{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T14:59:11Z","timestamp":1789138751465,"version":"build-2803163510"},"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:00:00Z","timestamp":1777852800000},"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>To address the challenges of complex acoustic patterns and limited interpretability in pertussis cough sound recognition, this study proposes an interpretable deep learning framework based on adaptive time\u2013frequency fusion and medically guided attention mechanisms. The framework first employs an Adaptive Time\u2013Frequency Fusion Transformer to extract multi-scale temporal and spectral features of cough sounds, followed by a Medically-Guided Interpretable Attention Mapping module that aligns attention distributions with medically relevant acoustic features, achieving explicit interpretability in the diagnostic process. Experiments were conducted on three publicly available pertussis cough sound datasets from Kaggle, containing 68, 66, and 44 recordings, respectively. Under an 8:2 training\u2013testing split with strict data leakage prevention, the proposed method achieved AUC scores of 0.994, 0.984, and 0.996 on the three datasets, outperforming the best existing baselines by an average of approximately 2%. Ablation studies demonstrated that the ATF module significantly enhances time\u2013frequency dependency modeling, while the MGIAM module improves attention consistency in medically relevant regions. In noise robustness experiments, performance degradation remained below 3%, confirming the model\u2019s reliability and generalization ability in clinical applications. Overall, the proposed framework achieves unified high accuracy and strong interpretability for pertussis sound recognition, providing a reusable modeling paradigm for medical acoustic analysis.<\/jats:p>","DOI":"10.1371\/journal.pone.0348508","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T17:46:01Z","timestamp":1777916761000},"page":"e0348508","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["ATF-MGIAM: Medically-guided interpretable attention mapping for robust pertussis cough sound recognition"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1299-581X","authenticated-orcid":true,"given":"Siheng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7927-8289","authenticated-orcid":true,"given":"Yan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5178-1706","authenticated-orcid":true,"given":"Ying","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,5,4]]},"reference":[{"issue":"11","key":"pone.0348508.ref001","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1038\/s41579-024-01064-8","article-title":"Pertussis vaccines, epidemiology and evolution","volume":"22","author":"M Domenech de Cell\u00e8s","year":"2024","journal-title":"Nat Rev Microbiol"},{"issue":"1","key":"pone.0348508.ref002","doi-asserted-by":"crossref","first-page":"2352606","DOI":"10.1080\/07853890.2024.2352606","article-title":"Severe pertussis in infants: a scoping review","volume":"56","author":"S Guo","year":"2024","journal-title":"Ann Med"},{"issue":"1","key":"pone.0348508.ref003","doi-asserted-by":"crossref","first-page":"2377904","DOI":"10.1080\/21645515.2024.2377904","article-title":"Public health management of pertussis in adults: Practical challenges and future strategies","volume":"20","author":"CR MacIntyre","year":"2024","journal-title":"Hum Vaccin Immunother"},{"key":"pone.0348508.ref004","doi-asserted-by":"crossref","unstructured":"Wan M, Zhang G, Yi H. Unraveling the resurgence of pertussis: Insights into epidemiology and global health strategies. 2024.","DOI":"10.1016\/j.pulmoe.2024.04.009"},{"issue":"10","key":"pone.0348508.ref005","doi-asserted-by":"crossref","first-page":"115","DOI":"10.3991\/ijoe.v20i10.49585","article-title":"Lung Sound Classification for Respiratory Disease Identification Using Deep Learning: A Survey","volume":"20","author":"T Wanasinghe","year":"2024","journal-title":"Int J Onl Eng"},{"issue":"2","key":"pone.0348508.ref006","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1007\/s00521-024-10437-2","article-title":"Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning","volume":"37","author":"E \u015eahin","year":"2024","journal-title":"Neural Comput & Applic"},{"key":"pone.0348508.ref007","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1016\/j.csbj.2024.05.004","article-title":"From explainable to interpretable deep learning for natural language processing in healthcare: How far from reality","volume":"24","author":"G Huang","year":"2024","journal-title":"Computational and structural biotechnology journal"},{"issue":"1","key":"pone.0348508.ref008","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/s00701-024-05892-8","article-title":"A critical moment in machine learning in medicine: on reproducible and interpretable learning","volume":"166","author":"O Ciobanu-Caraus","year":"2024","journal-title":"Acta Neurochir (Wien)"},{"key":"pone.0348508.ref009","doi-asserted-by":"crossref","first-page":"105846","DOI":"10.1016\/j.ijmedinf.2025.105846","article-title":"Explainability and uncertainty: Two sides of the same coin for enhancing the interpretability of deep learning models in healthcare","volume":"197","author":"M Salvi","year":"2025","journal-title":"Int J Med Inform"},{"key":"pone.0348508.ref010","doi-asserted-by":"crossref","first-page":"106073","DOI":"10.1016\/j.bspc.2024.106073","article-title":"Croup and pertussis cough sound classification algorithm based on channel attention and multiscale Mel-spectrogram","volume":"91","author":"K Luo","year":"2024","journal-title":"Biomedical Signal Processing and Control"},{"issue":"3","key":"pone.0348508.ref011","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1002\/lary.31042","article-title":"Cough Sounds in Screening and Diagnostics: A Scoping Review","volume":"134","author":"S Hegde","year":"2024","journal-title":"Laryngoscope"},{"issue":"4","key":"pone.0348508.ref012","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.3390\/s24041173","article-title":"Respiratory Diseases Diagnosis Using Audio Analysis and Artificial Intelligence: A Systematic Review","volume":"24","author":"P Kapetanidis","year":"2024","journal-title":"Sensors (Basel)"},{"issue":"1","key":"pone.0348508.ref013","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1038\/s41598-023-50371-2","article-title":"Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments","volume":"14","author":"S Ghrabli","year":"2024","journal-title":"Sci Rep"},{"issue":"3","key":"pone.0348508.ref014","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1002\/ppul.25801","article-title":"Development and technical validation of a smartphone-based pediatric cough detection algorithm","volume":"57","author":"MD Kruizinga","year":"2022","journal-title":"Pediatr Pulmonol"},{"key":"pone.0348508.ref015","doi-asserted-by":"crossref","first-page":"105020","DOI":"10.1016\/j.compbiomed.2021.105020","article-title":"COVID-19 cough sound symptoms classification from scalogram image representation using deep learning models","volume":"139","author":"M Loey","year":"2021","journal-title":"Comput Biol Med"},{"key":"pone.0348508.ref016","doi-asserted-by":"crossref","first-page":"104580","DOI":"10.1016\/j.bspc.2023.104580","article-title":"Cough sound detection from raw waveform using SincNet and bidirectional GRU","volume":"82","author":"RV Sharan","year":"2023","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0348508.ref017","doi-asserted-by":"crossref","first-page":"106165","DOI":"10.1016\/j.bspc.2024.106165","article-title":"SUPER-COUGH: A Super Learner-based ensemble machine learning method for detecting disease on cough acoustic signals","volume":"93","author":"EK Topuz","year":"2024","journal-title":"Biomedical Signal Processing and Control"},{"issue":"1","key":"pone.0348508.ref018","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1186\/s12911-025-03065-w","article-title":"Deep learning-based cough classification using application-recorded sounds: a transfer learning approach with VGGish","volume":"25","author":"S Han","year":"2025","journal-title":"BMC Med Inform Decis Mak"},{"key":"pone.0348508.ref019","doi-asserted-by":"crossref","first-page":"102486","DOI":"10.1016\/j.artmed.2022.102486","article-title":"The voice of COVID-19: Breath and cough recording classification with temporal decision trees and random forests","volume":"137","author":"F Manzella","year":"2023","journal-title":"Artif Intell Med"},{"key":"pone.0348508.ref020","doi-asserted-by":"crossref","first-page":"105093","DOI":"10.1016\/j.ijmedinf.2023.105093","article-title":"Detecting acute respiratory diseases in the pediatric population using cough sound features and machine learning: A systematic review","volume":"176","author":"RV Sharan","year":"2023","journal-title":"Int J Med Inform"},{"key":"pone.0348508.ref021","doi-asserted-by":"crossref","first-page":"21262","DOI":"10.1109\/ACCESS.2024.3361943","article-title":"Lung Sound Classification With Multi-Feature Integration Utilizing Lightweight CNN Model","volume":"12","author":"T Wanasinghe","year":"2024","journal-title":"IEEE Access"},{"issue":"6","key":"pone.0348508.ref022","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3637487","article-title":"Explainable AI for Medical Data: Current Methods, Limitations, and Future Directions","volume":"57","author":"MI Hossain","year":"2025","journal-title":"ACM Comput Surv"},{"issue":"4","key":"pone.0348508.ref023","doi-asserted-by":"crossref","DOI":"10.1016\/S2589-7500(22)00029-2","article-title":"Explainability and artificial intelligence in medicine","volume":"4","author":"S Reddy","year":"2022","journal-title":"The Lancet Digital Health"},{"issue":"4","key":"pone.0348508.ref024","doi-asserted-by":"crossref","DOI":"10.1002\/widm.1312","article-title":"Causability and explainability of artificial intelligence in medicine","volume":"9","author":"A Holzinger","year":"2019","journal-title":"Wiley