{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T18:41:29Z","timestamp":1776796889384,"version":"3.51.2"},"reference-count":63,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"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:p>Hypothyroidism, caused by reduced thyroid-hormone production, is often difficult to diagnose because its symptoms are non-specific and overlap with other disorders. We developed FusionNet-CXG, a hybrid deep-learning model that couples CNN, eXtended LSTM, and GRU components for hypothyroidism prediction. Experiments were performed on a public dataset (3,772 records; 30 features). Class imbalance was mitigated using SMOTE-NC, and performance was estimated using 10 repetitions of 5-fold stratified cross-validation, yielding 50 fold-level evaluations to obtain stable results. Across folds, FusionNet-CXG achieved 0.9394 mean accuracy, F1\u2009=\u20090.906, and AUC-ROC\u2009=\u20090.94, and it exceeded CNN+LSTM and CNN\u2009+\u2009BiLSTM baselines under the same protocol. The results indicate that combining local feature extraction with recurrent modelling is effective for this task. To support interpretability, SHAP was used to quantify feature influence on the predictions. Future work will focus on external validation using more diverse real-world cohorts and incorporating temporal clinical data to improve clinical relevance.<\/jats:p>","DOI":"10.1371\/journal.pone.0347203","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T17:48:08Z","timestamp":1776793688000},"page":"e0347203","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["A hybrid CNN-XLSTM-GRU deep learning model with autoencoder-based feature selection for hypothyroidism diagnosis"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8900-8759","authenticated-orcid":true,"given":"Divya","family":"Kesavulu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8530-9012","authenticated-orcid":true,"given":"Kannadasan","family":"R","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"pone.0347203.ref001","unstructured":"Status of Goitre or Thyroid Disorders in India. 2022. [Online]. Available: https:\/\/pib.gov.in\/PressReleasePage.aspx?PRID=1796440"},{"key":"pone.0347203.ref002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2019\/6212759","article-title":"Thyroid diagnosis from SPECT images using convolutional neural network with optimization","volume":"2019","author":"L Ma","year":"2019","journal-title":"Comput Intell Neurosci"},{"issue":"1","key":"pone.0347203.ref003","doi-asserted-by":"crossref","first-page":"19185","DOI":"10.1038\/s41598-023-46509-x","article-title":"Using machine learning algorithm to analyse the hypothyroidism complications caused by radiotherapy in patients with head and neck cancer","volume":"13","author":"T-F Lee","year":"2023","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0347203.ref004","doi-asserted-by":"crossref","first-page":"22524","DOI":"10.1038\/s41598-025-03299-8","article-title":"Improved bio-inspired with machine learning computing approach for thyroid prediction","volume":"15","author":"D Kesavulu","year":"2025","journal-title":"Sci Rep"},{"issue":"10","key":"pone.0347203.ref005","doi-asserted-by":"crossref","first-page":"183","DOI":"10.3390\/computation10100183","article-title":"A Proactive Explainable Artificial Neural Network Model for the Early Diagnosis of Thyroid Cancer","volume":"10","author":"SS Aljameel","year":"2022","journal-title":"Computation"},{"issue":"2","key":"pone.0347203.ref006","doi-asserted-by":"crossref","first-page":"299","DOI":"10.18280\/isi.280205","article-title":"Selection of features using adaptive tunicate swarm algorithm with optimized deep learning model for thyroid disease classification","volume":"28","author":"JP Kumar","year":"2023","journal-title":"Ing\u00e9nierie des syst\u00e8mes d information"},{"issue":"1","key":"pone.0347203.ref007","doi-asserted-by":"crossref","first-page":"36094","DOI":"10.1038\/s41598-025-19905-8","article-title":"Privacy preserving skin cancer diagnosis through federated deep learning and explainable AI","volume":"15","author":"NS Naz","year":"2025","journal-title":"Sci Rep"},{"key":"pone.0347203.ref008","doi-asserted-by":"crossref","first-page":"104267","DOI":"10.1016\/j.compbiomed.2021.104267","article-title":"Early diagnosis of thyroid cancer diseases using computational intelligence techniques: A case study of a Saudi Arabian dataset","volume":"131","author":"SO Olatunji","year":"2021","journal-title":"Comput