{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T06:01:47Z","timestamp":1785391307806,"version":"3.55.0"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T00:00:00Z","timestamp":1785369600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Respiratory complaints account for a substantial share of adult ambulatory visits, and accurate triage has direct consequences for antibiotic stewardship and pathogen-specific therapy. Prior work has investigated voice as a triage signal, but that literature is dominated by single-condition detection from scripted speech in crowdsourced or controlled clinical settings and has not been evaluated at the primary care scale using conversational ambient audio.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A dataset of 514,377 ambient-recorded primary care visits from 379,225 adult patients at a US clinic network was used, with per-visit clinically assigned ICD-10 diagnosis codes and de-identified demographic and geographic metadata. Patient audio was extracted from each doctor-patient conversation, and spectral, voice quality, and prosodic features were computed. Eleven binary classification tasks were defined, aligned with a respiratory triage cascade (e.g., acute respiratory vs. acute non-respiratory illness, and lower vs. upper respiratory tract infection). An acoustic model was trained independently for each task using patient-stratified 5-fold cross-validation and evaluated on a held-out test set. Each model was also compared against six non-acoustic baselines using a single demographic, geographic, or temporal variable. The 11 trained classifiers were combined into a hierarchical cascade and illustrated as case studies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Test-set AUC across the 11 tasks ranged from 0.602 (95% CI: 0.588\u20130.614) to 0.745 (95% CI: 0.742\u20130.748), with a mean expected calibration error of 0.018. After multiple-testing correction, six of the eleven binaries outperformed all six confounder baselines. Four binaries showed a median within-stratum AUC of 0.61\u20130.70 when the confounder was held fixed, indicating acoustic discrimination beyond what the confounder alone explains. Five binaries failed at least one axis; the only one outperformed by a confounder baseline was the pneumonia vs. non-pneumonia lower respiratory tract infection binary, which failed against the patient-city confounder baseline, plausibly reflecting a clinic-level difference in ICD-10 coding.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Conversational primary care audio contains an acoustic signal that discriminates clinically meaningful respiratory contrasts. Absolute performance is moderate, but the conditions are stricter than in prior work: conversational speech and differential-diagnosis contrasts among patients with illness. This pilot study establishes a baseline for voice-based clinical AI, advancing from sick-vs.-healthy detection toward differential-diagnosis panels and demonstrating a proof of concept for hierarchical composition.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1895376","type":"journal-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T05:40:07Z","timestamp":1785390007000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Conversational speech for respiratory triage in primary care: a pilot study"],"prefix":"10.3389","volume":"13","author":[{"given":"Vijay","family":"Ravi","sequence":"first","affiliation":[{"name":"Amplifier Health, Inc., San Francisco","place":["CA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Camille","family":"Noufi","sequence":"additional","affiliation":[{"name":"Amplifier Health, Inc., San Francisco","place":["CA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,30]]},"reference":[{"key":"B1","unstructured":"Preliminary Estimates of Visits to Health Centers in the United States, January 2022-December 2025\n          \n          2025"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1864","DOI":"10.1001\/jama.2016.4151","article-title":"Prevalence of inappropriate antibiotic prescriptions among US ambulatory care visits, 2010-2011","volume":"315","author":"Fleming-Dutra","year":"2016","journal-title":"JAMA"},{"key":"B3","unstructured":"Antibiotic Resistance Threats in the United States, 2019\n          \n          2019"},{"key":"B4","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1001\/jamainternmed.2013.2777","article-title":"Types