{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T13:58:08Z","timestamp":1775743088285,"version":"3.50.1"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:00:00Z","timestamp":1772496000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:00:00Z","timestamp":1775692800000},"content-version":"vor","delay-in-days":37,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02493-w","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T04:14:40Z","timestamp":1772511280000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal multi-instance learning for cardiopulmonary exercise testing performance prediction"],"prefix":"10.1038","volume":"9","author":[{"given":"Zhe","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weishen","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shudhanshu","family":"Alishetti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashley N.","family":"Beecy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenzhen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Albert","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saebyeol","family":"Shin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin J.","family":"Clerkin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rochelle L.","family":"Goldsmith","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David T.","family":"Majure","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chris","family":"Kelsey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"vanMaanan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeffrey","family":"Ruhl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naomi","family":"Tesfuzigta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erica","family":"Lancet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepa","family":"Kumaraiah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriel","family":"Sayer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deborah","family":"Estrin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kilian","family":"Weinberger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nir","family":"Uriel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,3]]},"reference":[{"key":"2493_CR1","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.cardfail.2024.07.001","volume":"31","author":"B Bozkurt","year":"2025","unstructured":"Bozkurt, B. et al. HF STATS 2024: Heart failure epidemiology and outcomes statistics an updated 2024 report from the heart failure society of America. J. Card. Fail 31, 66\u2013116 (2025).","journal-title":"J. Card. Fail"},{"key":"2493_CR2","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1097\/FJC.0000000000001755","volume":"86","author":"M Bernardi","year":"2025","unstructured":"Bernardi, M. et al. Current challenges for the diagnosis of HFpEF and possible simplification of the diagnostic approach. J. Cardiovasc. Pharm. 86, 522\u2013534 (2025).","journal-title":"J. Cardiovasc. Pharm."},{"key":"2493_CR3","doi-asserted-by":"publisher","first-page":"e021246","DOI":"10.1161\/JAHA.121.021246","volume":"10","author":"J Myers","year":"2021","unstructured":"Myers, J. et al. Comparison of the FRIEND and Wasserman-Hansen equations in predicting outcomes in heart failure. J. Am. Heart Assoc. 10, e021246 (2021).","journal-title":"J. Am. Heart Assoc."},{"key":"2493_CR4","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1161\/01.CIR.83.3.778","volume":"83","author":"DM Mancini","year":"1991","unstructured":"Mancini, D. M. et al. Value of peak exercise oxygen consumption for optimal timing of cardiac transplantation in ambulatory patients with heart failure. Circulation 83, 778\u2013786 (1991).","journal-title":"Circulation"},{"key":"2493_CR5","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1161\/CIRCULATIONAHA.118.034338","volume":"138","author":"J Zhang","year":"2018","unstructured":"Zhang, J. et al. Fully automated echocardiogram interpretation in clinical practice. Circulation 138, 1623\u20131635 (2018).","journal-title":"Circulation"},{"key":"2493_CR6","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1038\/s41586-020-2145-8","volume":"580","author":"D Ouyang","year":"2020","unstructured":"Ouyang, D. et al. Video-based AI for beat-to-beat assessment of cardiac function. Nature 580, 252\u2013256 (2020).","journal-title":"Nature"},{"key":"2493_CR7","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1038\/s41586-023-05947-3","volume":"616","author":"B He","year":"2023","unstructured":"He, B. et al. Blinded, randomized trial of sonographer versus AI cardiac function assessment. Nature 616, 520\u2013524 (2023).","journal-title":"Nature"},{"key":"2493_CR8","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1001\/jamacardio.2021.6059","volume":"7","author":"G Duffy","year":"2022","unstructured":"Duffy, G. et al. High-throughput precision phenotyping of left ventricular hypertrophy with cardiovascular deep learning. JAMA Cardiol. 7, 386\u2013395 (2022).","journal-title":"JAMA Cardiol."},{"key":"2493_CR9","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1161\/CIRCULATIONAHA.124.068996","volume":"150","author":"A Long","year":"2024","unstructured":"Long, A. et al. Deep learning for echo analysis, tracking, and evaluation of mitral regurgitation (DELINEATE-MR). Circulation 150, 911\u2013922 (2024).","journal-title":"Circulation"},{"key":"2493_CR10","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1038\/s41551-020-00667-9","volume":"5","author":"AE Ulloa Cerna","year":"2021","unstructured":"Ulloa Cerna, A. E. et al. Deep-learning-assisted analysis of echocardiographic videos improves predictions of all-cause mortality. Nat. Biomed. Eng. 5, 546\u2013554 (2021).","journal-title":"Nat. Biomed. Eng."},{"key":"2493_CR11","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1016\/j.jacc.2023.09.800","volume":"82","author":"ES Lau","year":"2023","unstructured":"Lau, E. S. et al. Deep learning-enabled assessment of left heart structure and function predicts cardiovascular outcomes. J. Am. Coll. Cardiol. 82, 1936\u20131948 (2023).","journal-title":"J. Am. Coll. Cardiol."},{"key":"2493_CR12","doi-asserted-by":"crossref","unstructured":"Alishetti, S. et al. Predicting cardiopulmonary exercise testing performance in patients undergoing transthoracic echocardiography - an AI based, multimodal model. medRxiv. 2025. 2025.07.05.25330921.","DOI":"10.1101\/2025.07.05.25330921"},{"key":"2493_CR13","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/S0004-3702(96)00034-3","volume":"89","author":"TG Dietterich","year":"1997","unstructured":"Dietterich, T. G., Lathrop, R. H. & Lozano-P\u00e9rez, T. Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 89, 31\u201371 (1997).","journal-title":"Artif. Intell."},{"key":"2493_CR14","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1038\/s41586-024-08328-6","volume":"637","author":"N Hollmann","year":"2025","unstructured":"Hollmann, N. et al. Accurate predictions on small data with a tabular foundation model. Nature 637, 319\u2013326 (2025).","journal-title":"Nature"},{"key":"2493_CR15","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","volume":"13","author":"T Cover","year":"1967","unstructured":"Cover, T. & Hart, P. Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13, 21\u201327 (1967).","journal-title":"IEEE Trans. Inf. Theory"},{"key":"2493_CR16","first-page":"2579","volume":"9","author":"L Maaten","year":"2008","unstructured":"Maaten, L. & Hinton, G. E. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008).","journal-title":"J. Mach. Learn. Res."},{"key":"2493_CR17","unstructured":"Draelos, R. L., Carin, L. Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks. arXiv [eess.IV]. (2020)."},{"key":"2493_CR18","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","volume":"28","author":"JN Acosta","year":"2022","unstructured":"Acosta, J. N., Falcone, G. J., Rajpurkar, P. & Topol, E. J. Multimodal biomedical AI. Nat. Med. 28, 1773\u20131784 (2022).","journal-title":"Nat. Med."