Biol Med"},{"issue":"1","key":"pone.0347203.ref009","doi-asserted-by":"crossref","first-page":"11143","DOI":"10.1038\/s41598-022-15342-z","article-title":"Improving the diagnosis of thyroid cancer by machine learning and clinical data","volume":"12","author":"NM Xi","year":"2022","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0347203.ref010","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0262128","article-title":"Multi-channel convolutional neural network architectures for thyroid cancer detection","volume":"17","author":"X Zhang","year":"2022","journal-title":"PLoS One"},{"issue":"1","key":"pone.0347203.ref011","doi-asserted-by":"crossref","DOI":"10.5812\/semj.100351","article-title":"Comparison of the particle swarm optimization with the genetic algorithms as a training for multilayer perceptron technique to diagnose thyroid functional disease","volume":"22","author":"A Sharifi","year":"2020","journal-title":"Shiraz E Med J"},{"issue":"1","key":"pone.0347203.ref012","article-title":"SSC: The novel self-stack ensemble model for thyroid disease prediction","volume":"19","author":"S Ji","year":"2024","journal-title":"PLoS One"},{"key":"pone.0347203.ref013","doi-asserted-by":"crossref","first-page":"89098","DOI":"10.1109\/ACCESS.2024.3418974","article-title":"An Improved Framework for Detecting Thyroid Disease Using Filter-Based Feature Selection and Stacking Ensemble","volume":"12","author":"G Obaido","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0347203.ref014","doi-asserted-by":"crossref","first-page":"1224191","DOI":"10.3389\/fendo.2023.1224191","article-title":"Diagnosis of thyroid disease using deep convolutional neural network models applied to thyroid scintigraphy images: a multicenter study","volume":"14","author":"H Zhao","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"key":"pone.0347203.ref015","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.1394","article-title":"A systematic review on artificial intelligence techniques for detecting thyroid diseases","volume":"9","author":"L Aversano","year":"2023","journal-title":"PeerJ Comput Sci"},{"issue":"6","key":"pone.0347203.ref016","doi-asserted-by":"crossref","first-page":"2840","DOI":"10.1109\/TAI.2023.3327981","article-title":"An Intelligent Thyroid Diagnosis System Utilizing Multiple Ensemble and Explainable Algorithms With Medical Supported Attributes","volume":"5","author":"A Sutradhar","year":"2024","journal-title":"IEEE Trans Artif Intell"},{"key":"pone.0347203.ref017","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1038\/s43856-022-00071-1","article-title":"Development and preliminary validation of a machine learning system for thyroid dysfunction diagnosis based on routine laboratory tests","volume":"2","author":"M Hu","year":"2022","journal-title":"Commun Med (Lond)"},{"key":"pone.0347203.ref018","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1016\/j.procs.2021.08.106","article-title":"Thyroid disease treatment prediction with machine learning approaches","volume":"192","author":"L Aversano","year":"2021","journal-title":"Procedia Comput Sci"},{"issue":"2","key":"pone.0347203.ref019","article-title":"Enhancing thyroid cancer diagnostics through hybrid machine learning and metabolomics approaches","volume":"15","author":"MG Raj","year":"2024","journal-title":"International Journal of Advanced Computer Science and Applications"},{"key":"pone.0347203.ref020","doi-asserted-by":"crossref","first-page":"193838","DOI":"10.1109\/ACCESS.2025.3627948","article-title":"Privacy-Preserving Federated Learning for Thyroid Disease Detection: A Comparative Study on Feature Selection and Class Balancing","volume":"13","author":"D Kesavulu","year":"2025","journal-title":"IEEE Access"},{"issue":"7","key":"pone.0347203.ref021","doi-asserted-by":"crossref","first-page":"75","DOI":"10.14445\/22315381\/IJETT-V71I7P208","article-title":"Predicting thyroid disease using optimized multi-layered long short-term memory (LSTM) neural network with residual attention mechanism","volume":"71","author":"N R","year":"2023","journal-title":"International Journal of Engineering Trends and Technology"},{"key":"pone.0347203.ref022","doi-asserted-by":"crossref","first-page":"68127","DOI":"10.1109\/ACCESS.2023.3289511","article-title":"Thyroid Detection and Classification Using DNN Based on Hybrid Meta-Heuristic and LSTM Technique","volume":"11","author":"E