and origins of diagnostic errors in primary care settings","volume":"173","author":"Singh","year":"2013","journal-title":"JAMA Intern Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e1","DOI":"10.1093\/cid\/ciy866","article-title":"Clinical practice guidelines by the infectious diseases society of America: 2018 update on diagnosis, treatment, chemoprophylaxis, and institutional outbreak management of seasonal influenza","volume":"68","author":"Uyeki","year":"2019","journal-title":"Clin Infect Dis"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.1056\/NEJMoa2118542","article-title":"Oral nirmatrelvir for high-risk, nonhospitalized adults with COVID-19","volume":"386","author":"Hammond","year":"2022","journal-title":"N Engl J Med"},{"key":"B7","volume-title":"Speech and Voice Science","author":"Behrman","year":"2023"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e163","DOI":"10.1597\/14-236","article-title":"Application of linear discriminant analysis to the long-term averaged spectra of simulated disorders of oral-nasal balance","volume":"53","author":"de Boer","year":"2016","journal-title":"Cleft Palate-Craniofacial J"},{"key":"B9","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1016\/j.jvoice.2021.09.038","article-title":"Sensation and repercussion of the use of humid heat in the treatment of dysphonia due to laryngitis in singers","volume":"38","author":"Pimenta","year":"2022","journal-title":"J Voice"},{"key":"B10","doi-asserted-by":"publisher","first-page":"108012","DOI":"10.1016\/j.rmed.2025.108012","article-title":"Assessment of breathing patterns and voice of patients with COPD and dysphonia","volume":"240","author":"Weglarz","year":"2025","journal-title":"Respir Med"},{"key":"B11","doi-asserted-by":"publisher","first-page":"e2534976","DOI":"10.1001\/jamanetworkopen.2025.34976","article-title":"Use of ambient AI scribes to reduce administrative burden and professional burnout","volume":"8","author":"Olson","year":"2025","journal-title":"JAMA Netw Open"},{"key":"B12","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1093\/jamia\/ocae295","article-title":"Ambient artificial intelligence scribes: physician burnout and perspectives on usability and documentation burden","volume":"32","author":"Shah","year":"2025","journal-title":"J Am Med Inform Assoc"},{"key":"B13","unstructured":"COVID-19 sounds: a large-scale audio dataset for digital respiratory screening\n          \n          \n            \n              Xia\n              T\n            \n            \n              Spathis\n              D\n            \n            \n              Brown\n              C\n            \n            \n              Chauhan\n              J\n            \n            \n              Grammenos\n              A\n            \n            \n              Han\n              J\n            \n          \n          Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track\n          \n          2021"},{"key":"B14","doi-asserted-by":"publisher","first-page":"901","DOI":"10.21437\/Interspeech.2021-74","article-title":"DiCOVA challenge: dataset, task, and baseline system for COVID-19 diagnosis using acoustics","author":"Muguli","year":"2021","journal-title":"Proc. Interspeech 2021"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1149","DOI":"10.1038\/s41597-024-03972-z","article-title":"A dataset of solicited cough sound for tuberculosis triage testing","volume":"11","author":"Huddart","year":"2024","journal-title":"Sci Data"},{"key":"B16","doi-asserted-by":"publisher","first-page":"105014","DOI":"10.1088\/1361-6579\/ac2fb8","article-title":"automatic cough classification for tuberculosis screening in a real-world environment","volume":"42","author":"Pahar","year":"2021","journal-title":"Physiol Meas"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e44410","DOI":"10.2196\/44410","article-title":"Development and validation of a respiratory-responsive vocal biomarker-based tool for generalizable detection of respiratory impairment: independent case-control studies in multiple respiratory conditions including asthma, chronic obstructive pulmonary disease, and COVID-19","volume":"25","author":"Kaur","year":"2023","journal-title":"J Med Internet Res"},{"key":"B18","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1186\/s12931-019-1046-6","article-title":"A prospective