{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T17:52:34Z","timestamp":1778262754356,"version":"3.51.4"},"reference-count":63,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Pneumonia is a major cause of mortality among children under five and adults over 65, especially in low-resource settings where access to skilled radiologists is limited. Accurate and early diagnosis is essential, but is often hindered by subjective interpretation and variability in its symptoms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>This study aims to develop a hybrid Artificial Intelligence (AI) based pneumonia diagnosis system that integrates Deep Learning (DL) confidence scores, DenseNet201 with Capsule Network (CapsNet), Mamdani-style fuzzy inference, and a dynamic symptom adjustment mechanism to enhance diagnostic accuracy, transparency, and clinical usability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The system was evaluated using 17,229 labelled chest X-ray images across multiple cross-validation techniques: Stratified, k-fold, Bootstrap, and Monte Carlo methods, each with five dataset iterations or folds. DenseNet was used to extract spatial features, while CapsNet preserved spatial orientation and hierarchical relationships. A DL based confidence score was generated and used as a fuzzy membership input to support classification in borderline cases, where severity scores were nearly tied, and the confidence score guided the final decision. A dynamic adjustment algorithm further refined symptom severity by incorporating recent trends in patient data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The DenseNet201\u2009+\u2009CapsNet architecture achieved the highest performance in the 5th fold of stratified cross-validation, with a test accuracy of 99.01%. The model also demonstrated strong generalization, with a weighted precision, recall and F1-score of 0.9878, 0.9874, and 0.9876, respectively, across all classes. The paired t-test confirmed that the CapsNet-based approach outperformed traditional fully connected layers, and the fuzzy logic system effectively handled ambiguous cases using DL confidence. The dynamic membership mechanism showed strong adaptability for real-time symptom tracking.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec005\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This hybrid model offers a robust, interpretable, and clinically relevant decision-support tool for pneumonia diagnosis. It bridges high-performance AI with real-world medical decision-making, especially in settings with limited radiological expertise.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0334899","type":"journal-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:26:29Z","timestamp":1761153989000},"page":"e0334899","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["A hybrid dense convolutional network and fuzzy inference system for pneumonia diagnosis with dynamic symptom tracking"],"prefix":"10.1371","volume":"20","author":[{"given":"Sulav","family":"Baral","sequence":"first","affiliation":[]},{"given":"Rabindra","family":"Bista","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0470-860X","authenticated-orcid":true,"given":"Sanjog","family":"Sigdel","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6662-0806","authenticated-orcid":true,"given":"Jo\u00e3o C.","family":"Ferreira","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2025,10,22]]},"reference":[{"key":"pone.0334899.ref001","volume-title":"Bacterial Pneumonia. StatPearls. Treasure Island (FL","author":"SBA Sattar","year":"2025"},{"key":"pone.0334899.ref002","author":"SKR Mallidi","year":"2025","journal-title":"Enhancing Pneumonia Diagnosis and Severity Assessment through Deep Learning: A Comprehensive Approach Integrating CNN Classification and Infection Segmentation"},{"issue":"1","key":"pone.0334899.ref003","doi-asserted-by":"crossref","DOI":"10.1016\/S2214-109X(18)30408-X","article-title":"Global, regional, and national estimates of pneumonia morbidity and mortality in children younger than 5 years between 2000 and 2015: a systematic analysis","volume":"7","author":"DA McAllister","year":"2019","journal-title":"Lancet Glob