{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T13:13:45Z","timestamp":1775654025641,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T00:00:00Z","timestamp":1772064000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"vor","delay-in-days":41,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2022YFC2010005"],"award-info":[{"award-number":["2022YFC2010005"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02445-4","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T11:36:21Z","timestamp":1772105781000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A device-invariant multi-modal learning framework for respiratory disease classification"],"prefix":"10.1038","volume":"9","author":[{"given":"Mo","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoyang","family":"Bu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxuan","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Si","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie-ming","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,26]]},"reference":[{"key":"2445_CR1","doi-asserted-by":"publisher","DOI":"10.1186\/s12931-024-03051-2","volume":"26","author":"Z Wang","year":"2025","unstructured":"Wang, Z. et al. Global, regional, and national burden of chronic obstructive pulmonary disease and its attributable risk factors from 1990 to 2021: an analysis for the global burden of disease study 2021. Respir. Res. 26, 2 (2025).","journal-title":"Respir. Res."},{"key":"2445_CR2","doi-asserted-by":"publisher","first-page":"2201519","DOI":"10.1183\/13993003.01519-2022","volume":"62","author":"NR Bhakta","year":"2023","unstructured":"Bhakta, N. R., McGowan, A., Ramsey, K. A. et al. European Respiratory Society\/american thoracic society technical statement: standardisation of the measurement of lung volumes, 2023 update. Eur. Respir. J. 62, 2201519 (2023).","journal-title":"Eur. Respir. J."},{"key":"2445_CR3","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1111\/resp.70062","volume":"30","author":"S Thawanaphong","year":"2025","unstructured":"Thawanaphong, S. & Nair, P. Contemporary concise review 2024: chronic obstructive pulmonary disease. Respirology 30, 574\u2013586 (2025).","journal-title":"Respirology"},{"key":"2445_CR4","doi-asserted-by":"publisher","first-page":"e20230369","DOI":"10.36416\/1806-3756\/e20230369","volume":"49","author":"A Agusti","year":"2023","unstructured":"Agusti, A. & Vogelmeier, C. F. Gold 2024: a brief overview of key changes. J. Bras. Pneumol. 49, e20230369 (2023).","journal-title":"J. Bras. Pneumol."},{"key":"2445_CR5","doi-asserted-by":"publisher","first-page":"413","DOI":"10.4046\/trd.2025.0009","volume":"88","author":"SH Kim","year":"2025","unstructured":"Kim, S. H. & Han, M. K. Challenges and the future of pulmonary function testing in chronic obstructive pulmonary disease (copd): toward earlier diagnosis of copd. Tuberc. Respir. Dis. 88, 413\u2013418 (2025).","journal-title":"Tuberc. Respir. Dis."},{"key":"2445_CR6","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1007\/s40747-025-01800-4","volume":"11","author":"Y Chu","year":"2025","unstructured":"Chu, Y. et al. Cycleguardian: a framework for automatic respiratory sound classification based on improved deep clustering and contrastive learning. Complex Intell. Syst. 11, 200 (2025).","journal-title":"Complex Intell. Syst."},{"key":"2445_CR7","doi-asserted-by":"publisher","first-page":"e54388","DOI":"10.2196\/54388","volume":"13","author":"KG Isangula","year":"2024","unstructured":"Isangula, K. G. & Haule, R. J. Leveraging ai and machine learning to develop and evaluate a contextualized user-friendly cough audio classifier for detecting respiratory diseases: Protocol for a diagnostic study in rural Tanzania. JMIR Res. Protoc. 13, e54388 (2024).","journal-title":"JMIR Res. Protoc."},{"key":"2445_CR8","doi-asserted-by":"publisher","first-page":"105912","DOI":"10.1016\/j.ijmedinf.2025.105912","volume":"199","author":"RV Sharan","year":"2025","unstructured":"Sharan, R. V. & Xiong, H. Wet and dry cough classification using cough sound characteristics and machine learning: a systematic review. Int. J. Med. Inform. 199, 105912 (2025).","journal-title":"Int. J. Med. Inform."