms Correlation coefficient MAE RMSE RAE RSE Decision Tree 0.947 0.0316 0.1259 10.1875 32.1233 Random Forest 0.9468 0.0321 0.1261 10.3478 32.1692 MLP 0.9406 0.0455 0.1353 14.6427 34.5226 Naïve Bayes 0.9465 0.0344 0.1265 11.0829 32.2806 Proposed Method 0.9670 0.0559 0.1624 15.672 38.6734 Comparing Multilayer Perceptron to other classifiers, its accuracy of 94.06% is poor. The results show that Naïve Bayes obtained 94.65% accuracy, Random Forest achieved 94.68% accuracy, Decision tree achieved 94.7%), and the suggested technique achieved the greatest accuracy of 96.7%. Table 4 displays the the results of performance measures for different ML techniques implemented on the dataset. The comparison study of the classification algorithms is shown in Figs. 5 and 6 , which take the shape of a bar graph. 5. Model Interpretation using SHAP In the above section, we have observed that the proposed ensemble method outshines all the other methods applied to the same dataset. But it is also critical to understand why the model is making certain predictions, only achieving accuracy is not enough. Mostly the ML algorithms operate as “black boxes” making it difficult to interpret their decision process. To overcome this black-box nature of ML algorithms, XAI plays an important role by bringing transparency and accountability to AI systems, which helps in validating model behavior ensures trust, and helps in ethical model deployment. To interpret the proposed model, SHAP is applied which explains the contribution of each feature in the predictions. It is a unified framework based on game theory and provides local as well as global interpretability. To understand the model’s behaviour we implemented SHAP summary plot as shown in Fig. 7, which shows the importance or contribution of each feature ranked by mean absolute SHAP value. The summary plot in Fig. 7 shows the most influential features including attending large gatherings, abroad travel, and breathing problems. Features are listed vertically as per their importance and those near the top have more impact on model output. Here the positive SHAP value means that the feature pushes the prediction towards a positive class means COVID positive and the negative values shift the prediction to a negative class i.e. COVID-negative. The red color indicates the high feature value whereas the blue color indicates the low feature value. For example, in the case of features like attending large gatherings and abroad travel, we can see that there are more red points on the right side which indicates that these feature increases the likelihood of positive COVID prediction. Based on this Summary plot, we can categorize the features as shown in Table 5 as high-impact and low-impact features. Table 5 High and low-value features High Value Low Value Attended Large Gathering Hyper Tension Abroad travel Asthma Breathing Problem Visited Public Exposed Places Sore throat Dry Cough Fever Contact with COVID Patient We have also plotted a SHAP force plot for local interpretation for a single instance or say for individual data points. As shown in Fig. 8 , the model’s base value is increased to 2.04 because of the high-impact features like attending large gatherings, Abroad Travel, and Contact with COVID Patients whereas on the other side, the features like Fever, Dry Cough, and Breathing Problems decreased the prediction. 6. Discussion and Conclusion The paper presents an optimized ensemble learning approach combining XGBoost with Random Forest for the early detection of COVID-19 using clinical and demographic data. The proposed model makes use of significant features for the study by employing Particle Swarm Optimization (PSO) for feature selection and SMOTE for handling data imbalance. The hybrid model shows a performance boost by achieving 96.7% accuracy and outperformed other baseline models such as MLP (94.06%), Naïve Bayes (94.65%), RF (94.68%), and Decision Tree (94.7%). The performance of the proposed model makes it a viable candidate to be implemented in rural and low-resource settings. Further, the model is integrated with Explainable AI (XAI) through SHAP, to address the black-box nature of ensemble models. The SHAP summary plot helped in identifying the high and low-value features, and the force plot showed how individual data points affect the prediction score. These findings enhanced trust and transparency which is crucial in the medical field where predictions need justifications. 7. Methods Multilayered Perceptron Multilayered Perceptron (MLP) is a fully connected neural network with backpropagation that can interact using weighted connections. MLP contains one layer of both input and out neurons and a few hidden layers which contain an arbitrary number of neurons to process weighted sum and then bring the outcome to the next layer. The input layer receives the data and then passes it to the first hidden layer, which processes the data using a non-linear activation function. The output of each layer is passed to the next hidden layer until it reaches the final output layer, which can be a predicted class label or a continuous value [ 25 ] Naïve Bayes: The Naïve Bayes algorithm because of its high computational efficiency, ability to express probability, and strong independent assumption makes it one of the most successful methods for classification. It comes under the category of probabilistic classifier and is based on applying Bayes theorem for solving complex classification problems. \(\:P\left(E|F\right)=\:\frac{P\left(F|E\right)P\left(e\right)}{P\left(F\right)}\) ------------- (2) The Bayes formula can also be written by applying the values of B in Eq. (3). \(\:P\left(E|f1,f2,\dots\:fn\right)=\:\frac{P\left(E\right)P(f1,f2,\dots\:fn|E)}{P(f1,f2,\dots\:,fn)}\) -------- (3) It works on the principle that the existence of one attribute is independent of the existence of other features [ 26 ]. Random Forest Random Forest is one of the most commonly used algorithms for data classification. It is a collection of multiple individual decision trees (DT), where each decision tree in the ensemble is comprised of a dataset from the training data and outputs a prediction value and the most frequent class (maximum support or vote) is declared as classification decision. The multiple decision trees are created using a predetermined probability of selecting relevant attributes [ 27 ]. Decision Tree A supervised learning method that is widely used for both classification and regression problems as it can mimic human thinking. A decision tree is a flowchart-like tree structure that makes decisions based on the set of rules provided. In a decision tree, a test on an attribute is denoted by an internal node which represents features of the proposed dataset, the decision rules are represented by different branches and finally, the outcome in the form of class labels is denoted by leaf nodes. In the hierarchical structure of a tree, a root node is the starting point [ 28 ]. Declarations Author Declarations Ethics approval It is important to note that all procedures utilized in studies involving human participants were performed in accordance with the ethical principles of the institutional and/or national research committees, as well as with the 1964 Helsinki Declaration and its subsequent amendments or equivalent ethical principles. This article does not contain any studies with animals performed by any of the authors. Competing Interest The authors state that they have no known competing interests or