Health"},{"key":"pone.0334899.ref004","doi-asserted-by":"crossref","first-page":"109319","DOI":"10.1016\/j.asoc.2022.109319","article-title":"Chest X-ray analysis empowered with deep learning: A systematic review","volume":"126","author":"D Meedeniya","year":"2022","journal-title":"Appl Soft Comput"},{"issue":"1","key":"pone.0334899.ref005","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.imed.2023.08.001","article-title":"Medical artificial intelligence and the black box problem: a view based on the ethical principle of \u201cdo no harm\u201d","volume":"4","author":"H Xu","year":"2024","journal-title":"Intelligent Medicine"},{"issue":"1","key":"pone.0334899.ref006","doi-asserted-by":"crossref","DOI":"10.1186\/s43055-024-01356-2","article-title":"Explainability, transparency and black box challenges of AI in radiology: impact on patient care in cardiovascular radiology","volume":"55","author":"A Marey","year":"2024","journal-title":"Egypt J Radiol Nucl Med"},{"key":"pone.0334899.ref007","doi-asserted-by":"crossref","first-page":"107214","DOI":"10.1016\/j.infsof.2023.107214","article-title":"Predicting neural network confidence using high-level feature distance","volume":"159","author":"J Wang","year":"2023","journal-title":"Information and Software Technology"},{"issue":"1","key":"pone.0334899.ref008","doi-asserted-by":"crossref","first-page":"4275","DOI":"10.1038\/s41598-024-54065-1","article-title":"A dynamic fuzzy rule-based inference system using fuzzy inference with semantic reasoning","volume":"14","author":"N Shoaip","year":"2024","journal-title":"Sci Rep"},{"issue":"4","key":"pone.0334899.ref009","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0249399","article-title":"Diagnostic performance of artificial intelligence model for pneumonia from chest radiography","volume":"16","author":"T Kwon","year":"2021","journal-title":"PLoS One"},{"issue":"3","key":"pone.0334899.ref010","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1016\/j.chest.2022.10.039","article-title":"Commonly Missed Findings on Chest Radiographs: Causes and Consequences","volume":"163","author":"WB Gefter","year":"2023","journal-title":"Chest"},{"key":"pone.0334899.ref011","doi-asserted-by":"crossref","first-page":"101785","DOI":"10.1016\/j.artmed.2019.101785","article-title":"The impact of machine learning on patient care: A systematic review","volume":"103","author":"D Ben-Israel","year":"2020","journal-title":"Artif Intell Med"},{"issue":"5","key":"pone.0334899.ref012","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1007\/s10143-019-01163-8","article-title":"Machine learning applications to clinical decision support in neurosurgery: an artificial intelligence augmented systematic review","volume":"43","author":"QD Buchlak","year":"2020","journal-title":"Neurosurg Rev"},{"key":"pone.0334899.ref013","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.jocn.2021.04.043","article-title":"Machine learning applications to neuroimaging for glioma detection and classification: An artificial intelligence augmented systematic review","volume":"89","author":"QD Buchlak","year":"2021","journal-title":"J Clin Neurosci"},{"issue":"4","key":"pone.0334899.ref014","doi-asserted-by":"crossref","first-page":"743","DOI":"10.3390\/diagnostics13040743","article-title":"Machine Learning Augmented Interpretation of Chest X-rays: A Systematic Review","volume":"13","author":"HK Ahmad","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"pone.0334899.ref015","first-page":"227","author":"H Sharma","year":"2020","journal-title":"Feature Extraction and Classification of Chest X-Ray Images Using CNN to Detect Pneumonia. 2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence"},{"key":"pone.0334899.ref016","first-page":"485","article-title":"An In-Depth Convolution Neural Network for Chest X-Ray Image Assessment Using CXRIA-Net.","author":"B Sujatha","year":"2024","journal-title":"Information System Design: AI and ML Applications."},{"issue":"4","key":"pone.0334899.ref017","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1007\/s13244-018-0639-9","article-title":"Convolutional neural networks: an overview and application in radiology","volume":"9","author":"R Yamashita","year":"2018","journal-title":"Insights Imaging"},{"key":"pone.0334899.ref018","first-page":"1","author":"D Varshni","year":"2019","journal-title":"Pneumonia Detection Using CNN based Feature Extraction. 