Mohan","year":"2023","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0347203.ref023","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1186\/s12911-024-02604-1","article-title":"DEL-Thyroid: deep ensemble learning framework for detection of thyroid cancer progression through genomic mutation","volume":"24","author":"AA Shah","year":"2024","journal-title":"BMC Med Inform Decis Mak"},{"issue":"7","key":"pone.0347203.ref024","doi-asserted-by":"crossref","first-page":"38","DOI":"10.9781\/ijimai.2024.07.006","article-title":"Semi-Supervised Machine Learning Approaches for Thyroid Disease Prediction and its Integration With the Internet of Everything","volume":"8","author":"M Agraz","year":"2024","journal-title":"IJIMAI"},{"issue":"1","key":"pone.0347203.ref025","doi-asserted-by":"crossref","first-page":"26765","DOI":"10.1038\/s41598-025-12151-y","article-title":"Diabetes diagnosis using a hybrid CNN LSTM MLP ensemble","volume":"15","author":"Y Fan","year":"2025","journal-title":"Sci Rep"},{"issue":"12","key":"pone.0347203.ref026","doi-asserted-by":"crossref","first-page":"3215","DOI":"10.3390\/diagnostics12123215","article-title":"Ensemble Learning Based on Hybrid Deep Learning Model for Heart Disease Early Prediction","volume":"12","author":"A Almulihi","year":"2022","journal-title":"Diagnostics"},{"issue":"4","key":"pone.0347203.ref027","doi-asserted-by":"crossref","first-page":"207","DOI":"10.3390\/info11040207","article-title":"Ensemble deep learning models for heart disease classification: A case study from Mexico","volume":"11","author":"A Baccouche","year":"2020","journal-title":"Information"},{"issue":"1","key":"pone.0347203.ref028","doi-asserted-by":"crossref","first-page":"12082","DOI":"10.1038\/s41598-025-95311-4","article-title":"Hybrid convolutional neural network and bi-LSTM model with EfficientNet-B0 for high-accuracy breast cancer detection and classification","volume":"15","author":"UK Lilhore","year":"2025","journal-title":"Sci Rep"},{"key":"pone.0347203.ref029","doi-asserted-by":"crossref","first-page":"106079","DOI":"10.1016\/j.bspc.2024.106079","article-title":"A novel hybrid ensemble based Alzheimer\u2019s identification system using deep learning technique","volume":"92","author":"I Ayus","year":"2024","journal-title":"Biomedical Signal Processing and Control"},{"issue":"2","key":"pone.0347203.ref030","doi-asserted-by":"crossref","first-page":"5","DOI":"10.9781\/ijimai.2024.10.04","article-title":"A Smart Healthcare System Using Consumer Electronics and Federated Learning to Automatically Diagnose Diabetic Foot Ulcers.","volume":"9","author":"S Kumar Das","year":"2025","journal-title":"IJIMAI"},{"issue":"6","key":"pone.0347203.ref031","doi-asserted-by":"crossref","first-page":"86","DOI":"10.9781\/ijimai.2022.11.002","article-title":"Drug Target Interaction Prediction Using Machine Learning Techniques \u2013 A Review","volume":"8","author":"A Suruliandi","year":"2024","journal-title":"IJIMAI"},{"issue":"1","key":"pone.0347203.ref032","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1007\/s00530-023-01241-4","article-title":"HCNNet: hybrid convolution neural network for automatic identification of ischaemia in diabetic foot ulcer wounds","volume":"30","author":"SK Das","year":"2024","journal-title":"Multimedia Systems"},{"key":"pone.0347203.ref033","doi-asserted-by":"crossref","first-page":"183","DOI":"10.37256\/ccds.5220244059","article-title":"Analysis and prediction of COVID-19 using growth analysis models: A case study","author":"K Lone","year":"2024","journal-title":"Cloud Computing and Data Science"},{"key":"pone.0347203.ref034","first-page":"95","article-title":"Internet of Things and Machine Learning for Smart Healthcare","volume-title":"Springer Nature Link","author":"CA da Costa","year":"2024"},{"issue":"2","key":"pone.0347203.ref035","doi-asserted-by":"crossref","first-page":"102845","DOI":"10.1016\/j.ipm.2021.102845","article-title":"Early prediction of cognitive impairments using physiological signal for enhanced socioeconomic status","volume":"59","author":"S Swati","year":"2022","journal-title":"Information Processing & Management"},{"issue":"3","key":"pone.0347203.ref036","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.3390\/s23031128","article-title":"A Novel Blunge Calibration Intelligent Feature Classification Model for the Prediction of Hypothyroid Disease","volume":"23","author":"MS Devi","year":"2023","journal-title":"Sensors (Basel)"},{"issue":"1","key":"pone.0347203.ref037","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1186\/s12911-024-02780-0","article-title":"Enhanced