{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T13:24:12Z","timestamp":1787145852664,"version":"build-2736575974"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100005614","name":"Biogen","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005614","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004238","name":"Universit\u00e4t Potsdam","doi-asserted-by":"publisher","award":["491466077"],"award-info":[{"award-number":["491466077"]}],"id":[{"id":"10.13039\/501100004238","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:p>\n                    Reference intervals (RIs) are a well-established clinical tool for defining healthy bounds of laboratory measures. Recently, they have been applied to acoustic features extracted from speech to provide a transparent and disorder-agnostic perspective on symptomatic speakers. We evaluate the potential and limitations of RIs across three datasets: clean, laboratory recordings from people with multiple sclerosis (pwMS) and two noisy datasets targeting respiratory symptoms and work-related stress, collected under everyday-life conditions. At the population level, we compare the proportion of features outside the RI bounds between control and symptomatic groups, test noise augmentation of the RI-estimation corpus for improved robustness, and identify the most indicative acoustic features for each health condition. At the individual level, we derive a per-speaker deviation score that quantifies how far each speaker\u2019s acoustic profile deviates from the healthy reference, and assess its discriminative ability using the area under the receiver operating characteristic curve (AUC). Noise augmentation of the healthy reference corpus yields similar population-level separation; the continuous\n                    <jats:inline-formula>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" id=\"IM1\">\n                        <mml:msub>\n                          <mml:mrow>\n                            <mml:mi mathvariant=\"normal\">DS<\/mml:mi>\n                          <\/mml:mrow>\n                          <mml:mrow>\n                            <mml:mrow>\n                              <mml:mi mathvariant=\"normal\">Q<\/mml:mi>\n                              <mml:mn>123<\/mml:mn>\n                            <\/mml:mrow>\n                          <\/mml:mrow>\n                        <\/mml:msub>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    deviation score yielded 12 features that remained significant after global Benjamini\u2013Hochberg false discovery rate (FDR) correction. The individual-level deviation score achieves promising discrimination for male pwMS (\n                    <jats:inline-formula>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" id=\"IM2\">\n                        <mml:mrow>\n                          <mml:mi mathvariant=\"normal\">AUC<\/mml:mi>\n                        <\/mml:mrow>\n                        <mml:mo>=<\/mml:mo>\n                        <mml:mn>0.97<\/mml:mn>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    for read speech), even in a clinically mild cohort, while results for audRespire and the work-related stress dataset remain limited at both levels. RIs show promise as interpretable, disorder-agnostic markers for speech-based health assessment; the individual-level deviation score complements the population-level analysis by providing a per-speaker health indicator that can surface deviations masked in group-level comparisons.\n                  <\/jats:p>","DOI":"10.3389\/fdgth.2026.1870061","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T12:30:03Z","timestamp":1787142603000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Outside the healthy bounds: reference intervals for population and individual-level medical speech analysis"],"prefix":"10.3389","volume":"8","author":[{"given":"Pascal","family":"Hecker","sequence":"first","affiliation":[{"name":"Digital Health\u2014Connected Healthcare, Hasso Plattner Institute, University of Potsdam","place":["Potsdam, Germany"]},{"name":"audEERING GmbH","place":["Gilching, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Monica","family":"Gonzalez-Machorro","sequence":"additional","affiliation":[{"name":"audEERING GmbH","place":["Gilching, Germany"]},{"name":"CHI\u2014Chair of Health Informatics, TUM University Hospital","place":["Munich, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catarina","family":"Botelho","sequence":"additional","affiliation":[{"name":"HLT\u2014Human Language Technologies Lab, INESC-ID","place":["Lisbon, Portugal"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helly","family":"Hammer","sequence":"additional","affiliation":[{"name":"Department of Neurology, Inselspital and University of Bern","place":["Bern, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hesam","family":"Sagha","sequence":"additional","affiliation":[{"name":"audEERING GmbH","place":["Gilching, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Kahlau","sequence":"additional","affiliation":[{"name":"audEERING GmbH","place":["Gilching, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Hoepner","sequence":"additional","affiliation":[{"name":"Department of Neurology, Inselspital and University of Bern","place":["Bern, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Eyben","sequence":"additional","affiliation":[{"name":"audEERING GmbH","place":["Gilching, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"audEERING GmbH","place":["Gilching, Germany"]},{"name":"CHI\u2014Chair of Health Informatics, TUM University Hospital","place":["Munich, Germany"]},{"name":"GLAM\u2014Group on Language, Audio, & Music, Imperial College