Interdiscip Rev Data Min Knowl Discov"},{"key":"pone.0348508.ref025","doi-asserted-by":"crossref","first-page":"133184","DOI":"10.1016\/j.physd.2022.133184","article-title":"Complex network-based pertussis and croup cough analysis: A machine learning approach","volume":"433","author":"A Renjini","year":"2022","journal-title":"Physica D: Nonlinear Phenomena"},{"issue":"7","key":"pone.0348508.ref026","article-title":"Predictive ability of artificial intelligence algorithms in pediatric respiratory disease diagnosis using cough sounds: a systematic review","volume":"17","author":"AAI Abdelhalim","year":"2025","journal-title":"Cureus"},{"key":"pone.0348508.ref027","doi-asserted-by":"crossref","DOI":"10.34133\/icomputing.0074","article-title":"Audio Explainable Artificial Intelligence: A Review","volume":"3","author":"A Akman","year":"2024","journal-title":"Intell Comput"},{"issue":"2","key":"pone.0348508.ref028","doi-asserted-by":"crossref","first-page":"634","DOI":"10.3390\/s23020634","article-title":"Survey of Explainable AI Techniques in Healthcare","volume":"23","author":"A Chaddad","year":"2023","journal-title":"Sensors (Basel)"},{"issue":"6","key":"pone.0348508.ref029","doi-asserted-by":"crossref","first-page":"5261","DOI":"10.1007\/s10462-022-10304-3","article-title":"Explainable AI for clinical and remote health applications: a survey on tabular and time series data","volume":"56","author":"F Di Martino","year":"2023","journal-title":"Artif Intell Rev"},{"key":"pone.0348508.ref030","article-title":"Improving the Robustness and Clinical Applicability of Automatic Respiratory Sound Classification Using Deep Learning-Based Audio Enhancement: Algorithm Development and Validation","volume":"4","author":"J-T Tzeng","year":"2025","journal-title":"JMIR AI"},{"key":"pone.0348508.ref031","unstructured":"Morshed MM, Ahsan AO, Mahmud H, Hasan MK. Learning audio representations with mlps. In: 2022. https:\/\/arxiv.org\/abs\/2203.08490"},{"issue":"1","key":"pone.0348508.ref032","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.jvoice.2020.02.009","article-title":"Classification of Voice Disorders Using a One-Dimensional Convolutional Neural Network","volume":"36","author":"S Fujimura","year":"2022","journal-title":"J Voice"},{"key":"pone.0348508.ref033","doi-asserted-by":"crossref","unstructured":"Pellegrini T, Khalfaoui-Hassani I, Labb\u00e9 E, Masquelier T. Adapting a ConvNeXt model to audio classification on AudioSet. 2023. https:\/\/arxiv.org\/abs\/230600830","DOI":"10.21437\/Interspeech.2023-1564"},{"key":"pone.0348508.ref034","doi-asserted-by":"crossref","unstructured":"Chen J, Hao J, Chen K, Xie D, Yang S, Pu S. An end-to-end audio classification system based on raw waveforms and mix-training strategy. 2019. https:\/\/arxiv.org\/abs\/1911.09349","DOI":"10.21437\/Interspeech.2019-1579"},{"issue":"7","key":"pone.0348508.ref035","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.3390\/electronics13071177","article-title":"Advancing Cough Classification: Swin Transformer vs. 2D CNN with STFT and Augmentation Techniques","volume":"13","author":"M Ghourabi","year":"2024","journal-title":"Electronics"},{"issue":"17","key":"pone.0348508.ref036","doi-asserted-by":"crossref","first-page":"17644","DOI":"10.1609\/aaai.v39i17.33940","article-title":"M3Net: Efficient Time-Frequency Integration Network with Mirror Attention for Audio Classification on Edge","volume":"39","author":"X Jiang","year":"2025","journal-title":"AAAI"},{"key":"pone.0348508.ref037","doi-asserted-by":"crossref","first-page":"2975","DOI":"10.1109\/LSP.2024.3483009","article-title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","volume":"31","author":"MH Erol","year":"2024","journal-title":"IEEE Signal Process Lett"},{"key":"pone.0348508.ref038","doi-asserted-by":"crossref","unstructured":"Dibbo SV, Moore JS, Kenyon GT, Teti MA. LCANets++: Robust Audio Classification Using Multi-Layer Neural Networks with Lateral Competition. In: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), 2024. 129\u201333. https:\/\/doi.org\/10.1109\/icasspw62465.2024.10627668","DOI":"10.1109\/ICASSPW62465.2024.10627668"},{"key":"pone.0348508.ref039","doi-asserted-by":"crossref","unstructured":"Wanasinghe T, Bandara S, Madusanka S, Meedeniya D, Bandara M. CNN-based Optimization for Lung Sound Classification with Mobile Accessibility. In: 2024 International Research Conference on Smart Computing and Systems Engineering (SCSE), 2024. 1\u20136. https:\/\/doi.org\/10.1109\/scse61872.2024.10550572","DOI":"10.1109\/SCSE61872.2024.10550572"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T17:46:09Z","timestamp":1777916769000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348508"}},"subtitle":[],"editor":[{"given":"Jie","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,4]]},"references-count":39,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,4]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0348508","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,4]]}}}