interpretable thyroid disease diagnosis by leveraging synthetic oversampling and machine learning models","volume":"24","author":"A Raza","year":"2024","journal-title":"BMC Med Inform Decis Mak"},{"key":"pone.0347203.ref038","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.ceh.2025.01.002","article-title":"Enhancing thyroid disease prediction and comorbidity management through advanced machine learning frameworks","volume":"8","author":"P Sanju","year":"2025","journal-title":"Clinical eHealth"},{"key":"pone.0347203.ref039","doi-asserted-by":"crossref","first-page":"106823","DOI":"10.1016\/j.cmpb.2022.106823","article-title":"Deep convolutional neural networks in thyroid disease detection: A multi-classification comparison by ultrasonography and computed tomography","volume":"220","author":"X Zhang","year":"2022","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0347203.ref040","doi-asserted-by":"crossref","first-page":"102049","DOI":"10.1016\/j.media.2021.102049","article-title":"Applying deep learning in digital breast tomosynthesis for automatic breast cancer detection: A review","volume":"71","author":"J Bai","year":"2021","journal-title":"Med Image Anal"},{"key":"pone.0347203.ref041","doi-asserted-by":"crossref","first-page":"101858","DOI":"10.1016\/j.media.2020.101858","article-title":"Convolutional neural networks for the automatic diagnosis of melanoma: An extensive experimental study","volume":"67","author":"E P\u00e9rez","year":"2021","journal-title":"Med Image Anal"},{"key":"pone.0347203.ref042","unstructured":"Kaggle. Hypothyroid dataset. [Online]. Available: https:\/\/www.kaggle.com\/datasets\/kumar012\/hypothyroid"},{"key":"pone.0347203.ref043","doi-asserted-by":"crossref","first-page":"5761","DOI":"10.1016\/j.csbj.2022.10.016","article-title":"Multi-task deep autoencoder to predict Alzheimer\u2019s disease progression using temporal DNA methylation data in peripheral blood","volume":"20","author":"L Chen","year":"2022","journal-title":"Comput Struct Biotechnol J"},{"issue":"7","key":"pone.0347203.ref044","doi-asserted-by":"crossref","DOI":"10.1007\/s42452-024-06068-w","article-title":"Explainable artificial intelligence and machine learning algorithms for classification of thyroid disease","volume":"6","author":"P Kumari","year":"2024","journal-title":"Discov Appl Sci"},{"issue":"1","key":"pone.0347203.ref045","doi-asserted-by":"crossref","first-page":"012030","DOI":"10.1088\/1742-6596\/1767\/1\/012030","article-title":"Variant component principal linear reduction for prediction of hypothyroid disease using machine learning","volume":"1767","author":"M Shyamala Devi","year":"2021","journal-title":"J Phys Conf Ser"},{"key":"pone.0347203.ref046","doi-asserted-by":"crossref","first-page":"106885","DOI":"10.1016\/j.ymssp.2020.106885","article-title":"CNN-LSTM deep learning architecture for computer vision-based modal frequency detection","volume":"144","author":"R Yang","year":"2020","journal-title":"Mechanical Systems and Signal Processing"},{"key":"pone.0347203.ref047","doi-asserted-by":"crossref","first-page":"104028","DOI":"10.1016\/j.jtice.2021.08.016","article-title":"A comparative study on long short-term memory and gated recurrent unit neural networks in fault diagnosis for chemical processes using visualization","volume":"130","author":"S Mirzaei","year":"2022","journal-title":"J Taiwan Inst Chem Eng"},{"issue":"9","key":"pone.0347203.ref048","doi-asserted-by":"crossref","first-page":"3744","DOI":"10.17762\/ijritcc.v11i9.9607","article-title":"Efficient Extraction and Automated Thyroid Prediction with an Optimized Gated Recurrent Unit in Recurrent Neural Networks","volume":"11","author":"al. Nagavali Saka E","year":"2023","journal-title":"IJRITCC"},{"key":"pone.0347203.ref049","doi-asserted-by":"crossref","first-page":"129977","DOI":"10.1016\/j.jhydrol.2023.129977","article-title":"An ensemble CNN-LSTM and GRU adaptive weighting model based improved sparrow search algorithm for predicting runoff using historical meteorological and runoff data as input","volume":"625","author":"Z Yao","year":"2023","journal-title":"Journal of Hydrology"},{"issue":"1","key":"pone.0347203.ref050","doi-asserted-by":"crossref","DOI":"10.2174\/0118750362305982240627034926","article-title":"A Comparative Study on Thyroid Nodule Classification Using Transfer Learning Methods","volume":"17","author":"V