personal con-nections that might have influenced the research presented in this publication. Consent statement Informed consent was obtained from all participants. Approval statement All experimental protocols were approved by Manipal University Jaipur, India Consent to participate We voluntarily agree to take part in this study. Consent for publication All people who were included in the research have given their written consent for their data to be published. Funding Funding is provided by Manipal University Jaipur, India Author contribution Varun Sapra, Ankit Vishnoi, Neelu Jyoti Ahuja, Luxmi Sapra,: Conceptual frameworks, Methodology, Writing-original version, writing-review, and editing. Parul Madan, Preeti Narooka: supervision, writing-review and editing. Data Availability The dataset is publicly available at Kaggle. Following is the URL for the dataset https://www.kaggle.com/datasets/hemanthhari/symptoms-and-covid-presence?resource=download References M. Ghaderzadeh and A. Farkhondeh , "Deep learning in the detection and diagnosis of COVID-19 using radiology modalities: a systematic review," Journal of Healthcare Engineering, 2021. Chen et al, "Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study," The lancet, vol. 395, pp. 507-513, 2020. e. a. Samsami, "Clinical and demographic characteristics of patients with COVID-19 infection: statistics from a single hospital in Iran," Human Antibodies, vol. 29, pp. 49-54, 2020. T. L. Dao, V. T. Hoang and P. Gautret, "Recurrence of SARS-CoV-2 viral RNA in recovered COVID-19 patients: a narrative review," European Journal of Clinical Microbiology & Infectious Diseases, vol. 40, pp. 13-25, 2021. M. e. a. Yang, "Development and evaluation of a rapid and sensitive EBOV-RPA test for rapid diagnosis of Ebola virus disease," Scientific reports, vol. 6, pp. 1-7, 2016. T. S. E. A. B. J. &. H. C. Jefferson, "Viral cultures for COVID-19 infectivity assessment-a systematic review," MedRxiv, vol. 8, 2020. N. Chaitali, "Evaluation of the Indian TrueNAT micro RT-PCR device with GeneXpert for case detection of pulmonary tuberculosis," International journal of mycobacteriology, vol. 3, pp. 205-210, 2014. V. Sapra and L. Sapra, "An Interpretable Approach with Explainable AI for the Detection of Cardiovascular Disease," in International Conference on Integrated Intelligence and Communication , 2024. M. A. e. a. Elaziz, "New machine learning method for image-based diagnosis of COVID-19," PLoS ONE, vol. 15, 2020. D. A. C. D. F. M. L. G. B. a. F. C. Brinati, "Detection of COVID-19 infection from routine blood exams with machine learning: a feasibility study.," Journal of medical systems, vol. 44, no. 8, pp. 1-12, 2020. M. Barstugan, O. Umut and O. aban , "Coronavirus (covid-19) classification using ct images by machine learning methods," arXiv preprint arXiv:2003, 2020. S. P. M. K. a. K. B. P. Premisha, "An Ensemble Machine Learning Approach for Stroke Prediction," in International Research Conference on Smart Computing and Systems Engineering , Colombo, 2022. F. e. a. Cabitza, "Development, evaluation, and validation of machine learning models for COVID-19 detection based on routine blood tests," Clinical Chemistry and Laboratory Medicine , vol. 59, no. 2, pp. 421-431, 2021. d. O. e. a. "Machine learning applied in SARS-CoV-2 COVID 19 screening using clinical analysis parameters," IEEE Latin America Transactions, vol. 19, no. 6, pp. 978-985, 2021. O. N. Oyelade, "CovFrameNet: An Enhanced Deep Learning framework for COVID-19 detection," IEEE Access, 2021. Y. O. a. Y. Mitani, "Evaluation of feature extraction methods with ensemble learning for breast cancer classification," in IEEE 4th Global Conference on Life Sciences and Technologies (LifeTech), Osaka Japan, 2022. e. a. Xie Xingzhi, "Chest CT for typical coronavirus disease 2019 (COVID-19) pneumonia: relationship to negative RT-PCR testing," Radiology, vol. 296, no. 2, pp. E41-E45, 2020. D. C. d. S. Gomes and de Oliveira Serra, "Machine Learning Model for Computational Tracking and Forecasting the COVID-19 Dynamic Propagation," IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, vol. 25, no. 3, pp. 615-622, 2021. A. S. Elkorany and Z. F. E. , "COVIDetection-Net: A tailored COVID-19 detection from chest radiography images using deep learning," Optik , vol. 231, 2021. M. J. Raihan, M. A. Khan, S. H. Kee and A. A. Nahid, Detection of the chronic kidney disease using XGBoost classifier and explaining the influence of the attributes on the model using SHAP, Scientific Reports, 2023. W. e. al., "Identifying diagnostic biomarkers for erythemato-squamous diseases using explainable machine learning," Biomedical Signal Processing and Control, vol. 100, 2025. J. R. e. a. Larsen, "Modeling the Onset of Symptoms of COVID-19.," Frontiers in public health, vol. 8, 2020. S. K. &. W. Z. Kiangala, "An effective adaptive customization framework for small manufacturing plants using extreme gradient boosting-XGBoost and random forest ensemble learning algorithms in an Industry 4.0 environment.," Machine Learning with Applications, vol. 4, p. 100024, 2021. E. K. Sahin, "Assessing the predictive capability of ensemble tree methods for landslide susceptibility mapping using XGBoost, gradient boosting machine, and random forest," SN Applied Sciences, vol. 2, no. 7, p. 1308, 2020. V. Sapra and M. L. Saini, "Computational intelligence for detection of coronary artery disease with optimized features," International Journal of Innovative Technology and Exploring Engineering, vol. 8, no. 6C, pp. 144 - 148, 2019. S. Jayachitra and A. Prasanth, "Multi-feature analysis for automated brain stroke classification using weighted Gaussian naïve Bayes classifier.," Journal of Circuits, Systems and Computers , vol. 30, no. 10, p. 178, 2021. V. Jackins, V. S, M. Kaliappan and M. Lee, "AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes," The Journal of Supercomputing, vol. 77, no. 5, pp. 5198-5219, 2021. B. Charbuty and A. Abdulazeez, "Classification based on decision tree algorithm for machine learning," Journal of Applied Science and Technology Trends, vol. 2, no. 01, pp. 20-28, 2021. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6769397","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":471921651,"identity":"8b562bb4-c039-4d9f-8d0e-2907bafa5a35","order_by":0,"name":"Varun Sapra","email":"","orcid":"","institution":"University of Petroleum and Energy Studies","correspondingAuthor":false,"prefix":"","firstName":"Varun","middleName":"","lastName":"Sapra","suffix":""},{"id":471921652,"identity":"381e0b80-a9d3-4572-8956-7d601a7647c8","order_by":1,"name":"Ankit Vishnoi","email":"","orcid":"","institution":"Graphic Era Deemed to be University","correspondingAuthor":false,"prefix":"","firstName":"Ankit","middleName":"","lastName":"Vishnoi","suffix":""},{"id":471921653,"identity":"b437035d-e19d-405d-a659-a45b201231ca","order_by":2,"name":"Neelu Jyoti Ahuja","email":"","orcid":"","institution":"University of Petroleum and Energy Studies","correspondingAuthor":false,"prefix":"","firstName":"Neelu","middleName":"Jyoti","lastName":"Ahuja","suffix":""},{"id":471921654,"identity":"844f7f74-62c0-4f1f-a70c-824eb7c7d4d5","order_by":3,"name":"Luxmi Sapra","email":"","orcid":"","institution":"Graphic Era Hill University","correspondingAuthor":false,"prefix":"","firstName":"Luxmi","middleName":"","lastName":"Sapra","suffix":""},{"id":471921655,"identity":"96f0a638-7987-4465-b90e-8b85d2ca02d9","order_by":4,"name":"Parul Madan","email":"","orcid":"","institution":"Graphic