{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"Research Square"}],"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T11:15:08Z","timestamp":1787915708738,"version":"build-2784847793"},"posted":{"date-parts":[[2025,6,30]]},"group-title":"In Review","reference-count":0,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,3,24]]},"abstract":"<title>Abstract<\/title>\n        <p>Importance: Obtaining spirometry requires repeated testing and using the maximal values based\non quality control criteria. Whether the suboptimal efforts are useful for the prediction of respiratory\noutcomes is not clear.\n\nObjective: To determine whether a machine learning model could predict respiratory outcomes and\nmortality based on suboptimal spirometry.\n\nDesign: Observational cohorts (UK Biobank and COPDGene).\n\nSetting: Multi-center; population, and disease-enriched.\n\nParticipants: UK aged 40-69; US aged 45-80, &gt;10 pack-years smoking, without respiratory diseases\nother than COPD or asthma.\n\nExposures: Raw spirograms (volume-time).\n\nMain outcomes and measures: To create a combined representation of lung function we\nimplemented a contrastive learning approach, Spirogram-based Contrastive Learning Framework\n(Spiro-CLF), which utilized all recorded volume-time curves per participant and applied different\ntransformations (e.g. flow-volume, flow-time). We defined \u201cmaximal\u201d efforts as those passing quality\ncontrol (QC) with the maximum FVC; all other efforts, including submaximal and QC-failing efforts,\nwere defined as \u201csuboptimal\u201d. We trained the Spiro-CLF model using both maximal and suboptimal\nefforts from the UK Biobank. We tested the model in a held-out 20% testing UK Biobank subset and\nCOPDGene, on 1) binary predictions of FEV1\/FVC &lt;0.7, and FEV1 Percent Predicted (FEV1PP)\n&lt;80%, 2) Cox regression for all-cause mortality, and 3) prediction of respiratory phenotypes.\n\nResults: We trained Spiro-CLF on 940,705 volume-time curves from 352,684 UKB participants with\n2-3 spirometry efforts per individual (66.7% with 3 efforts) and at least one QC-passing spirometry\neffort. Of all spirometry efforts, 61.6% were suboptimal (37.5% submaximal and 24.1% QC-failing).\nIn the UK Biobank, Spiro-CLF using QC-failing and submaximal efforts predicted FEV1\/FVC &lt;\n0.7 with an Area under the Receiver Operating Characteristics (AUROC) of 0.956, mortality with\na concordance index of 0.647, and asthma with a 9-42% improvement versus baseline models. In\nCOPDGene (n=10,110 participants), adding QC-passing, submaximal efforts did not improve the\nprediction of lung function or mortality; however, Spiro-CLF representations predicted asthma and\nrespiratory phenotypes (joint test P \u2264 2 \u00d7 10\u22123).\n\nConclusions and Relevance: A machine-learning model can predict respiratory phenotypes using\nsuboptimal spirometry; results from all spirometry efforts may contain valuable data. Additional\nstudies are required to determine performance and utility in specific clinical scenarios.<\/p>","DOI":"10.21203\/rs.3.rs-6296752\/v1","type":"posted-content","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T06:31:23Z","timestamp":1751265083000},"source":"Crossref","is-referenced-by-count":2,"title":["Deep Learning of Suboptimal Spirometry to Predict Respiratory Outcomes and Mortality"],"prefix":"10.21203","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4907-1657","authenticated-orcid":false,"given":"Michael","family":"Cho","sequence":"first","affiliation":[{"name":"Brigham and Women's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davin","family":"Hill","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Max","family":"Torop","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aria","family":"Masoomi","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Castaldi","sequence":"additional","affiliation":[{"name":"Brigham and Women's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edwin","family":"Silverman","sequence":"additional","affiliation":[{"name":"Brigham and Women's Hospital, Harvard Medical School"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandeep","family":"Bodduluri","sequence":"additional","affiliation":[{"name":"University of Alabama at Birmingham"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8418-4497","authenticated-orcid":false,"given":"Surya","family":"Bhatt","sequence":"additional","affiliation":[{"name":"University of Alabama at Birmingham"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6242-5536","authenticated-orcid":false,"given":"Taedong","family":"Yun","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9928-8216","authenticated-orcid":false,"given":"Cory","family":"McLean","sequence":"additional","affiliation":[{"name":"Google (United States)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5617-6174","authenticated-orcid":false,"given":"Farhad","family":"Hormozdiari","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jennifer","family":"Dy","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9564-0745","authenticated-orcid":false,"given":"Brian","family":"Hobbs","sequence":"additional","affiliation":[{"name":"Brigham and Women's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","container-title":[],"original-title":[],"link":[{"URL":"https:\/\/www.researchsquare.com\/article\/rs-6296752\/v1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.researchsquare.com\/article\/rs-6296752\/v1.html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T06:31:23Z","timestamp":1751265083000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchsquare.com\/article\/rs-6296752\/v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":0,"URL":"https:\/\/doi.org\/10.21203\/rs.3.rs-6296752\/v1","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"subtype":"preprint"}}