},{"key":"2445_CR9","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-03972-z","volume":"11","author":"S Huddart","year":"2024","unstructured":"Huddart, S. et al. A dataset of solicited cough sound for tuberculosis triage testing. Sci. Data 11, 1149 (2024).","journal-title":"Sci. Data"},{"key":"2445_CR10","doi-asserted-by":"crossref","unstructured":"Morocutti, T., Schmid, F., Koutini, K. & Widmer, G. Device-robust acoustic scene classification via impulse response augmentation. In Proc. 31st European Signal Processing Conference (EUSIPCO) 176-180 (IEEE, 2023).","DOI":"10.23919\/EUSIPCO58844.2023.10289983"},{"key":"2445_CR11","unstructured":"Mezza, A. I., Habets, E. A., M\u00fcller, M. & Sarti, A. Unsupervised domain adaptation for acoustic scene classification using band-wise statistics matching. In Proc. 28th European Signal Processing Conference (EUSIPCO) 11\u221215 (IEEE, 2020)."},{"key":"2445_CR12","doi-asserted-by":"crossref","unstructured":"Ma, C., Wang, H. & Hoi, S. C. H. Multi-label thoracic disease image classification with cross-attention networks. In Proc. Int. Conf. on Medical Image Computing and Computer-Assisted Intervention 730\u2212738 (Cham: Springer International Publishing, 2019).","DOI":"10.1007\/978-3-030-32226-7_81"},{"key":"2445_CR13","doi-asserted-by":"publisher","first-page":"110407","DOI":"10.1016\/j.apacoust.2024.110407","volume":"229","author":"T Lei","year":"2025","unstructured":"Lei, T., Hu, Q., Hou, Z. & Lu, J. Enhancing real-world far-field speech with supervised adversarial training. Appl. Acoust. 229, 110407 (2025).","journal-title":"Appl. Acoust."},{"key":"2445_CR14","unstructured":"Arjovsky, M., Bottou, L., Gulrajani, I. & Lopez-Paz, D. Invariant risk minimization. https:\/\/arxiv.org\/abs\/1907.02893 (2020)."},{"key":"2445_CR15","unstructured":"Wang, J. et al. Joint asymmetric loss for learning with noisy labels. In Proc. IEEE\/CVF International Conference on Computer Vision 1947\u22121956 (IEEE, 2025)."},{"key":"2445_CR16","doi-asserted-by":"crossref","unstructured":"Gong, Y., Chung, Y.-A. & Glass, J. Ast: audio spectrogram transformer. In Proc. Interspeech 571-575 (2021).","DOI":"10.21437\/Interspeech.2021-698"},{"key":"2445_CR17","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008).","journal-title":"J. Mach. Learn. Res."},{"key":"2445_CR18","doi-asserted-by":"publisher","first-page":"e958","DOI":"10.7717\/peerj-cs.958","volume":"8","author":"KC Santosh","year":"2022","unstructured":"Santosh, K. C., Rasmussen, N., Mamun, M. & Aryal, S. A systematic review on cough sound analysis for covid-19 diagnosis and screening: is my cough sound COVID-19? PeerJ Comput. Sci. 8, e958 (2022).","journal-title":"PeerJ Comput. Sci."},{"key":"2445_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01584-4","volume":"8","author":"M Santamaria","year":"2025","unstructured":"Santamaria, M. et al. Longitudinal voice monitoring in a decentralized bring your own device trial for respiratory illness detection. npj Digit. Med. 8, 202 (2025).","journal-title":"npj Digit. Med."},{"key":"2445_CR20","doi-asserted-by":"publisher","first-page":"128111","DOI":"10.1016\/j.neucom.2024.128111","volume":"599","author":"M Mersha","year":"2024","unstructured":"Mersha, M., Lam, K., Wood, J., AlShami, A. K. & Kalita, J. Explainable artificial intelligence: a survey of needs, techniques, applications, and future direction. Neurocomputing 599, 128111 (2024).","journal-title":"Neurocomputing"},{"key":"2445_CR21","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1093\/ectj\/utae004","volume":"27","author":"A Baiardi","year":"2024","unstructured":"Baiardi, A. & Naghi, A. A. The value added of machine learning to causal inference: evidence from revisited studies. Econom. J. 27, 213\u2013234 (2024).","journal-title":"Econom. J."},{"key":"2445_CR22","unstructured":"Poinsot, A. et al. Position: causal machine learning requires rigorous synthetic experiments for broader adoption. In Proc. 42nd International Conference on Machine Learning 81995-82015 (PMLR, 2025)."},{"key":"2445_CR23","doi-asserted-by":"publisher","first-page":"198345","DOI":"10.1007\/s11704-024-40646-w","volume":"19","author":"L-Z Guo","year":"2025","unstructured":"Guo, L.-Z., Jia, L.-H., Shao, J.-J. & Li, Y.-F. Robust semi-supervised learning in open environments. Front. Comput. Sci. 19, 198345 (2025).","journal-title":"Front. Comput. Sci."},{"key":"2445_CR24","unstructured":"Schmidt, R. M. Recurrent neural networks (rnns): a gentle introduction and overview https:\/\/arxiv.org\/abs\/1912.05911 (2019)."},{"key":"2445_CR25","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. Random forests. Mach. Learn. 45, 5\u201332 (2001).","journal-title":"Mach. Learn."