Era Deemed to be University","correspondingAuthor":false,"prefix":"","firstName":"Parul","middleName":"","lastName":"Madan","suffix":""},{"id":471921656,"identity":"96384828-482f-4e9f-b26e-5c1c7cb2c202","order_by":5,"name":"Preeti Narooka","email":"data:image/png;base64,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","orcid":"","institution":"Manipal University Jaipur","correspondingAuthor":true,"prefix":"","firstName":"Preeti","middleName":"","lastName":"Narooka","suffix":""}],"badges":[],"createdAt":"2025-05-28 15:08:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6769397/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6769397/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":84874465,"identity":"72dbd5ec-b515-4c80-97fa-d08f8022fb25","added_by":"auto","created_at":"2025-06-18 09:26:57","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":50168,"visible":true,"origin":"","legend":"\u003cp\u003eMajor Symptoms for COVID-19\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-6769397/v1/68bb94f4bb72129d0cbd9ccc.png"},{"id":84874462,"identity":"2279e843-3df8-45c4-8e23-7336c404db5c","added_by":"auto","created_at":"2025-06-18 09:26:57","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":172914,"visible":true,"origin":"","legend":"\u003cp\u003eProposed Model\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-6769397/v1/7af8d7f2b3b68a7e6f23171a.png"},{"id":84874848,"identity":"e4d32a04-6bda-4e95-a4db-51f2205a4ad5","added_by":"auto","created_at":"2025-06-18 09:34:57","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":13599,"visible":true,"origin":"","legend":"\u003cp\u003eAccuracy achieved by classifiers.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-6769397/v1/a3f685c53affa1fa59a298c7.png"},{"id":84874851,"identity":"b9276bce-4f17-415d-8784-c3cb9041723a","added_by":"auto","created_at":"2025-06-18 09:34:57","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":69156,"visible":true,"origin":"","legend":"\u003cp\u003eAccuracy of the proposed method\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-6769397/v1/db982d40e8645336c641955e.png"},{"id":84874852,"identity":"0e5c866f-e7bb-4b5e-ba95-7b0e83971d9c","added_by":"auto","created_at":"2025-06-18 09:34:57","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":13935,"visible":true,"origin":"","legend":"\u003cp\u003eComparative analysis of Correlation coefficient, MAE, RMSE of DT, RF, MLP, NB\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-6769397/v1/86c9adf8ffa03456fdb3ec3b.png"},{"id":84875681,"identity":"95bc8742-cea6-4483-811d-ab8ebbb257fe","added_by":"auto","created_at":"2025-06-18 09:42:57","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":11853,"visible":true,"origin":"","legend":"\u003cp\u003eComparative analysis of RAE and Root RSE of DT, RF, MLP, NB\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-6769397/v1/13ba6dd67a77756dc30172f2.png"},{"id":84874471,"identity":"6588d791-ebea-4ae2-8512-a274bde156af","added_by":"auto","created_at":"2025-06-18 09:26:57","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":142857,"visible":true,"origin":"","legend":"\u003cp\u003eSHAP Summary Plot\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-6769397/v1/19b40ab2eb9c5c6f28bfd867.png"},{"id":84874475,"identity":"34708019-d93c-4ac7-95f9-d5f8a961fe5e","added_by":"auto","created_at":"2025-06-18 09:26:57","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":44051,"visible":true,"origin":"","legend":"\u003cp\u003eSHAP force plot\u003c/p\u003e","description":"","filename":"8.png","url":"https://assets-eu.researchsquare.com/files/rs-6769397/v1/da41015eb1815af9a6a7367e.png"},{"id":90798692,"identity":"de90a769-340d-46da-9d72-eb1205b3732f","added_by":"auto","created_at":"2025-09-08 09:39:18","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1224698,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6769397/v1/ef586202-a686-4665-904b-c495cfc68932.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"SHAP-Driven Ensemble Learning for Explainable COVID-19 Detection","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eThe COVID-19 pandemic has had a global impact, influencing not only public health but also hindering the productivity and developmental progress of nations. The rapid spread of the disease led to severe consequences worldwide and was declared a global pandemic by the WHO [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e] [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. The major symptoms found in the suspects of COVID-19 were flu-like symptoms that include fatigue, headache, dry cough, fever, and, respiratory problems [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Early diagnosis is critical in controlling the disease and ensuring timely medical intervention.\u003c/p\u003e \u003cp\u003eWith the advancements in technology and prices plummeting medical sector is increasingly adopting automated processes, leading to vast data generation. COVID-19 diagnosis primarily relies on reverse transcription-polymerase chain reaction (RT-PCR) tests, which are considered the gold standard [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. The RT-PCR test requires a sophisticated lab and well-trained medical practitioners to carry out the tests which makes the test less accessible in resource-limited settings. At the testing centers, the swab samples from suspected patients are collected and referred to the laboratories for the final diagnosis. The test can take anything from a few hours to a couple of days to get results [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. The prolonged stay at the collection centers with the suspected victims of COVID-19 also increases the exposure risk of COVID-19. RT-PCR tests can also yield false negative results due to improper sample collection, or if the viral load is low [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. This can lead to misdiagnoses and potential disease spread. Considering the situation, the need for a non-invasive and interpretable AI-driven diagnostics test based on clinical symptoms is required so that one can compute the results in real time, particularly in rural and underserved areas where access to sophisticated labs is limited. The system can be used to diagnose the disease and can refer the highly suspected victims for further medical examination [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. Such systems will help in reducing the mortality rate in rural areas due to COVID-19.\u003c/p\u003e \u003cp\u003eTo address this challenge, this paper proposes a SHAP-aware ensemble learning model for COVID-19 detection. The proposed model integrates Random Forest and XGBoost, leveraging the strengths of both methods to enhance predictive performance. Ensemble learning techniques improve accuracy by combining multiple classifiers, but they often function as \"black-box\" models, lacking interpretability. To overcome this limitation, we incorporate \u0026lsquo;SHapley Additive exPlanations\u0026rsquo; (SHAP), an advanced explainability technique that assigns important scores to each feature, thereby providing insights into the decision-making process of the model. SHAP not only enhances transparency but also facilitates feature selection, improving the model\u0026rsquo;s efficiency while maintaining high predictive power [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. The integration of SHAP-aware modeling ensures that the system remains interpretable and trustworthy, making it suitable for clinical decision support and real-time COVID-19 screening.