2019 IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT"},{"issue":"9","key":"pone.0334899.ref019","doi-asserted-by":"crossref","first-page":"3233","DOI":"10.3390\/app10093233","article-title":"Transfer Learning with Deep Convolutional Neural Network (CNN) for Pneumonia Detection Using Chest X-ray","volume":"10","author":"T Rahman","year":"2020","journal-title":"Applied Sciences"},{"issue":"4","key":"pone.0334899.ref020","doi-asserted-by":"crossref","first-page":"1625","DOI":"10.1007\/s10278-024-01005-0","article-title":"Classification of Lung Diseases Using an Attention-Based Modified DenseNet Model","volume":"37","author":"U Chutia","year":"2024","journal-title":"J Imaging Inform Med"},{"key":"pone.0334899.ref021","article-title":"A deep learning approach for classification of COVID and pneumonia using DenseNet-201","author":"HA Sanghvi","year":"2022","journal-title":"Int J Imaging Syst Technol"},{"issue":"9","key":"pone.0334899.ref022","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0256630","article-title":"Pneumonia detection in chest X-ray images using an ensemble of deep learning models","volume":"16","author":"R Kundu","year":"2021","journal-title":"PLoS One"},{"issue":"15","key":"pone.0334899.ref023","doi-asserted-by":"crossref","first-page":"5682","DOI":"10.1080\/07391102.2020.1788642","article-title":"Classification of the COVID-19 infected patients using DenseNet201 based deep transfer learning","volume":"39","author":"A Jaiswal","year":"2021","journal-title":"J Biomol Struct Dyn"},{"key":"pone.0334899.ref024","first-page":"327","author":"O Rochmawanti","year":"2021","journal-title":"Chest X-Ray Image to Classify Lung diseases in Different Resolution Size using DenseNet-121 Architectures."},{"key":"pone.0334899.ref025","first-page":"1","author":"BM Anakha","year":"2021","journal-title":"Detecting COVID-19 from Chest X-Ray Images using Deep Learning."},{"key":"pone.0334899.ref026","first-page":"1","author":"S Shrimali","year":"2024","journal-title":"Optimizing Chest X-ray Analysis for Pneumonia Detection Through Comparative Evaluation of Transfer Learning CNN Architectures."},{"key":"pone.0334899.ref027","first-page":"440","author":"J Tang","year":"2024","journal-title":"Pneumonia Image Classification: Deep Learning and Machine Learning Fusion. 2024 7th International Conference on Artificial Intelligence and Big Data (ICAIBD"},{"issue":"1","key":"pone.0334899.ref028","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s10140-021-01954-x","article-title":"Limited generalizability of deep learning algorithm for pediatric pneumonia classification on external data","volume":"29","author":"KZ Xin","year":"2022","journal-title":"Emerg Radiol"},{"issue":"2","key":"pone.0334899.ref029","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/91.755393","article-title":"Implementation of evolutionary fuzzy systems","volume":"7","author":"S Yuhui","year":"1999","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"pone.0334899.ref030","first-page":"1","article-title":"An Introduction to Computational Intelligence Paradigms.","author":"A Konar","year":"2001","journal-title":"Practical Applications of Computational Intelligence Techniques"},{"key":"pone.0334899.ref031","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1504\/IJRIS.2010.036873","article-title":"Fuzzy-neural networks for medical diagnosis","volume":"2","author":"C Senol","year":"2010","journal-title":"IJRIS"},{"key":"pone.0334899.ref032","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1007\/978-3-031-16075-2_27","article-title":"Building a Fuzzy Expert System for Assessing the Severity of Pneumonia.","author":"R Burnashev","year":"2023","journal-title":"Intelligent Systems and Applications"},{"key":"pone.0334899.ref033","doi-asserted-by":"crossref","DOI":"10.3103\/S000510552570027X","article-title":"Development of an Expert System Based on Fuzzy Logic for Pneumonia Diagnostics","volume":"58","author":"AI Enikeeva","year":"2024","journal-title":"Autom Doc Math Linguist"},{"issue":"2","key":"pone.0334899.ref034","doi-asserted-by":"crossref","first-page":"103","DOI":"10.5455\/aim.2019.27.103-107","article-title":"An