},{"key":"2445_CR26","unstructured":"Liu, Y. et al. Roberta: a robustly optimized bert pretraining approach https:\/\/arxiv.org\/abs\/1907.11692 (2019)."},{"key":"2445_CR27","doi-asserted-by":"crossref","unstructured":"Chen, F., Datta, G., Kundu, S. & Beerel, P. Self-attentive pooling for efficient deep learning. In Proc. IEEE\/CVF Winter Conference on Applications of Computer Vision 3974-3983 (IEEE, 2023).","DOI":"10.1109\/WACV56688.2023.00396"},{"key":"2445_CR28","first-page":"1","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y. et al. Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 1\u201335 (2016).","journal-title":"J. Mach. Learn. Res."},{"key":"2445_CR29","doi-asserted-by":"crossref","unstructured":"Luo, J., Phan, H., Wang, L. & Reiss, J. D. Bimodal connection attention fusion for speech emotion recognition https:\/\/arxiv.org\/abs\/2503.05858 (2025).","DOI":"10.2139\/ssrn.5208858"},{"key":"2445_CR30","unstructured":"Vaswani, A. et al. Attention is all you need. In Proc. Advances in Neural Information Processing Systems 30 (2023)."},{"key":"2445_CR31","doi-asserted-by":"publisher","first-page":"110740","DOI":"10.1016\/j.patcog.2024.110740","volume":"156","author":"H Aly","year":"2024","unstructured":"Aly, H., Al-Ali, A. K. & Suganthan, P. N. Boosted multilayer feedforward neural network with multiple output layers. Pattern Recognit. 156, 110740 (2024).","journal-title":"Pattern Recognit."},{"key":"2445_CR32","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929\u20131958 (2014).","journal-title":"J. Mach. Learn. Res."},{"key":"2445_CR33","unstructured":"Hendrycks, D. & Gimpel, K. Gaussian error linear units (GELUs) https:\/\/arxiv.org\/abs\/1606.08415 (2016)."},{"key":"2445_CR34","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D. E., Hinton, G. E. & Williams, R. J. Learning representations by back-propagating errors. Nature 323, 533\u2013536 (1986).","journal-title":"Nature"},{"key":"2445_CR35","doi-asserted-by":"publisher","unstructured":"Wang, Z., Xu, B., Yuan, Y., Shen, H. & Cheng, X. Infonce is a free lunch for semantically guided graph contrastive learning. In Proc. 48th International ACM SIGIR Conference on Research and Development in Information Retrieval 719\u2013728 https:\/\/doi.org\/10.1145\/3726302.3730007 (ACM, 2025).","DOI":"10.1145\/3726302.3730007"},{"key":"2445_CR36","doi-asserted-by":"crossref","unstructured":"He, K. et al. Dalr: dual-level alignment learning for multimodal sentence representation learning. In Proc. Findings of the Association for Computational Linguistics: ACL 2025 3586-3601 (2025).","DOI":"10.18653\/v1\/2025.findings-acl.183"},{"key":"2445_CR37","doi-asserted-by":"crossref","unstructured":"Kendall, A., Gal, Y. & Cipolla, R. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 7482-7491 (IEEE, 2018).","DOI":"10.1109\/CVPR.2018.00781"},{"key":"2445_CR38","unstructured":"Chen, W., Liang, Y., Ma, Z., Zheng, Z. & Chen, X. EAT: Self-supervised pre-training with efficient audio transformer. In Proc. Thirty-Third International Joint Conference on Artificial Intelligence 3807-3815 (2024)."},{"key":"2445_CR39","doi-asserted-by":"crossref","unstructured":"Kim, J.-W., Toikkanen, M., Choi, Y., Moon, S.-E. & Jung, H.-Y. Bts: bridging text and sound modalities for metadata-aided respiratory sound classification. In Interspeech 2024 1690\u20131694 (GitHub, 2024).","DOI":"10.21437\/Interspeech.2024-492"},{"key":"2445_CR40","doi-asserted-by":"crossref","unstructured":"Shao, N., Li, X. & Li, X. Fine-tune the pretrained atst model for sound event detection. In Proc. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 911\u2013915 (IEEE, 2024).","DOI":"10.1109\/ICASSP48485.2024.10446159"},{"key":"2445_CR41","unstructured":"Chen, S. et al. BEATs: audio pre-training with acoustic tokenizers. In Proc. 40th International Conference on Machine Learning 5178-5193 (2023)."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02445-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02445-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02445-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T12:17:27Z","timestamp":1775650647000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02445-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,26]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2445"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02445-4","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,26]]},"assertion":[{"value":"5 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"290"}}