\u003c/p\u003e \u003cp\u003eThis study article is divided into four sections, the first of which provides an overview of the usage of AI approaches, the current state of COVID-19, and its effects. An important study in a related field of COVID-19 illness prediction based on the categorization of numerical and visual data is presented in the second section. Section three follows, in which the study methodology and the data and techniques utilized to produce the suggested method are presented. Section four presents a discussion of the results based on the various performance parameters, concluding with potential avenues for future research.\u003c/p\u003e"},{"header":"2. Related Work","content":"\u003cp\u003eIn the last couple of years, many researchers have continuously worked in the areas of ML for the early identification of COVID-19 at an early stage. Elaziz et al. [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e] in their research introduced a machine learning approach for accurately diagnosing the disease using X-ray images, leveraging Fractional Multichannel Exponent Moments. The method demonstrated high performance, achieving accuracy rates of 96.09% and 98.09%, respectively.\u003c/p\u003e \u003cp\u003eBrinati et al [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e] designed classification models based on hematochemical values from routine blood tests from San Raffaele Hospital, Italy for 279 patients, out of which 177 tested positive. A three-way model was proposed comprising of random forest and decision tree for the identification of the disease. They were able to achieve accuracy between 82% and 86% with a sensitivity of 92 to 95%.\u003c/p\u003e \u003cp\u003eAnother research work was carried out by Barstugan et al [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e] on abdominal computed tomography (CT) images. They have implemented different algorithms for feature extraction to increase classification performance. Further, the authors applied a support vector machine with 2-fold, 5-fold, and 10-fold cross-validation and the proposed method was able to achieve 99.68% accuracy.\u003c/p\u003e \u003cp\u003eToday, one in four persons over the age of 25 will experience a stroke. Particularly this year, when a stroke was discovered in about 13.7\u0026nbsp;million people for the first time, the greatest number ever. According to a WHO report, there were 5.5\u0026nbsp;million fatalities out of 13.7\u0026nbsp;million. If nothing is done, it is predicted that there will be 6.7\u0026nbsp;million fatalities annually. The increased death rate from strokes will be significantly influenced by the COVID-19 pandemic situation. Even adults and patients with moderate risk factors are now more likely than ever to get a stroke. Premisha et al. (2022) created an ensemble model by merging the different classifiers that each performed well on their own to predict the impact level of stroke. The dataset includes information on 5110 patients as well as 12 variables that were examined in this study. Their model had an accuracy of 95.76% [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eFederico et al [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e] performed research on the hematochemical values of 1624 patients, the data of whom were collected from San Raphel Hospital (OSR). Five different ML models have been implemented on the dataset and the performance of each was evaluated. Random forest outperformed all other techniques and achieved a higher accuracy of 93%. Further, they have implemented the same techniques on two other datasets CBC dataset and the COVID-specific dataset where KNN outshines all other techniques.\u003c/p\u003e \u003cp\u003eOleviera et al [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e] implemented various ML techniques for identifying COVID-19 suspected patients. They also proposed another model for classifying hospitalized patients with COVID-19. The suggested models achieved a high accuracy of more than 96%.\u003c/p\u003e \u003cp\u003eA framework consisting of a pipelined image preprocessing method was proposed by Olaide et al [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e] for the detection of coronavirus infection. They implemented the model on an X-ray dataset obtained from the National Institute of Health (NIH) and also used the COVID-19 radiography dataset. Their proposed model was able to achieve an accuracy of 0.1 with 0.85 and 0.9 precision and F-measure respectively.\u003c/p\u003e \u003cp\u003eBreast cancer is among the most dangerous diseases and stands as a primary cause of mortality in women aged 40 to 55. To support accurate classification, there is a need for developing computer-aided diagnostic systems. A recent study utilized the Wisconsin Diagnostic Breast Cancer (WDBC) dataset for breast cancer detection and identified the random forest algorithm, an ensemble learning technique, as one of the most effective classifiers. Additionally, we discovered that the random forest with recursive feature elimination (RFE) is more effective at classifying breast cancer than XGBoost and LightGBM, two other ensemble learning techniques (LGBM). The RFE is a technique for choosing features. However, there was no comparison with the principal component analysis's feature extraction in the trials by Ono et al. (2022). (PCA). This study uses the WDBC dataset to give an evaluation of feature extraction techniques with ensemble learning for breast cancer classification [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eXie et al. [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]analyzed the chest CT findings and RT-PCR reports of the 167 patients and analyzed that a combination of both reports is a much more efficient way of detecting COVID-19.\u003c/p\u003e \u003cp\u003eGomes and Oliveira [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e] in their research developed a tool for analyzing epidemiological data for predicting the Covid-19 dynamic spread. They have used a machine-learning approach with the integration of a Kalman filter for adaptive tracking.\u003c/p\u003e \u003cp\u003eAhmed and Zeinab [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e] proposed a model COVIDetection-Net using a chest radiography images dataset with 1200 images. They used a Multiclass support vector machine for classification. Their model was able to achieve accuracy of 100%, 99.72%, and 94.44% for all three different pairs of classes.\u003c/p\u003e \u003cp\u003eRaihan et al. [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e] in their research proposed a method to detect chronic kidney disease. They have used XGBoost ML classifier for the prediction of the disease. The dataset obtained from UCI contains 24 attributes and 400 records for both CKD and non-CKD pa tients. The significant features have been extracted using the Biogeography Based Optimization algorithm. They were able to achieve an accuracy of 99.16% using the full dataset and 98.33% using the reduced dataset.\u003c/p\u003e \u003cp\u003eThe study proposed by Wang et al [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e] utilized XAI techniques to extract significant biomarkers for the successful detection of Erythemato-Squamous disease. The dataset was taken from the UCI machine repository with 34 attributes and 366 instances. The authors have implemented the CatBoost classifier for the detection of the disease and were able to achieve an accuracy of 99.07% with an F1-score of 98.97%.