{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T17:02:51Z","timestamp":1781024571035,"version":"3.54.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:00:00Z","timestamp":1780963200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:00:00Z","timestamp":1780963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01KA2223B"],"award-info":[{"award-number":["01KA2223B"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009139","name":"Deutsches Zentrum f\u00fcr Infektionsforschung","doi-asserted-by":"publisher","award":["01KA2108"],"award-info":[{"award-number":["01KA2108"]}],"id":[{"id":"10.13039\/100009139","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Commun Med"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Spirometry remains the gold standard for assessing pulmonary function. Deep learning models have demonstrated potential for estimating measurements from chest X-rays (CXR). We aim to effectively address anatomical variability and integrate probabilistic reasoning to enhance estimation reliability near diagnostic thresholds.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a probabilistic machine learning framework to estimate the forced expiratory volume in the first second (FEV1) and the forced vital capacity (FVC) as measured through spirometry. Estimations use morphologically regularized CXRs and anthropometric-normalized peak expiratory flow rate (PEFR) as proxy for volumetric information unavailable in imaging. By estimating FEV1 and FVC z-scores, we decouple appearance from anatomic variability. We demonstrate our method on a multi-national cohort of pulmonary tuberculosis patients exhibiting diverse structural abnormalities and ventilatory impairments.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Using ensembles of neural networks, we analyze 982 CXR and spirometry pairs from 568 individuals. The best model achieves an area under curve (AUC) of 0.879 (FEV1; 99%CI 0.876, 0.881) and 0.853 (FVC; 99%CI 0.850, 0.856) in identifying moderate or severe lung-function impairment on a previously unseen test-set, signifying an AUC improvement of 0.144 (FEV1) and 0.118 (FVC) over previous methods. When allowing up to 10% of samples to remain unclassified due to uncertainty, AUC further rises to 0.894 (0.891, 0.896) and 0.857 (0.854, 0.860), respectively. Our method performs robustly across diverse impairment types and CXR pathologies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our study shows that decoupling anatomical variability from functional assessment improves lung function estimation. Incorporation of probabilistic modeling improved diagnostic reliability around a decision threshold. Therefore, our system offers a promising approach to practical lung function estimation in settings where spirometry is unavailable.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1038\/s43856-026-01702-7","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:36:17Z","timestamp":1781022977000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning approach for probabilistic pulmonary function estimation from chest X-ray and peak expiratory flow rate"],"prefix":"10.1038","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9849-8316","authenticated-orcid":false,"given":"Christoph","family":"Killing","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9173-4872","authenticated-orcid":false,"given":"Maximilian","family":"Wekerle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jayne S.","family":"Sutherland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Rassool","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lindsay","family":"Zurba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olena","family":"Ivanova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salome","family":"Charalambous","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Celso","family":"Khosa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6152-5183","authenticated-orcid":false,"given":"Robert S.","family":"Wallis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7642-1835","authenticated-orcid":false,"given":"Michael","family":"Hoelscher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claire","family":"Calderwood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Allwood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noemi","family":"Castelletti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Rachow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"On behalf of the TB Sequel Consortium","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Rachow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Hoelscher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noemi","family":"Castelletti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"1702_CR1","unstructured":"Momtazmanesh, S. et al. Global burden of chronic respiratory diseases and risk factors: an update from the Global Burden of Disease Study 2019. eClinicalMedicine 59, 101936 (2023)."},{"key":"1702_CR2","doi-asserted-by":"publisher","first-page":"e613","DOI":"10.1016\/S2214-109X(19)30070-1","volume":"7","author":"M Duong","year":"2019","unstructured":"Duong, M. et al. Mortality and cardiovascular and respiratory morbidity in individuals with impaired FEV1 (PURE): an international, community-based cohort study.  