Sureshkumar","year":"2024","journal-title":"TOBIOIJ"},{"issue":"1","key":"pone.0347203.ref051","doi-asserted-by":"crossref","first-page":"13588","DOI":"10.1038\/s41598-023-40717-1","article-title":"An active learning machine technique based prediction of cardiovascular heart disease from UCI-repository database","volume":"13","author":"S Srinivasan","year":"2023","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0347203.ref052","doi-asserted-by":"crossref","first-page":"6256","DOI":"10.1038\/s41598-022-10358-x","article-title":"Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction","volume":"12","author":"S Uddin","year":"2022","journal-title":"Sci Rep"},{"issue":"10","key":"pone.0347203.ref053","doi-asserted-by":"crossref","first-page":"13935","DOI":"10.1007\/s11042-022-12385-2","article-title":"Breast cancer diagnosis in an early stage using novel deep learning with hybrid optimization technique","volume":"81","author":"KK Dewangan","year":"2022","journal-title":"Multimed Tools Appl"},{"issue":"15","key":"pone.0347203.ref054","doi-asserted-by":"crossref","first-page":"3891","DOI":"10.3390\/cancers13153891","article-title":"Deep Learning Fast Screening Approach on Cytological Whole Slides for Thyroid Cancer Diagnosis","volume":"13","author":"Y-J Lin","year":"2021","journal-title":"Cancers (Basel)"},{"issue":"2","key":"pone.0347203.ref055","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1049\/qtc2.12078","article-title":"Quantum intelligence in medicine: Empowering thyroid disease prediction through advanced machine learning","volume":"5","author":"M Sha","year":"2023","journal-title":"IET Quantum Communication"},{"issue":"3","key":"pone.0347203.ref056","doi-asserted-by":"crossref","first-page":"2909","DOI":"10.32604\/iasc.2023.030335","article-title":"Butterfly Optimized Feature Selection with Fuzzy C-Means Classifier for Thyroid Prediction","volume":"35","author":"S J. K. Jagadeesh Kumar","year":"2023","journal-title":"Intelligent Automation & Soft Computing"},{"key":"pone.0347203.ref057","doi-asserted-by":"crossref","unstructured":"Zhang X, Lee VCS, Rong J, Lee JC, Song J, Liu F. Multi-channel deep convolutional neural networks for multi-classifying thyroid disease. 2022. doi: 10.48550\/arXiv.2203.03627","DOI":"10.1016\/j.compbiomed.2022.105961"},{"key":"pone.0347203.ref058","first-page":"77","volume-title":"Efficient method for predicting thyroid disease classification using convolutional neural network with support vector machine","author":"V Brindha","year":"2023"},{"key":"pone.0347203.ref059","first-page":"37","volume-title":"Efficient method for the prediction of thyroid disease classification using support vector machine and logistic regression","author":"V Brindha","year":"2023"},{"issue":"3","key":"pone.0347203.ref060","first-page":"368","article-title":"Hypothyroidism disease diagnosis by using machine learning algorithms","volume":"11","author":"A Bin Naeem","year":"2023","journal-title":"International Journal of Intelligent Systems and Applications in Engineering"},{"issue":"16","key":"pone.0347203.ref061","doi-asserted-by":"crossref","first-page":"2259","DOI":"10.2169\/internalmedicine.2825-23","article-title":"An Evaluation of the Efficacy of Machine Learning in Predicting Thyrotoxicosis and Hypothyroidism: A Comparative Assessment of Biochemical Test Parameters Used in Different Health Checkups","volume":"63","author":"J Yoshimura Noh","year":"2024","journal-title":"Intern Med"},{"issue":"01","key":"pone.0347203.ref062","first-page":"11","article-title":"Thyroid disease prediction: leveraging machine learning for accuracy","volume":"3","author":"T Kavya Suma","year":"2025","journal-title":"IRJAEH"},{"issue":"1","key":"pone.0347203.ref063","doi-asserted-by":"crossref","first-page":"12501","DOI":"10.1038\/s41598-025-94827-z","article-title":"Leveraging machine learning in precision medicine to unveil organochlorine pesticides as predictive biomarkers for thyroid dysfunction","volume":"15","author":"S Shamma","year":"2025","journal-title":"Scientific Reports"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0347203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T17:48:24Z","timestamp":1776793704000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0347203"}},"subtitle":[],"editor":[{"given":"Maciej","family":"Huk","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":63,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0347203","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]}}}