},{"key":"2493_CR19","first-page":"950","volume":"4","author":"A Krogh","year":"1991","unstructured":"Krogh, A. & Hertz, J. A simple weight decay can improve generalization. Neural Inf. Process Syst. 4, 950\u2013957 (1991).","journal-title":"Neural Inf. Process Syst."},{"key":"2493_CR20","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G. E., 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":"2493_CR21","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S. X. & Lin, D. Unsupervised feature learning via non-parametric instance discrimination. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (IEEE, 2018).","DOI":"10.1109\/CVPR.2018.00393"},{"key":"2493_CR22","doi-asserted-by":"publisher","first-page":"8940","DOI":"10.1038\/s41598-025-94172-1","volume":"15","author":"S Kwast","year":"2025","unstructured":"Kwast, S. et al. Cardiopulmonary exercise capacity markers and their link to symptom burden in patients at risk for heart failure with non-reduced ejection fraction. Sci. Rep. 15, 8940 (2025).","journal-title":"Sci. Rep."},{"key":"2493_CR23","doi-asserted-by":"crossref","unstructured":"Ericsson, L., Gouk, H. & Hospedales, T. M. How well do self-supervised models transfer? In: Proc.IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). (IEEE, 2021).","DOI":"10.1109\/CVPR46437.2021.00537"},{"key":"2493_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S. & Girshick, R. Momentum contrast for unsupervised visual representation learning. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). (IEEE, 2020).","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2493_CR25","unstructured":"Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. In: Proc. International Conference on Machine Learning. (ICML, 2020)."},{"key":"2493_CR26","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T. & Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition. (IEEE, 2014).","DOI":"10.1109\/CVPR.2014.81"},{"key":"2493_CR27","unstructured":"Donahue, J. et al. DeCAF: a deep convolutional activation feature for generic visual recognition. In: Proc. International Conference on Machine Learning. (ICML, 2013)."},{"key":"2493_CR28","doi-asserted-by":"crossref","unstructured":"Caron, M. et al. Emerging properties in self-supervised vision transformers. In: Proc. IEEE\/CVF International Conference on Computer Vision (ICCV). (IEEE,2021).","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2493_CR29","doi-asserted-by":"publisher","first-page":"4592","DOI":"10.1093\/eurheartj\/ehad456","volume":"44","author":"G Holste","year":"2023","unstructured":"Holste, G. et al. Severe aortic stenosis detection by deep learning applied to echocardiography. Eur. Heart J. 44, 4592\u20134604 (2023).","journal-title":"Eur. Heart J."},{"key":"2493_CR30","doi-asserted-by":"crossref","unstructured":"Lu, M. Y., Chen, R. J., Wang, J., Dillon, D. & Mahmood, F. Semi-supervised histology classification using deep multiple instance learning and contrastive predictive coding. Advances in Neural Information Processing Systems. (NIPS, 2019).","DOI":"10.1117\/12.2549627"},{"key":"2493_CR31","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1109\/TMI.2019.2945514","volume":"39","author":"N Wu","year":"2020","unstructured":"Wu, N. et al. Deep neural networks improve radiologists\u2019 performance in breast cancer screening. IEEE Trans. Med Imaging 39, 1184\u20131194 (2020).","journal-title":"IEEE Trans. Med Imaging"},{"key":"2493_CR32","unstructured":"Khosla, P. et al. Supervised Contrastive Learning. Advances in Neural Information Processing Systems. (NIPS, 2020)."},{"key":"2493_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Z., Dai, Z., P\u00f3czos, B. & Carbonell, J. Characterizing and avoiding negative transfer. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (IEEE, 2019).","DOI":"10.1109\/CVPR.2019.01155"},{"key":"2493_CR34","doi-asserted-by":"crossref","unstructured":"Saporta, A. et al. Benchmarking saliency methods for chest X-ray interpretation. Nat. Mach. Intell. 