\u003c/p\u003e"},{"header":"3. Materials and Methods","content":"\u003cp\u003e\u003cstrong\u003e3.1 Data Description\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eFor the experimental purpose the dataset entitled \u0026ldquo;COVID-19 symptoms and Presence\u0026rdquo; publicly available from Kaggle has been used. The dataset contains 20 attributes as shown in Table 1.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eFig 1 shows some of the major symptoms of COVID-19 extracted from the literature. It is evident from the figure that breathing, fever, dry cough, and sore throat are among the major factors that affect the presence or absence of COVID-19 [22].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 1\u003c/strong\u003e: Attribute Description of the COVID-19 dataset\u003c/p\u003e\n\u003cp\u003e\u003cimg src=\"data:image/png;base64,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\" width=\"538\" height=\"766\"\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003eThe dimensionality of the dataset has been reduced by using a correlation-based feature subset evaluation method along with the PSO search method.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.2 Methodology\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e3.2.1 Proposed Model\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eFor experimental purposes, the data has been taken from a public library Kaggle, and preprocessing of the data has been carried out. During the pre-processing phase, it has been observed that classes in the dataset under study have an imbalance of 4:1. To balance the dataset the Synthetic minority oversampling technique (SMOTE) has been applied. This method generates synthetic samples for the minority class by creating interpolations between existing instances within that class.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTo improve the performance of the classifier one needs to perform both oversampling as well as under-sampling of the majority of samples. The random under-sampling and over-sampling techniques have been applied for the selection of random majority samples and deleting them from the training dataset. After performing the under-sampling and over-sampling methods the updated balanced dataset contains 2102 records for positive COVID patients and 2102 for negative COVID records. Various models were then created on the updated dataset using various machine learning algorithms (Multi-layered Perceptron, Na\u0026iuml;ve Bayes, Random Forest, and Decision Tree) and their performance was evaluated.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe proposed model shown in Fig 2, with random forest optimized with XGBoost, is then implemented on the same dataset and the performance of the model was evaluated and compared. The proposed method is explained in Table 2.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cimg src=\"data:image/png;base64,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\" style=\"width: 855px; height: 621.736px;\" width=\"855\" height=\"621.736\"\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003eAlthough random forest is considered a simpler technique as compared to gradient boosting, gradient boosting is preferred because of its performance. In this proposed model, we have used XGBoost Random Forest (XGBRF) instead of the normal gradient boosting technique as XGBoost handles the speed issues (training a model) of gradient boosting. XGBoost provides an effective execution of gradient boosting which is effective in training random forest ensembles [23] [24]. It also helps in handling sparse data and the issues related to regularization to reduce overfitting and improve the overall performance of the model.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe basic idea behind XGBRF is to use XGBoost to build a strong model by combining the strengths of both XGBoost and Random Forest. To use XGBoost as a booster for Random Forest, the training process of the Random Forest is modified to use XGBoost models instead of decision trees. XGBRF involves optimizing the loss function by adjusting the weights of the XGBoost models and combining their predictions to make the final prediction. After each iteration of the boosting process, the predictions of the XGBoost models are combined to form a final prediction. This process is repeated until a satisfactory level of performance is achieved.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe final prediction made by XGBRF is a weighted combination of the predictions made by the XGBoost models, and it is given by:\u003c/p\u003e\n\u003cp\u003e\u003cimg src=\"data:image/png;base64,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\" width=\"616\" height=\"34\"\u003e\u003c/p\u003e\n\u003cp\u003eWhere m represents the number of XGBoost models, a_j is the weight assigned to the jth model, and f_j(x) is the prediction made by the jth model for the example x.\u003c/p\u003e\n\u003cp\u003eFor the experimental purpose, the dataset was divided in a ratio of 70:30, and models were compared.\u003c/p\u003e"},{"header":"4. Results","content":"\u003cp\u003eThe dataset has been implemented on different machine learning algorithms and a contingency table is produced to show the performance of the models. Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows the accuracy achieved by different techniques on the reduced dataset.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eComparative analysis of accuracy values of different techniques\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eS.no\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMachine Learning Model\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAccuracy (%)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultilayer Perceptron\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e94.06\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNa\u0026iuml;ve Bayes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e94.65\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e3.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRandom Forest\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e94.68\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e4.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDecision Tree\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e94.7\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e5.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProposed Ensemble Method\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e96.7\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows the bar graph of accuracy achieved by the machine learning algorithm and Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e shows the average accuracy achieved by the proposed method.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePerformance measures using Machine learning algorithms on COVID Dataset.