Expert System to Diagnose Pneumonia Using Fuzzy Logic","volume":"27","author":"LA Arani","year":"2019","journal-title":"Acta Inform Med"},{"key":"pone.0334899.ref035","doi-asserted-by":"crossref","first-page":"110307","DOI":"10.1016\/j.apacoust.2024.110307","article-title":"TPat: Transition pattern feature extraction based Parkinson\u2019s disorder detection using FNIRS signals","volume":"228","author":"T Tuncer","year":"2025","journal-title":"Applied Acoustics"},{"issue":"1","key":"pone.0334899.ref036","doi-asserted-by":"crossref","first-page":"79","DOI":"10.4103\/aihb.aihb_50_22","article-title":"A Novel Convolutional Neural Network\u2013Fuzzy-Based Diagnosis in the Classification of Dental Pulpitis","volume":"13","author":"RB Chauhan","year":"2023","journal-title":"Advances in Human Biology"},{"issue":"1","key":"pone.0334899.ref037","doi-asserted-by":"crossref","first-page":"14538","DOI":"10.1038\/s41598-021-93783-8","article-title":"A fuzzy rank-based ensemble of CNN models for classification of cervical cytology","volume":"11","author":"A Manna","year":"2021","journal-title":"Sci Rep"},{"key":"pone.0334899.ref038","article-title":"Detection of pneumonia using fuzzy expert system","volume":"9","author":"R B","year":"2024","journal-title":"Int J Nov Res Dev"},{"issue":"2","key":"pone.0334899.ref039","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.artmed.2010.05.007","article-title":"Evolving fuzzy medical diagnosis of Pima Indians diabetes and of dermatological diseases","volume":"50","author":"S Lekkas","year":"2010","journal-title":"Artif Intell Med"},{"issue":"5","key":"pone.0334899.ref040","doi-asserted-by":"crossref","first-page":"805","DOI":"10.18280\/mmep.080517","article-title":"Early Identification of COVID-19 Using Dynamic Fuzzy Rule Based System","volume":"8","author":"MIB Ahmed","year":"2021","journal-title":"MMEP"},{"key":"pone.0334899.ref041","unstructured":"Eldsouky M. Chest x-ray images pneumonia dataset. 2025. Available: https:\/\/www.kaggle.com\/datasets\/moazeldsokyx\/chest-x-ray-images-pneumonia-dataset\/data"},{"key":"pone.0334899.ref042","doi-asserted-by":"crossref","DOI":"10.3389\/fnano.2022.972421","article-title":"SKCV: Stratified K-fold cross-validation on ML classifiers for predicting cervical cancer","volume":"4","author":"S Prusty","year":"2022","journal-title":"Front Nanotechnol"},{"issue":"2","key":"pone.0334899.ref043","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1007\/s13369-020-04972-y","article-title":"A Method of Classification Performance Improvement Via a Strategy of Clustering-Based Data Elimination Integrated with k-Fold Cross-Validation","volume":"46","author":"O Inan","year":"2020","journal-title":"Arab J Sci Eng"},{"issue":"1","key":"pone.0334899.ref044","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0169-7439(00)00122-2","article-title":"Monte Carlo cross validation","volume":"56","author":"Q-S Xu","year":"2001","journal-title":"Chemometrics and Intelligent Laboratory Systems"},{"issue":"6","key":"pone.0334899.ref045","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1002\/wics.182","article-title":"Bootstrap","volume":"3","author":"T Hesterberg","year":"2011","journal-title":"WIREs Computational Stats"},{"key":"pone.0334899.ref046","unstructured":"Sabour S, Frosst N, Hinton GE. Dynamic Routing Between Capsules. Advances in Neural Information Processing Systems. Curran Associates, Inc.; 2017. Available: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/hash\/2cad8fa47bbef282badbb8de5374b894-Abstract.html"},{"issue":"3","key":"pone.0334899.ref047","first-page":"00051","article-title":"Outcomes of community-acquired pneumonia using the Pneumonia Severity Index versus the CURB-65 in routine practice of emergency departments","volume":"9","author":"AG Kaal","year":"2023","journal-title":"ERJ Open Res"},{"issue":"1","key":"pone.0334899.ref048","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1186\/s12890-025-03550-y","article-title":"Assessment of disease severity in hospitalized community-acquired pneumonia by the use of validated scoring systems","volume":"25","author":"S Iftikhar","year":"2025","journal-title":"BMC Pulm Med"},{"key":"pone.0334899.ref049","first-page":"1636","article-title":"Study