4, 867\u2013878 2022.","DOI":"10.1038\/s42256-022-00536-x"},{"key":"2493_CR35","doi-asserted-by":"publisher","first-page":"e230488","DOI":"10.1148\/ryai.230488","volume":"6","author":"M Yanagawa","year":"2024","unstructured":"Yanagawa, M. & Sato, J. Seeing is not always believing: discrepancies in saliency maps. Radio. Artif. Intell. 6, e230488 (2024).","journal-title":"Radio. Artif. Intell."},{"key":"2493_CR36","doi-asserted-by":"publisher","first-page":"e220221","DOI":"10.1148\/ryai.220221","volume":"6","author":"J Zhang","year":"2024","unstructured":"Zhang, J. et al. Revisiting the trustworthiness of saliency methods in radiology AI. Radio. Artif. Intell. 6, e220221 (2024).","journal-title":"Radio. Artif. Intell."},{"key":"2493_CR37","unstructured":"Adebayo, J. et al. Sanity checks for saliency maps. Advances in Neural Information Processing Systems. (NIPS, 2018)."},{"key":"2493_CR38","doi-asserted-by":"publisher","first-page":"0036","DOI":"10.34133\/bmef.0036","volume":"5","author":"G Wang","year":"2024","unstructured":"Wang, G. Making \u201cCASES\u201d for AI in medicine. BME Front 5, 0036 (2024).","journal-title":"BME Front"},{"key":"2493_CR39","doi-asserted-by":"publisher","first-page":"2838","DOI":"10.1038\/s41591-024-03113-4","volume":"30","author":"Y Yang","year":"2024","unstructured":"Yang, Y., Zhang, H., Gichoya, J. W., Katabi, D. & Ghassemi, M. The limits of fair medical imaging AI in real-world generalization. Nat. Med. 30, 2838\u20132848 (2024).","journal-title":"Nat. Med."},{"key":"2493_CR40","unstructured":"Sagawa, S., Koh, P. W., Hashimoto, T. B. & Liang, P. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. (ICLR, 2020)."},{"key":"2493_CR41","unstructured":"Idrissi, B. Y., Arjovsky, M., Pezeshki, M. & Lopez-Paz, D. Simple data balancing achieves competitive worst-group-accuracy. (PMLR, 2022)."},{"key":"2493_CR42","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1109\/TBME.2021.3117407","volume":"69","author":"H Guan","year":"2022","unstructured":"Guan, H. & Liu, M. Domain adaptation for medical image analysis: a survey. IEEE Trans. Biomed. Eng. 69, 1173\u20131185 (2022).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"2493_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neuroimage.2019.03.026","volume":"194","author":"CS Perone","year":"2019","unstructured":"Perone, C. S., Ballester, P., Barros, R. C. & Cohen-Adad, J. Unsupervised domain adaptation for medical imaging segmentation with self-ensembling. Neuroimage 194, 1\u201311 (2019).","journal-title":"Neuroimage"},{"key":"2493_CR44","doi-asserted-by":"crossref","unstructured":"Karani, N., Chaitanya, K., Baumgartner, C. & Konukoglu, E. A lifelong learning approach to brain MR segmentation across scanners and protocols. In: International Conference on Medical Image Computing and Computer-assisted Intervention. (ICML, 2018).","DOI":"10.1007\/978-3-030-00928-1_54"},{"key":"2493_CR45","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1038\/s41591-024-02959-y","volume":"30","author":"M Christensen","year":"2024","unstructured":"Christensen, M., Vukadinovic, M., Yuan, N. & Ouyang, D. Vision-language foundation model for echocardiogram interpretation. Nat. Med. 30, 1481\u20131488 (2024).","journal-title":"Nat. Med."},{"key":"2493_CR46","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/s12574-021-00531-y","volume":"19","author":"DR Anderson","year":"2021","unstructured":"Anderson, D. R., Blissett, S., O\u2019Sullivan, P. & Qasim, A. Differences in echocardiography interpretation techniques among trainees and expert readers. J. Echocardiogr. 19, 222\u2013231 (2021).","journal-title":"J. Echocardiogr."