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMachine Learning Algorithms\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCorrelation coefficient\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMAE\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRMSE\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eRAE\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eRSE\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDecision Tree\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.947\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0316\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.1259\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e10.1875\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e32.1233\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRandom Forest\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.9468\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0321\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.1261\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e10.3478\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e32.1692\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMLP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.9406\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0455\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.1353\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e14.6427\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e34.5226\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNa\u0026iuml;ve Bayes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.9465\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0344\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.1265\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e11.0829\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e32.2806\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eProposed Method\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.9670\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0559\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.1624\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e15.672\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e38.6734\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eComparing Multilayer Perceptron to other classifiers, its accuracy of 94.06% is poor. The results show that Na\u0026iuml;ve Bayes obtained 94.65% accuracy, Random Forest achieved 94.68% accuracy, Decision tree achieved 94.7%), and the suggested technique achieved the greatest accuracy of 96.7%. Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e4\u003c/span\u003e displays the the results of performance measures for different ML techniques implemented on the dataset. The comparison study of the classification algorithms is shown in Figs.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e and \u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e, which take the shape of a bar graph.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"5. Model Interpretation using SHAP","content":"\u003cp\u003eIn the above section, we have observed that the proposed ensemble method outshines all the other methods applied to the same dataset. But it is also critical to understand why the model is making certain predictions, only achieving accuracy is not enough. Mostly the ML algorithms operate as \u0026ldquo;black boxes\u0026rdquo; making it difficult to interpret their decision process. To overcome this black-box nature of ML algorithms, XAI plays an important role by bringing transparency and accountability to AI systems, which helps in validating model behavior ensures trust, and helps in ethical model deployment.\u003c/p\u003e\n\u003cp\u003eTo interpret the proposed model, SHAP is applied which explains the contribution of each feature in the predictions. It is a unified framework based on game theory and provides local as well as global interpretability. To understand the model\u0026rsquo;s behaviour we implemented SHAP summary plot as shown in Fig. 7, which shows the importance or contribution of each feature ranked by mean absolute SHAP value.\u003c/p\u003e\n\u003cp\u003eThe summary plot in Fig.\u0026nbsp;7 shows the most influential features including attending large gatherings, abroad travel, and breathing problems. Features are listed vertically as per their importance and those near the top have more impact on model output. Here the positive SHAP value means that the feature pushes the prediction towards a positive class means COVID positive and the negative values shift the prediction to a negative class i.e. COVID-negative. The red color indicates the high feature value whereas the blue color indicates the low feature value. For example, in the case of features like attending large gatherings and abroad travel, we can see that there are more red points on the right side which indicates that these feature increases the likelihood of positive COVID prediction.\u003c/p\u003e\n\u003cp\u003eBased on this Summary plot, we can categorize the features as shown in Table \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e as high-impact and low-impact features.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab4\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eHigh and low-value features\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"2\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eHigh Value\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eLow Value\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAttended Large Gathering\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHyper Tension\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAbroad travel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAsthma\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBreathing Problem\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eVisited Public Exposed Places\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSore throat\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDry Cough\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFever\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eContact with COVID Patient\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eWe have also plotted a SHAP force plot for local interpretation for a single instance or say for individual data points.\u003c/p\u003e\n\u003cp\u003eAs shown in Fig. \u003cspan class=\"InternalRef\"\u003e8\u003c/span\u003e, the model\u0026rsquo;s base value is increased to 2.04 because of the high-impact features like attending large gatherings, Abroad Travel, and Contact with COVID Patients whereas on the other side, the features like Fever, Dry Cough, and Breathing Problems decreased the prediction.\u003c/p\u003e"},{"header":"6. Discussion and Conclusion","content":"\u003cp\u003eThe paper presents an optimized ensemble learning approach combining XGBoost with Random Forest for the early detection of COVID-19 using clinical and demographic data. The proposed model makes use of significant features for the study by employing Particle Swarm Optimization (PSO) for feature selection and SMOTE for handling data imbalance. The hybrid model shows a performance boost by achieving 96.7% accuracy and outperformed other baseline models such as MLP (94.06%), Na\u0026iuml;ve Bayes (94.65%), RF (94.68%), and Decision Tree (94.7%). The performance of the proposed model makes it a viable candidate to be implemented in rural and low-resource settings.\u003c/p\u003e \u003cp\u003eFurther, the model is integrated with Explainable AI (XAI) through SHAP, to address the black-box nature of ensemble models. The SHAP summary plot helped in identifying the high and low-value features, and the force plot showed how individual data points affect the prediction score. These findings enhanced trust and transparency which is crucial in the medical field where predictions need justifications.