[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125096-en":3,"doc-seo-125096-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125096,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Acoustic and Clinical Data Analysis of Vocal Recordings - Pandemic Insights and Lessons","The COVID-19 pandemic accelerated interest in processing human speech and other audio signals as diagnostic tools. The OSCAR (vOice Screening of CoronA viRus) project developed an algorithm using Portuguese participants’ voice recordings and clinical data. A cross-sectional study characterised sound patterns from vocal apparatus in RT-PCR confirmed SARS-CoV-2 infection and built a screening model. Phase I training used 166 subjects and Phase II validation involved 58 participants, yielding 85% sensitivity, 88.9% specificity, and 84.7% F1-score.","diagnostics  \nArticle  \nAcoustic and Clinical Data Analysis of Vocal Recordings: Pandemic Insights and Lessons  \nPedro Carreiro-Martins 1,2,*, Paulo Paixão 1, Iolanda Caires 1, Pedro Matias 3, Hugo Gamboa 3,4, Filipe Soares 3, Pedro Gomez 5, Joana Sousa 6 and Nuno Neuparth 1,2  \nCitation: Carreiro-Martins, P.; Paixão, P.; Caires, I.; Matias, P.; Gamboa, H.; Soares, F.; Gomez, P.; Sousa, J.; Neuparth, N. Acoustic and Clinical Data Analysis of Vocal Recordings:  \nPandemic Insights and Lessons. Diagnostics 2024, 14, 2273. [https://](https://)[ ](https://)[doi.org/10.3390/diagnostics14202273](doi.org/10.3390/diagnostics14202273)  \nAcademic Editor: Juan Rafael Orozco-Arroyave  \nReceived: 16 August 2024  \nRevised: 3 October 2024  \nAccepted: 9 October 2024  \nPublished: 12 October 2024  \nCopyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 Comprehensive Health Research Center (CHRC), LA-REAL, NOVA Medical School, Campo Mártires da Pátria, 130, 1169-056 Lisboa, Portugal; [nneuparth@gmail.com](nneuparth@gmail.com) (N.N.)  \n2 Serviço de Imunoalergologia, Hospital de Dona Estefânia, ULS São José, Rua Jacinta Marto, 1169-045 Lisbon, Portugal  \n3 Fraunhofer Portugal AICOS, Rua Alfredo Allen 455/461, 4200-135 Porto, Portugal; [filipe.soares@aicos.fraunhofer.pt](filipe.soares@aicos.fraunhofer.pt) (F.S.)  \n4 Laboratory for Instrumentation, Biomedical Engineering and Radiation Physics (LIBPhys), Faculdade de Ciências e Tecnologia, NOVA University of Lisbon, Caparica, 2820-001 Lisbon, Portugal  \n5 NeuSpeLab, CTB, Universidad Politécnica de Madrid, Campus de Montegancedo, s/n, 28223 Madrid, Spain; [pedrogvilda@telefonica.net](pedrogvilda@telefonica.net)  \n6 NOS Inovação, Rua Actor António Silva, 9–6◦ Piso, Campo Grande, 1600-404 Lisboa, Portugal  \n* [Correspondence: pmartinsalergo@gmail.com](Correspondence: pmartinsalergo@gmail.com)  \nAbstract: Background/Objectives: The interest in processing human speech and other humangenerated audio signals as a diagnostic tool has increased due to the COVID-19 pandemic. The project OSCAR (vOice Screening of CoronA viRus) aimed to develop an algorithm to screen for COVID-19 using a dataset of Portuguese participants with voice recordings and clinical data. Methods: This cross-sectional study aimed to characterise the pattern of sounds produced by the vocal apparatus in patients with SARS-CoV-2 infection documented by a positive RT-PCR test, and to develop and validate a screening algorithm. In Phase II, the algorithm developed in Phase I was tested in areal-world setting. Results: In Phase I, after filtering, the training group consisted of 166 subjects who were effectively available to train the classification model (34.3% SARS-CoV-2 positive/65.7% SARS-CoV-2 negative) . Phase II enrolled 58 participants (69.0% SARS-CoV-2 positive/31.0% SARSCoV-2 negative) . The final model achieved a sensitivity of 85%, a specificity of 88.9%, and an F1-score of 84.7%, suggesting voice screening algorithms as an attractive strategy for COVID-19 diagnosis. Conclusions: Our findings highlight the potential of a voice-based detection strategy as an alternative method for respiratory tract screening.  \nKeywords: diagnostic tests; machine learning; SARS-CoV-2; speech; voice  \n1. Introduction  \nDiseases of the respiratory tract frequently affect the vocal apparatus, which leads to changes in the timbre of the voice.  \nAnalysing the voice and other audio signals is an attractive tool for screening diseases, as sound recordings are easy to obtain and non-invasive [1–3] . However, due to the subtle changes in voice and cough characteristics, artificial intelligence techniques are required to recognise specific disease patterns [4","cbCaigdM4JkADheZ","https://ap.wps.com/l/cbCaigdM4JkADheZ","pdf",2996036,1,16,"English","en",105,"# Introduction\n## Respiratory diseases and vocal changes\n## COVID-19 pandemic and audio-based diagnosis\n## Respiratory audio datasets and prior ML approaches\n## Study aims","[{\"question\":\"What problem does this study address?\",\"answer\":\"It explores whether acoustic analysis of voice recordings can support COVID-19 screening by detecting patterns related to SARS-CoV-2 infection.\"},{\"question\":\"How was the screening algorithm developed and tested?\",\"answer\":\"The study first trained a model in Phase I using labeled training data, then evaluated it in Phase II in a real-world setting.\"},{\"question\":\"What diagnostic performance did the final model achieve?\",\"answer\":\"The final model reported 85% sensitivity, 88.9% specificity, and an F1-score of 84.7%.\"}]","Acoustic and Clinical Data Analysis of Vocal Recordings - Pandemic Insights and Lessons | PDF",1785896617,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"acoustic-and-clinical-data-analysis-of-vocal-recordings-pandemic-insights-and-lessons","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/acoustic-and-clinical-data-analysis-of-vocal-recordings-pandemic-insights-and-lessons/125096/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does this study address?","Question",{"text":75,"@type":76},"It explores whether acoustic analysis of voice recordings can support COVID-19 screening by detecting patterns related to SARS-CoV-2 infection.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How was the screening algorithm developed and tested?",{"text":80,"@type":76},"The study first trained a model in Phase I using labeled training data, then evaluated it in Phase II in a real-world setting.",{"name":82,"@type":73,"acceptedAnswer":83},"What diagnostic performance did the final model achieve?",{"text":84,"@type":76},"The final model reported 85% sensitivity, 88.9% specificity, and an F1-score of 84.7%.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]