multicentre study testing the diagnostic accuracy of an automated cough sound centred analytic system for the identification of common respiratory disorders in children","volume":"20","author":"Porter","year":"2019","journal-title":"Respir Res"},{"key":"B19","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1038\/s41597-023-02266-0","article-title":"Coswara: a respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection","volume":"10","author":"Bhattacharya","year":"2023","journal-title":"Sci Data"},{"key":"B20","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41597-021-00937-4","article-title":"The COUGHVID crowdsourcing dataset, a corpus for the study of large-scale cough analysis algorithms","volume":"8","author":"Orlandic","year":"2021","journal-title":"Sci Data"},{"key":"B21","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1109\/ICASSP43922.2022.9747188","article-title":"The second DiCOVA challenge: dataset and performance analysis for diagnosis of covid-19 using acoustics","author":"Sharma","year":"2022","journal-title":"Proc. IEEE international conference on acoustics, speech and signal processing (ICASSP)"},{"key":"B22","author":"Chaudhari","year":"2020","journal-title":"Virufy: Global Applicability of Crowdsourced and Clinical Datasets for AI Detection of COVID-19 from Cough"},{"key":"B23","doi-asserted-by":"publisher","first-page":"154087","DOI":"10.1109\/ACCESS.2020.3018028","article-title":"Novel coronavirus cough database: NoCoCoDa","volume":"8","author":"Cohen-McFarlane","year":"2020","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"publisher","first-page":"045005","DOI":"10.1088\/1361-6579\/aab6d0","article-title":"Detection of tuberculosis by automatic cough sound analysis","volume":"39","author":"Botha","year":"2018","journal-title":"Physiol Meas"},{"key":"B25","doi-asserted-by":"publisher","first-page":"eadi0282","DOI":"10.1126\/sciadv.adi0282","article-title":"TBscreen: a passive cough classifier for tuberculosis screening with a controlled dataset","volume":"10","author":"Sharma","year":"2024","journal-title":"Sci Adv"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.1016\/j.mayocp.2023.03.007","article-title":"Guess what we can hear\u2013novel voice biomarkers for the remote detection of disease","volume":"98","author":"Sara","year":"2023","journal-title":"Mayo Clin Proc"},{"key":"B27","doi-asserted-by":"publisher","first-page":"28682","DOI":"10.1038\/s41598-025-14645-1","article-title":"Non-invasive acoustic classification of adult asthma using an XGBoost model with vocal biomarkers","volume":"15","author":"Lyu","year":"2025","journal-title":"Sci Rep"},{"key":"B28","doi-asserted-by":"publisher","first-page":"108796","DOI":"10.1016\/j.cmpb.2025.108796","article-title":"Developing a multi-feature fusion model for exacerbation classification in asthma and COPD","volume":"268","author":"Yan","year":"2025","journal-title":"Comput Methods Programs Biomed"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.5152\/balkanmedj.2014.14511","article-title":"Comparison of acoustic and stroboscopic findings and voice handicap index between allergic rhinitis patients and controls","author":"Ko\u00e7","year":"2014","journal-title":"Balkan Med J"},{"key":"B30","doi-asserted-by":"publisher","first-page":"e0275479","DOI":"10.1371\/journal.pone.0275479","article-title":"A classification framework for identifying bronchitis and pneumonia in children based on a small-scale cough sounds dataset","volume":"17","author":"Liao","year":"2022","journal-title":"PLoS ONE"},{"key":"B31","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1109\/JBHI.2023.3327292","article-title":"Automated cough sound analysis for detecting childhood pneumonia","volume":"28","author":"Sharan","year":"2024","journal-title":"IEEE J Biomed Health Inform"},{"key":"B32","doi-asserted-by":"publisher","first-page":"432","DOI":"10.2500\/ajr.2006.20.2882","article-title":"Changes in nasal resonance after functional endoscopic sinus surgery","volume":"20","author":"Jiang","year":"2006","journal-title":"Am J Rhinol"},{"key":"B33","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1597\/1545-1569_1993_030_0421_paaaco_2.3.co_2","article-title":"Peritonsillar abscess as a cause of transient velopharyngeal insufficiency","volume":"30","author":"Finkelstein","year":"1993","journal-title":"Cleft Palate-Craniofacial