Lancet Glob. Health 7, e613\u2013e623 (2019).","journal-title":"Lancet Glob. Health"},{"key":"1702_CR3","doi-asserted-by":"crossref","unstructured":"Kalra S., et al. The association of interstitial lung abnormalities and preserved ratio impaired spirometry (PRISm) with mortality. CHEST 168, 136\u2013145 (2025).","DOI":"10.1016\/j.chest.2025.02.002"},{"key":"1702_CR4","doi-asserted-by":"crossref","unstructured":"Moore V. C. Spirometry: step by step. Breathe 8, 232\u2013240 (2012).","DOI":"10.1183\/20734735.0021711"},{"key":"1702_CR5","doi-asserted-by":"publisher","first-page":"e70","DOI":"10.1164\/rccm.201908-1590ST","volume":"200","author":"BL Graham","year":"2019","unstructured":"Graham, B. L. et al. Standardization of Spirometry 2019 Update. An Official American Thoracic Society and European Respiratory Society Technical Statement. Am. J. Respir. Crit. Care Med. 200, e70\u2013e88 (2019).","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"1702_CR6","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s13223-019-0329-2","volume":"15","author":"D Kibirige","year":"2019","unstructured":"Kibirige, D., Sanya, R. E., Nantanda, R., Worodria, W. & Kirenga, B. Availability and affordability of medicines and diagnostic tests recommended for management of asthma and chronic obstructive pulmonary disease in sub-Saharan Africa: a systematic review. Allergy Asthma Clin. Immunol. 15, 14 (2019).","journal-title":"Allergy Asthma Clin. Immunol."},{"key":"1702_CR7","doi-asserted-by":"publisher","first-page":"850","DOI":"10.5588\/ijtld.23.0040","volume":"27","author":"A Rachow","year":"2023","unstructured":"Rachow, A. et al. Performance of spirometry assessment at TB diagnosis.  Int. J. Tuberculosis Lung Dis. 27, 850\u2013857 (2023).","journal-title":"Int. J. Tuberculosis Lung Dis."},{"key":"1702_CR8","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1159\/000512531","volume":"100","author":"BW Allwood","year":"2021","unstructured":"Allwood, B. W. et al. Post-tuberculosis lung disease: clinical review of an under-recognised global challenge. Respiration 100, 751\u2013763 (2021).","journal-title":"Respiration"},{"key":"1702_CR9","doi-asserted-by":"publisher","first-page":"e605","DOI":"10.1016\/S2589-7500(24)00118-3","volume":"6","author":"ZZ Qin","year":"2024","unstructured":"Qin, Z. Z. et al. Computer-aided detection of tuberculosis from chest radiographs in a tuberculosis prevalence survey in South Africa: external validation and modelled impacts of commercially available artificial intelligence software.  Lancet Digital Health 6, e605\u2013e613 (2024).","journal-title":"Lancet Digital Health"},{"key":"1702_CR10","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s11604-018-0726-3","volume":"36","author":"K Yasaka","year":"2018","unstructured":"Yasaka, K., Akai, H., Kunimatsu, A., Kiryu, S. & Abe, O. Deep learning with convolutional neural network in radiology. Jpn J. Radio. 36, 257\u2013272 (2018).","journal-title":"Jpn J. Radio."},{"key":"1702_CR11","doi-asserted-by":"publisher","first-page":"e580","DOI":"10.1016\/S2589-7500(24)00113-4","volume":"6","author":"D Ueda","year":"2024","unstructured":"Ueda, D. et al. A deep learning-based model to estimate pulmonary function from chest x-rays: multi-institutional model development and validation study in Japan.  Lancet Digit. Health 6, e580\u2013e588 (2024).","journal-title":"Lancet Digit. Health"},{"key":"1702_CR12","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1164\/rccm.200506-975OC","volume":"173","author":"LB Herpel","year":"2006","unstructured":"Herpel, L. B. et al. Variability of spirometry in chronic obstructive pulmonary disease. Am. J. Respir. Crit. Care Med. 173, 1106\u20131113 (2006).","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"1702_CR13","doi-asserted-by":"publisher","first-page":"e880","DOI":"10.1016\/S2589-7500(24)00247-4","volume":"6","author":"X Li","year":"2024","unstructured":"Li, X., Lv, J., Xue, J., Zhang, R. & Li, D. Challenges of AI-based pulmonary function estimation from chest x-rays.  Lancet Digital Health 6, e880 (2024).","journal-title":"Lancet Digital Health"},{"key":"1702_CR14","doi-asserted-by":"publisher","DOI":"10.1186\/s12890-018-0777-3","volume":"19","author":"A Rachow","year":"2019","unstructured":"Rachow, A. et al. TB sequel: incidence, pathogenesis and risk factors of long-term medical and social sequelae of pulmonary TB \u2013 a study protocol. BMC Pulm. Med. 19, 4 (2019).","journal-title":"BMC Pulm. Med."},{"key":"1702_CR15","unstructured":"Moons C., Collins. G., Reitsma H. Tripod Statement. December 4th, 2024 2020. https:\/\/www.tripod-statement.org (accessed December 4th, 2024 2024)."},{"key":"1702_CR16","doi-asserted-by":"publisher","first-page":"1324","DOI":"10.1183\/09031936.00080312","volume":"40","author":"PH Quanjer","year":"2012","unstructured":"Quanjer, P. H. et al. Multi-ethnic reference values for spirometry for the 3\u201395-yr age range: the global lung function 2012 equations. Eur. Respir. J. 40, 1324\u20131343 (2012).","journal-title":"Eur. Respir. J."},{"key":"1702_CR17","doi-asserted-by":"publisher","first-page":"1724","DOI":"10.1164\/rccm.202005-2085LE","volume":"202","author":"S-J Smith","year":"2020","unstructured":"Smith, S.