{
  "abstract": "Patient narratives can reveal aspects of health that standardized measures miss, yet collecting open-ended responses at population scale remains difficult. We evaluated whether speech-to-text (STT) could enable richer responses in online health surveys without the resource demands of interviews. Across four surveys involving people with post-COVID-19 condition, healthy adults, people who engage in sex work, and older adults, participants could answer open-ended questions by typing or using STT. We compared response length, lexical diversity, stop-word proportion, and total unique content words, alongside STT uptake and participant feedback. Quantitative comparisons were made using a mixed-effects model including modality (STT vs typed) as fixed effect and a random intercept per participant. STT uptake varied markedly across populations (0.7-80.0%). Spoken responses were estimated to contain more characters than typed responses in two studies, by 245.0 and 891.8 characters on average (both p<0.001), and contained more unique content words, despite lower lexical diversity and higher stop-word proportions. Participants generally valued STT for its convenience and spontaneity, but uptake was constrained by context, privacy, interface design and individual preferences. STT may enable population-scale collection of richer health narratives, provided implementation is tailored to the study population and research context.",
  "abstract_shown": true,
  "affiliations": [
    "University of Zurich: Universitat Zurich"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 13,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "A. M. Baumer"
    },
    {
      "name": "P. Naoumis"
    },
    {
      "name": "J. Fabian"
    },
    {
      "name": "S. Strukova"
    },
    {
      "name": "M. Wolf"
    },
    {
      "name": "T. Ballouz"
    },
    {
      "name": "A. Farnham"
    },
    {
      "name": "V. X. C. Hofmann"
    },
    {
      "name": "G. Spitale"
    },
    {
      "name": "V. Dellwo"
    },
    {
      "name": "A. Glaessel"
    },
    {
      "name": "M. A. Puhan"
    },
    {
      "name": "V. von Wyl"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/aekj74b9njw9t.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.23.26363819",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.23.26363819v1.full",
  "id": "aekj74b9njw9t",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.23.26363819v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "health informatics"
    ],
    [
      "openalex",
      "3312|Survey Methodology and Nonresponse"
    ]
  ],
  "openalex": "W7214365125",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.23.26363819v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/aekj74b9njw9t.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:23Z",
      "native_id": "10.64898/2026.09.23.26363819",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.23.26363819v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:health informatics",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Collecting health narratives at scale: A multi-study evaluation of speech-to-text in health surveys",
  "title_text": "Collecting health narratives at scale: A multi-study evaluation of speech-to-text in health surveys",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:23Z",
  "url": "https://research.draconitic.com/paper/aekj74b9njw9t",
  "venue": "medRxiv",
  "versions": []
}