of pneumonia severity index and CURB-65 in community acquired pneumonia in industrial set-up","volume":"31","author":"DSBM Reddy","year":"2024","journal-title":"J Popul Ther Clin Pharmacol"},{"issue":"6","key":"pone.0334899.ref050","doi-asserted-by":"crossref","first-page":"386","DOI":"10.2471\/BLT.18.223271","article-title":"Impact of the change in WHO\u2019s severe pneumonia case definition on hospitalized pneumonia epidemiology: case studies from six countries","volume":"97","author":"FM Russell","year":"2019","journal-title":"Bull World Health Organ"},{"key":"pone.0334899.ref051","article-title":"On Appropriate Selection of Fuzzy Aggregation Operators in Medical Decision Support System.","author":"KMM Hossain","year":"2013"},{"issue":"1","key":"pone.0334899.ref052","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3703461","article-title":"Enhanced Fuzzy Score-Based Decision Support System for Early Stroke Prediction","volume":"6","author":"M Ben Kahla","year":"2025","journal-title":"ACM Trans Comput Healthcare"},{"issue":"11","key":"pone.0334899.ref053","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1590\/1414-431X20143640","article-title":"Estimating the average length of hospitalization due to pneumonia: a fuzzy approach","volume":"47","author":"LFC Nascimento","year":"2014","journal-title":"Braz J Med Biol Res"},{"key":"pone.0334899.ref054","volume-title":"Statistics for business and economics","author":"P Newbold","year":"2013"},{"issue":"4","key":"pone.0334899.ref055","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1016\/j.ijforecast.2006.03.005","article-title":"Exponential smoothing: The state of the art\u2014Part II","volume":"22","author":"Jr Gardner ES","year":"2006","journal-title":"International Journal of Forecasting"},{"key":"pone.0334899.ref056","doi-asserted-by":"crossref","first-page":"100391","DOI":"10.1016\/j.imu.2020.100391","article-title":"Hybrid deep learning for detecting lung diseases from X-ray images","volume":"20","author":"S Bharati","year":"2020","journal-title":"Inform Med Unlocked"},{"issue":"6","key":"pone.0334899.ref057","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0252573","article-title":"COVID-19 detection using federated machine learning","volume":"16","author":"M Abdul Salam","year":"2021","journal-title":"PLoS One"},{"issue":"7825","key":"pone.0334899.ref058","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"CR Harris","year":"2020","journal-title":"Nature"},{"key":"pone.0334899.ref059","author":"TA Caswell","year":"2021","journal-title":"matplotlib\/matplotlib: REL: v3.4.0"},{"issue":"12","key":"pone.0334899.ref060","doi-asserted-by":"crossref","first-page":"6487","DOI":"10.3390\/app15126487","article-title":"PELM: A Deep Learning Model for Early Detection of Pneumonia in Chest Radiography","volume":"15","author":"E Yanar","year":"2025","journal-title":"Applied Sciences"},{"key":"pone.0334899.ref061","doi-asserted-by":"crossref","first-page":"107141","DOI":"10.1016\/j.cmpb.2022.107141","article-title":"IEViT: An enhanced vision transformer architecture for chest X-ray image classification","volume":"226","author":"GI Okolo","year":"2022","journal-title":"Comput Methods Programs Biomed"},{"issue":"8","key":"pone.0334899.ref062","doi-asserted-by":"crossref","first-page":"176","DOI":"10.3390\/jimaging10080176","article-title":"Deep Learning for Pneumonia Detection in Chest X-ray Images: A Comprehensive Survey","volume":"10","author":"R Siddiqi","year":"2024","journal-title":"J Imaging"},{"issue":"1","key":"pone.0334899.ref063","doi-asserted-by":"crossref","first-page":"2487","DOI":"10.1038\/s41598-024-52703-2","article-title":"Efficient pneumonia detection using Vision Transformers on chest X-rays","volume":"14","author":"S Singh","year":"2024","journal-title":"Sci Rep"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0334899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:26:39Z","timestamp":1761153999000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0334899"}},"subtitle":[],"editor":[{"given":"Fatih","family":"Uysal","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":63,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0334899","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,22]]}}}