London","place":["London, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bert","family":"Arnrich","sequence":"additional","affiliation":[{"name":"Digital Health\u2014Connected Healthcare, Hasso Plattner Institute, University of Potsdam","place":["Potsdam, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1159\/000515346","article-title":"Voice for health: the use of vocal biomarkers from research to clinical practice","volume":"5","author":"Fagherazzi","year":"2021","journal-title":"Digit Biomarkers"},{"key":"B2","doi-asserted-by":"publisher","first-page":"842301","DOI":"10.3389\/fdgth.2022.842301","article-title":"Voice analysis for neurological disorder recognition\u2014a systematic review and perspective on emerging trends","volume":"4","author":"Hecker","year":"2022","journal-title":"Front Digit Health"},{"key":"B3","doi-asserted-by":"publisher","first-page":"184487","DOI":"10.1109\/ACCESS.2024.3506433","article-title":"Speech as a biomarker for disease detection","volume":"12","author":"Botelho","year":"2024","journal-title":"IEEE Access"},{"key":"B4","author":"Botelho","year":""},{"key":"B5","author":"Orozco-Arroyave","year":""},{"key":"B6","author":"Luz","year":""},{"key":"B7","author":"White","year":""},{"key":"B8","author":"Gonzalez-Machorro","year":""},{"key":"B9","doi-asserted-by":"publisher","first-page":"1721274","DOI":"10.3389\/fdgth.2026.1721274","article-title":"Listening to MS: AI-assisted speech analysis for diagnosis and fatigue prediction (COMMITMENT)","volume":"8","author":"Hammer","year":"2026","journal-title":"Front Digit Health"},{"key":"B10","first-page":"29","article-title":"Mental wellbeing at sea: a prototype to collect speech data in maritime settings","volume-title":"Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies \u2013 Volume 2: HEALTHINF","author":"Hecker","year":"2025"},{"key":"B11","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1007\/s42979-026-05107-0","article-title":"Mental wellbeing at sea: active and passive speech monitoring in a maritime setting","volume":"7","author":"Hecker","year":"2026","journal-title":"SN Comput Sci"},{"key":"B12","author":"Hecker","year":""},{"key":"B13","author":"Haulcy","year":""},{"key":"B14","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.1177\/1352458509348519","article-title":"The fatigue scale for motor and cognitive functions (FSMC): validation of a new instrument to assess multiple sclerosis-related fatigue","volume":"15","author":"Penner","year":"2009","journal-title":"Mult Scler J"},{"key":"B15","author":"Gonzalez-Machorro","year":""},{"key":"B16","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1017\/S0025100300004084","volume":"20","author":"Kohler","year":"1990","journal-title":"J Int Phon Assoc"},{"key":"B17","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00995674","article-title":"Vocal cues in emotion encoding and decoding","volume":"15","author":"Scherer","year":"1991","journal-title":"Motiv Emot"},{"key":"B18","author":"Mittag","year":""},{"key":"B19","author":"Snyder","year":""},{"key":"B20","first-page":"341","article-title":"Praat, a system for doing phonetics by computer","volume":"5","author":"Boersma","year":"2001","journal-title":"Glot Int"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.wocn.2018.07.001","article-title":"Introducing Parselmouth: a Python interface to Praat","volume":"71","author":"Jadoul","year":"2018","journal-title":"J Phon"},{"key":"B22","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","article-title":"The meaning and use of the area under a receiver operating characteristic (ROC) curve","volume":"143","author":"Hanley","year":"1982","journal-title":"Radiology"},{"key":"B23","doi-asserted-by":"publisher","first-page":"879.e13","DOI":"10.1016\/j.jvoice.2020.09.024","article-title":"Voice quality evaluation in patients with COVID-19: An acoustic analysis","volume":"36","author":"Asiaee","year":"2022","journal-title":"J Voice"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1994","DOI":"10.3389\/fpsyg.2018.01994","article-title":"Voice stress analysis: a new framework for voice and effort in human performance","volume":"9","author":"Van Puyvelde","year":"2018","journal-title":"Front Psychol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1075736","DOI":"10.3389\/fneur.2023.1075736","article-title":"Articulatory speech measures can be related to the severity of multiple sclerosis","volume":"14","author":"Kieling","year":"2023","journal-title":"Front Neurol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1186\/s40001-023-01230-3","article-title":"Speech deficits in multiple sclerosis: a narrative review of the existing literature","volume":"28","author":"Plotas","year":"2023","journal-title":"Eur J Med Res"},{"key":"B27","doi-asserted-by":"publisher","first-page":"351","DOI":"10.2307\/2087176","article-title":"Ecological correlations and the behavior of individuals","volume":"15","author":"Robinson","year":"1950","journal-title":"Am Sociol Rev"},{"key":"B28","doi-asserted-by":"publisher","first-page":"e42886","DOI":"10.2196\/42886","article-title":"Association between acoustic features and neuropsychological test performance in the framingham heart study: observational study","volume":"24","author":"Ding","year":"2022","journal-title":"J Med Internet Res"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1870061\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T12:30:05Z","timestamp":1787142605000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1870061\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,19]]},"references-count":28,"alternative-id":["10.3389\/fdgth.2026.1870061"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2026.1870061","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,19]]},"article-number":"1870061"}}