\u003c/p\u003e"},{"header":"7. Methods","content":"\u003cp\u003e \u003cstrong\u003eMultilayered Perceptron\u003c/strong\u003e \u003cp\u003eMultilayered Perceptron (MLP) is a fully connected neural network with backpropagation that can interact using weighted connections. MLP contains one layer of both input and out neurons and a few hidden layers which contain an arbitrary number of neurons to process weighted sum and then bring the outcome to the next layer. The input layer receives the data and then passes it to the first hidden layer, which processes the data using a non-linear activation function. The output of each layer is passed to the next hidden layer until it reaches the final output layer, which can be a predicted class label or a continuous value [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cb\u003eNa\u0026iuml;ve Bayes: The\u003c/b\u003e Na\u0026iuml;ve Bayes algorithm because of its high computational efficiency, ability to express probability, and strong independent assumption makes it one of the most successful methods for classification. It comes under the category of probabilistic classifier and is based on applying Bayes theorem for solving complex classification problems.\u003c/p\u003e \u003cp\u003e \u003cspan class=\"InlineEquation\"\u003e \u003cspan class=\"mathinline\"\u003e\\(\\:P\\left(E|F\\right)=\\:\\frac{P\\left(F|E\\right)P\\left(e\\right)}{P\\left(F\\right)}\\)\u003c/span\u003e \u003c/span\u003e ------------- (2)\u003c/p\u003e \u003cp\u003eThe Bayes formula can also be written by applying the values of B in Eq.\u0026nbsp;(3).\u003c/p\u003e \u003cp\u003e \u003cspan class=\"InlineEquation\"\u003e \u003cspan class=\"mathinline\"\u003e\\(\\:P\\left(E|f1,f2,\\dots\\:fn\\right)=\\:\\frac{P\\left(E\\right)P(f1,f2,\\dots\\:fn|E)}{P(f1,f2,\\dots\\:,fn)}\\)\u003c/span\u003e \u003c/span\u003e -------- (3)\u003c/p\u003e \u003cp\u003eIt works on the principle that the existence of one attribute is independent of the existence of other features [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e].\u003c/p\u003e \u003cp\u003e \u003cstrong\u003eRandom Forest\u003c/strong\u003e \u003cp\u003eRandom Forest is one of the most commonly used algorithms for data classification. It is a collection of multiple individual decision trees (DT), where each decision tree in the ensemble is comprised of a dataset from the training data and outputs a prediction value and the most frequent class (maximum support or vote) is declared as classification decision. The multiple decision trees are created using a predetermined probability of selecting relevant attributes [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e].\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003eDecision Tree\u003c/strong\u003e \u003cp\u003eA supervised learning method that is widely used for both classification and regression problems as it can mimic human thinking. A decision tree is a flowchart-like tree structure that makes decisions based on the set of rules provided. In a decision tree, a test on an attribute is denoted by an internal node which represents features of the proposed dataset, the decision rules are represented by different branches and finally, the outcome in the form of class labels is denoted by leaf nodes. In the hierarchical structure of a tree, a root node is the starting point [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e].\u003c/p\u003e \u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAuthor Declarations\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003cem\u003eEthics approval\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eIt is important to note that all procedures utilized in studies involving human participants were performed in accordance with the ethical principles of the institutional and/or national research committees, as well as with the 1964 Helsinki Declaration and its subsequent amendments or equivalent ethical principles. This article does not contain any studies with animals performed by any of the authors.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eCompeting Interest\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eThe authors state that they have no known competing interests or personal con-nections that might have influenced the research presented in this publication.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eConsent statement\u0026nbsp;\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eInformed consent was obtained from all participants.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eApproval statement\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eAll experimental protocols were approved by Manipal University Jaipur, India\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eConsent to participate\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eWe voluntarily agree to take part in this study.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eConsent for publication\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eAll people who were included in the research have given their written consent\u003c/p\u003e\n\u003cp\u003efor their data to be published.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eFunding\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eFunding is provided by Manipal University Jaipur, India\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eAuthor contribution\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eVarun Sapra, Ankit Vishnoi, Neelu Jyoti Ahuja, Luxmi Sapra,: Conceptual frameworks, Methodology, Writing-original version, writing-review, and editing.\u003c/p\u003e\n\u003cp\u003eParul Madan, Preeti Narooka: supervision, writing-review and editing.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eData Availability\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eThe dataset is publicly available at Kaggle. Following is the URL for the dataset\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003ehttps://www.kaggle.com/datasets/hemanthhari/symptoms-and-covid-presence?resource=download\u003c/em\u003e\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eM. Ghaderzadeh and A. Farkhondeh , \u0026quot;Deep learning in the detection and diagnosis of COVID-19 using radiology modalities: a systematic review,\u0026quot; Journal of Healthcare Engineering, 2021. \u003c/li\u003e\n\u003cli\u003eChen et al, \u0026quot;Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study,\u0026quot; The lancet, vol. 395, pp. 507-513, 2020. \u003c/li\u003e\n\u003cli\u003ee. a. Samsami, \u0026quot;Clinical and demographic characteristics of patients with COVID-19 infection: statistics from a single hospital in Iran,\u0026quot; Human Antibodies, vol. 29, pp. 49-54, 2020. \u003c/li\u003e\n\u003cli\u003eT. L. Dao, V. T. Hoang and P. Gautret, \u0026quot;Recurrence of SARS-CoV-2 viral RNA in recovered COVID-19 patients: a narrative review,\u0026quot; European Journal of Clinical Microbiology \u0026amp; Infectious Diseases, vol. 40, pp. 13-25, 2021. \u003c/li\u003e\n\u003cli\u003eM. e. a. Yang, \u0026quot;Development and evaluation of a rapid and sensitive EBOV-RPA test for rapid diagnosis of Ebola virus disease,\u0026quot; Scientific reports, vol. 6, pp. 1-7, 2016. \u003c/li\u003e\n\u003cli\u003eT. S. E. A. B. J. \u0026amp;. H. C. Jefferson, \u0026quot;Viral cultures for COVID-19 infectivity assessment-a systematic review,\u0026quot; MedRxiv, vol. 8, 2020. \u003c/li\u003e\n\u003cli\u003eN. Chaitali, \u0026quot;Evaluation of the Indian TrueNAT micro RT-PCR device with GeneXpert for case detection of pulmonary tuberculosis,\u0026quot; International journal of mycobacteriology, vol. 3, pp. 205-210, 2014. \u003c/li\u003e\n\u003cli\u003eV. Sapra