-J. et al. Choosing the Better Global Lung Initiative 2012 Equation in South African Population Groups. Am. J. Respir. Crit. Care Med. 202, 1724\u20131727 (2020).","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"1702_CR18","doi-asserted-by":"publisher","first-page":"1068","DOI":"10.1136\/bmj.298.6680.1068","volume":"298","author":"AJ Nunn","year":"1989","unstructured":"Nunn, A. J. & Gregg, I. New regression equations for predicting peak expiratory flow in adults. Bmj 298, 1068\u20131070 (1989).","journal-title":"Bmj"},{"key":"1702_CR19","unstructured":"Seibold, C. M. et al. Detailed annotations of chest X-rays via CT projection for report understanding. BMVA Press."},{"key":"1702_CR20","unstructured":"Seibold, C. Accurate fine-grained segmentation of human anatomy in radiographs via volumetric pseudo-labeling."},{"key":"1702_CR21","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1002\/ajim.21002","volume":"54","author":"L Jacquin","year":"2011","unstructured":"Jacquin, L. et al. Short-term spirometric changes in wildland firefighters. Am. J. Ind. Med. 54, 819\u2013825 (2011).","journal-title":"Am. J. Ind. Med."},{"key":"1702_CR22","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6","volume":"3","author":"K Weiss","year":"2016","unstructured":"Weiss, K., Khoshgoftaar, T. M. & Wang, D. A survey of transfer learning. J. Big Data 3, 9 (2016).","journal-title":"J. Big Data"},{"key":"1702_CR23","doi-asserted-by":"crossref","unstructured":"Huang G., Liu Z., van der Maaten L., Weinberger K. Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017).","DOI":"10.1109\/CVPR.2017.243"},{"key":"1702_CR24","unstructured":"Cohen J. P., Hashir M., Brooks R., Bertrand H. On the limits of cross-domain generalization in automated X-ray prediction. Proc. Med. Imaging Deep Learn. 121, 136\u2013149 (2020)."},{"key":"1702_CR25","doi-asserted-by":"publisher","first-page":"2101499","DOI":"10.1183\/13993003.01499-2021","volume":"60","author":"S Stanojevic","year":"2022","unstructured":"Stanojevic, S. et al. ERS\/ATS technical standard on interpretive strategies for routine lung function tests. Eur. Respir. J. 60, 2101499 (2022).","journal-title":"Eur. Respir. J."},{"key":"1702_CR26","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1136\/thoraxjnl-2020-216037","volume":"76","author":"VV Polosukhin","year":"2021","unstructured":"Polosukhin, V. V. et al. Small airway determinants of airflow limitation in chronic obstructive pulmonary disease. Thorax 76, 1079\u20131088 (2021).","journal-title":"Thorax"},{"key":"1702_CR27","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/1471-2466-6-14","volume":"6","author":"T Bongers","year":"2006","unstructured":"Bongers, T. & O\u2019Driscoll, B. R. Effects of equipment and technique on peak flow measurements. BMC Pulm. Med. 6, 14 (2006).","journal-title":"BMC Pulm. Med."},{"key":"1702_CR28","doi-asserted-by":"publisher","first-page":"e58","DOI":"10.2500\/aap.2022.43.220049","volume":"43","author":"S Mamyrbekova","year":"2022","unstructured":"Mamyrbekova, S. et al. The diagnostic accuracy of spirometry versus peak expiratory flow test for follow-up of adult asthma patients at primary care level. Allergy Asthma Proc. 43, e58\u2013e64 (2022).","journal-title":"Allergy Asthma Proc."},{"key":"1702_CR29","doi-asserted-by":"publisher","DOI":"10.1177\/20552076211005959","volume":"7","author":"P Sakkatos","year":"2021","unstructured":"Sakkatos, P. & Williams, A. Testing the accuracy of a novel digital peak flow meter aligned with a smartphone app compared to a lab spirometer: a pilot work. Digit. Health 7, 20552076211005959 (2021).","journal-title":"Digit. Health"},{"key":"1702_CR30","doi-asserted-by":"publisher","first-page":"36538","DOI":"10.1109\/ACCESS.2022.3163384","volume":"10","author":"AA Abdullah","year":"2022","unstructured":"Abdullah, A. A., Hassan, M. M. & Mustafa, Y. T. A review on Bayesian deep learning in healthcare: applications and challenges. IEEE Access 10, 36538\u201336562 (2022).","journal-title":"IEEE Access"},{"key":"1702_CR31","doi-asserted-by":"publisher","unstructured":"Killing C., et al. Deep learning approach for probabilistic pulmonary function estimation from chest X-ray and peak expiratory flow rate - A code repository. https:\/\/doi.org\/10.5281\/zenodo.19285757 (2026).","DOI":"10.5281\/zenodo.19285757"}],"container-title":["Communications Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43856-026-01702-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43856-026-01702-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43856-026-01702-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:44:11Z","timestamp":1781023451000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43856-026-01702-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,9]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1702"],"URL":"https:\/\/doi.org\/10.1038\/s43856-026-01702-7","relation":{},"ISSN":["2730-664X"],"issn-type":[{"value":"2730-664X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,9]]},"assertion":[{"value":"29 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflicting interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"330"}}