J"},{"key":"B34","doi-asserted-by":"publisher","first-page":"3474","DOI":"10.1145\/3394486.3412865","article-title":"Exploring automatic diagnosis of COVID-19 from crowdsourced respiratory sound data","author":"Brown","year":"2020","journal-title":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1121\/10.0003434","article-title":"Artificial intelligence enabled preliminary diagnosis for COVID-19 from voice cues and questionnaires","volume":"149","author":"Shimon","year":"2021","journal-title":"J Acoust Soc Am"},{"key":"B36","doi-asserted-by":"publisher","first-page":"105153","DOI":"10.1016\/j.compbiomed.2021.105153","article-title":"COVID-19 detection in cough, breath and speech using deep transfer learning and bottleneck features","volume":"141","author":"Pahar","year":"2021","journal-title":"Comput Biol Med"},{"key":"B37","doi-asserted-by":"publisher","first-page":"cnab039","DOI":"10.1093\/comnet\/cnab039","article-title":"Graph-based feature extraction and classification of wet and dry cough signals: a machine learning approach","volume":"9","author":"Renjini","year":"2021","journal-title":"J Complex Netw"},{"key":"B38","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","article-title":"The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for voice research and affective computing","volume":"7","author":"Eyben","year":"2016","journal-title":"IEEE Trans Affect Comput"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1459","DOI":"10.1145\/1873951.1874246","article-title":"openSMILE: the Munich versatile and fast open-source audio feature extractor","author":"Eyben","year":"2010","journal-title":"Proceedings of the 18th ACM international conference on multimedia (MM '10)"},{"key":"B40","doi-asserted-by":"publisher","first-page":"18","DOI":"10.25080\/Majora-7b98e3ed-003","article-title":"librosa: audio and music signal analysis in Python","author":"McFee","year":"2015","journal-title":"Proceedings of the 14th Python in science conference (SciPy 2015)"},{"key":"B41","doi-asserted-by":"publisher","first-page":"247","DOI":"10.21437\/odyssey.2024-35","article-title":"Odyssey 2024 - speech emotion recognition challenge: dataset, baseline framework, and results","author":"Goncalves","year":"2024","journal-title":"The speaker and language recognition workshop (Odyssey 2024)"},{"key":"B42","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"International conference on learning representations (ICLR)"},{"key":"B43","article-title":"SGDR: stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2017","journal-title":"International conference on learning representations (ICLR)"},{"key":"B44","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","article-title":"Index for rating diagnostic tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer"},{"key":"B45","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J R Stat Soc: Ser B (Methodol)"},{"key":"B46","doi-asserted-by":"publisher","first-page":"195","DOI":"10.4103\/tjem.tjem_182_23","article-title":"Receiver operating characteristic curve analysis in diagnostic accuracy studies: a guide to interpreting the area under the curve value","volume":"23","author":"\u00c7orbac\u0131o\u011flu","year":"2023","journal-title":"Turk J Emerg Med"},{"key":"B47","doi-asserted-by":"publisher","first-page":"110076","DOI":"10.1016\/j.annepidem.2026.110076","article-title":"Cough acoustic analysis using artificial intelligence for COVID-19 detection: a comparative study of patient cohorts from Lima, Peru and Montreal, Canada","volume":"118","author":"Zimmer","year":"2026","journal-title":"Ann Epidemiol"},{"key":"B48","doi-asserted-by":"publisher","first-page":"50492","DOI":"10.1038\/s41598-026-50492-4","article-title":"External validation of|AQQ20 cough-based algorithms for pulmonary tuberculosis screening from the CODA TB DREAM challenge using cough data from Peru","volume":"16","author":"Zimmer","year":"2026","journal-title":"Sci Rep"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1895376\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T05:40:09Z","timestamp":1785390009000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1895376\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,30]]},"references-count":48,"alternative-id":["10.3389\/fmed.2026.1895376"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1895376","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,30]]},"article-number":"1895376"}}