and L. Sapra, \u0026quot;An Interpretable Approach with Explainable AI for the Detection of Cardiovascular Disease,\u0026quot; in International Conference on Integrated Intelligence and Communication , 2024. \u003c/li\u003e\n\u003cli\u003eM. A. e. a. Elaziz, \u0026quot;New machine learning method for image-based diagnosis of COVID-19,\u0026quot; PLoS ONE, vol. 15, 2020. \u003c/li\u003e\n\u003cli\u003eD. A. C. D. F. M. L. G. B. a. F. C. Brinati, \u0026quot;Detection of COVID-19 infection from routine blood exams with machine learning: a feasibility study.,\u0026quot; Journal of medical systems, vol. 44, no. 8, pp. 1-12, 2020. \u003c/li\u003e\n\u003cli\u003eM. Barstugan, O. Umut and O. aban , \u0026quot;Coronavirus (covid-19) classification using ct images by machine learning methods,\u0026quot; arXiv preprint arXiv:2003, 2020. \u003c/li\u003e\n\u003cli\u003eS. P. M. K. a. K. B. P. Premisha, \u0026quot;An Ensemble Machine Learning Approach for Stroke Prediction,\u0026quot; in International Research Conference on Smart Computing and Systems Engineering , Colombo, 2022. \u003c/li\u003e\n\u003cli\u003eF. e. a. Cabitza, \u0026quot;Development, evaluation, and validation of machine learning models for COVID-19 detection based on routine blood tests,\u0026quot; Clinical Chemistry and Laboratory Medicine , vol. 59, no. 2, pp. 421-431, 2021. \u003c/li\u003e\n\u003cli\u003ed. O. e. a. \u0026quot;Machine learning applied in SARS-CoV-2 COVID 19 screening using clinical analysis parameters,\u0026quot; IEEE Latin America Transactions, vol. 19, no. 6, pp. 978-985, 2021. \u003c/li\u003e\n\u003cli\u003eO. N. Oyelade, \u0026quot;CovFrameNet: An Enhanced Deep Learning framework for COVID-19 detection,\u0026quot; IEEE Access, 2021. \u003c/li\u003e\n\u003cli\u003eY. O. a. Y. Mitani, \u0026quot;Evaluation of feature extraction methods with ensemble learning for breast cancer classification,\u0026quot; in IEEE 4th Global Conference on Life Sciences and Technologies (LifeTech), Osaka Japan, 2022. \u003c/li\u003e\n\u003cli\u003ee. a. Xie Xingzhi, \u0026quot;Chest CT for typical coronavirus disease 2019 (COVID-19) pneumonia: relationship to negative RT-PCR testing,\u0026quot; Radiology, vol. 296, no. 2, pp. E41-E45, 2020. \u003c/li\u003e\n\u003cli\u003eD. C. d. S. Gomes and de Oliveira Serra, \u0026quot;Machine Learning Model for Computational Tracking and Forecasting the COVID-19 Dynamic Propagation,\u0026quot; IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, vol. 25, no. 3, pp. 615-622, 2021. \u003c/li\u003e\n\u003cli\u003eA. S. Elkorany and Z. F. E. , \u0026quot;COVIDetection-Net: A tailored COVID-19 detection from chest radiography images using deep learning,\u0026quot; Optik , vol. 231, 2021. \u003c/li\u003e\n\u003cli\u003eM. J. Raihan, M. A. Khan, S. H. Kee and A. A. Nahid, Detection of the chronic kidney disease using XGBoost classifier and explaining the influence of the attributes on the model using SHAP, Scientific Reports, 2023. \u003c/li\u003e\n\u003cli\u003eW. e. al., \u0026quot;Identifying diagnostic biomarkers for erythemato-squamous diseases using explainable machine learning,\u0026quot; Biomedical Signal Processing and Control, vol. 100, 2025. \u003c/li\u003e\n\u003cli\u003eJ. R. e. a. Larsen, \u0026quot;Modeling the Onset of Symptoms of COVID-19.,\u0026quot; Frontiers in public health, vol. 8, 2020. \u003c/li\u003e\n\u003cli\u003eS. K. \u0026amp;. W. Z. Kiangala, \u0026quot;An effective adaptive customization framework for small manufacturing plants using extreme gradient boosting-XGBoost and random forest ensemble learning algorithms in an Industry 4.0 environment.,\u0026quot; Machine Learning with Applications, vol. 4, p. 100024, 2021. \u003c/li\u003e\n\u003cli\u003eE. K. Sahin, \u0026quot;Assessing the predictive capability of ensemble tree methods for landslide susceptibility mapping using XGBoost, gradient boosting machine, and random forest,\u0026quot; SN Applied Sciences, vol. 2, no. 7, p. 1308, 2020. \u003c/li\u003e\n\u003cli\u003eV. Sapra and M. L. Saini, \u0026quot;Computational intelligence for detection of coronary artery disease with optimized features,\u0026quot; International Journal of Innovative Technology and Exploring Engineering, vol. 8, no. 6C, pp. 144 - 148, 2019. \u003c/li\u003e\n\u003cli\u003eS. Jayachitra and A. Prasanth, \u0026quot;Multi-feature analysis for automated brain stroke classification using weighted Gaussian na\u0026iuml;ve Bayes classifier.,\u0026quot; Journal of Circuits, Systems and Computers , vol. 30, no. 10, p. 178, 2021. \u003c/li\u003e\n\u003cli\u003eV. Jackins, V. S, M. Kaliappan and M. Lee, \u0026quot;AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes,\u0026quot; The Journal of Supercomputing, vol. 77, no. 5, pp. 5198-5219, 2021. \u003c/li\u003e\n\u003cli\u003eB. Charbuty and A. Abdulazeez, \u0026quot;Classification based on decision tree algorithm for machine learning,\u0026quot; Journal of Applied Science and Technology Trends, vol. 2, no. 01, pp. 20-28, 2021. \u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"XGBoost, Random Forest, Ensemble Learning, COVID-19, SHAP, Machine Learning, Explainable AI (XAI)","lastPublishedDoi":"10.21203/rs.3.rs-6769397/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6769397/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe COVID-19 pandemic had a disastrous impact on the global community and challenged healthcare systems worldwide. The progress of the disease also has disastrous effects on the heart, kidney, and liver of an individual. The only way to save mankind from this minacious disease is its accurate and explainable detection. In this study, we propose a SHAP-driven ensemble learning framework using an optimized XGBoost algorithm ensemble with Random Forest for COVID-19 detection while providing interpretable insights into model predictions. We employ different ML models on the same dataset to evaluate the performance of these ML techniques with the proposed framework. The study also integrates Shapley additive explanations (SHAP) to improve feature selection, model interpretability, and prediction reliability. The proposed framework identifies key biomarkers that have a significant impact on COVID-19 thus improving transparency and trust in AI applications. Experimental results showed that the proposed ensemble model outperformed all other models and achieved an accuracy of 96.7%. The integration of SHAP not only enhances the model\u0026rsquo;s performance but also helps in understanding the critical factors that have a significant impact on the detection of COVID-19.\u003c/p\u003e","manuscriptTitle":"SHAP-Driven Ensemble Learning for Explainable COVID-19 Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-18 09:26:52","doi":"10.21203/rs.3.rs-6769397/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"38283f67-d2f1-493f-92d9-559c65ae3165","owner":[],"postedDate":"June 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":50113820,"name":"Biological sciences/Computational biology and bioinformatics/Predictive medicine"},{"id":50113821,"name":"Health sciences/Diseases"},{"id":50113822,"name":"Health sciences/Medical research"},{"id":50113823,"name":"Physical sciences/Engineering"}],"tags":[],"updatedAt":"2025-09-08T09:39:00+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-18 09:26:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6769397","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6769397","identity":"rs-6769397","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}