},{"key":"2493_CR47","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1016\/j.neuroimage.2016.05.053","volume":"139","author":"C Wachinger","year":"2016","unstructured":"Wachinger, C. & Reuter, M. Alzheimer\u2019s disease neuroimaging initiative, Australian imaging biomarkers and lifestyle flagship study of ageing. Domain adaptation for Alzheimer\u2019s disease diagnostics. Neuroimage 139, 470\u2013479 (2016).","journal-title":"Neuroimage"},{"key":"2493_CR48","doi-asserted-by":"publisher","first-page":"1486","DOI":"10.1109\/JBHI.2017.2769800","volume":"22","author":"V Cheplygina","year":"2018","unstructured":"Cheplygina, V. et al. Transfer learning for multicenter classification of chronic obstructive pulmonary disease. IEEE J. Biomed. Health Inf. 22, 1486\u20131496 (2018).","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"2493_CR49","unstructured":"Ganin, Y. et al. Domain-adversarial training of neural networks. Journal of machine learning research. 2015."},{"key":"2493_CR50","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.media.2018.12.002","volume":"52","author":"J Cai","year":"2019","unstructured":"Cai, J., Zhang, Z., Cui, L., Zheng, Y. & Yang, L. Towards cross-modal organ translation and segmentation: A cycle- and shape-consistent generative adversarial network. Med Image Anal. 52, 174\u2013184 (2019).","journal-title":"Med Image Anal."},{"key":"2493_CR51","doi-asserted-by":"crossref","unstructured":"Wollmann, T., Eijkman, C. S. & Rohr, K. Adversarial domain adaptation to improve automatic breast cancer grading in lymph nodes. In: Proc. IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). (IEEE, 2018).","DOI":"10.1109\/ISBI.2018.8363643"},{"key":"2493_CR52","doi-asserted-by":"publisher","first-page":"e2245","DOI":"10.7717\/peerj-cs.2245","volume":"10","author":"M Sivakumar","year":"2024","unstructured":"Sivakumar, M., Parthasarathy, S. & Padmapriya, T. Trade-off between training and testing ratio in machine learning for medical image processing. PeerJ Comput Sci. 10, e2245 (2024).","journal-title":"PeerJ Comput Sci."},{"key":"2493_CR53","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1038\/s41746-024-01130-8","volume":"7","author":"SV Kalmady","year":"2024","unstructured":"Kalmady, S. V. et al. Development and validation of machine learning algorithms based on electrocardiograms for cardiovascular diagnoses at the population level. npj Digit. Med. 7, 133 (2024).","journal-title":"npj Digit. Med."},{"key":"2493_CR54","doi-asserted-by":"publisher","first-page":"103613","DOI":"10.1016\/j.ebiom.2021.103613","volume":"73","author":"JW Hughes","year":"2021","unstructured":"Hughes, J. W. et al. Deep learning evaluation of biomarkers from echocardiogram videos. EBioMedicine 73, 103613 (2021).","journal-title":"EBioMedicine"},{"key":"2493_CR55","unstructured":"Ilse, M., Tomczak, J. M. & Welling, M. Attention-based deep multiple instance learning. In: Proc. International Conference on Machine Learning. (ICML, 2018)."},{"key":"2493_CR56","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al. Video Swin Transformer. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (IEEE, 2022).","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"2493_CR57","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al. Swin transformer: HIERArchical vision transformer using shifted windows. In: Proc. IEEE\/CVF International Conference on Computer Vision. (IEEE, 2021).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2493_CR58","doi-asserted-by":"crossref","unstructured":"Breiman, L. Random forests. Mach. Learn. 45, 5\u201332 (2001).","DOI":"10.1023\/A:1010933404324"},{"key":"2493_CR59","doi-asserted-by":"crossref","unstructured":"Chen, T. & Guestrin, C. XGBoost: A Scalable Tree Boosting System. In: Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. (SIGKDD, 2016).","DOI":"10.1145\/2939672.2939785"},{"key":"2493_CR60","unstructured":"Ke, G. et al. LightGBM: a highly efficient gradient boosting decision tree. Neural Inf. Process. Syst. 3146\u20133154 (2017)."},{"key":"2493_CR61","doi-asserted-by":"crossref","unstructured":"Grinsztajn, L., Oyallon, E. & Varoquaux, G. Why do tree-based models still outperform deep learning on typical tabular data? Neural Inf. Process. Syst. (NIPS, 2022).","DOI":"10.52202\/068431-0037"},{"key":"2493_CR62","first-page":"6679","volume":"35","author":"S\u00d6 Arik","year":"2021","unstructured":"Arik, S. \u00d6 & Pfister, T. TabNet: attentive interpretable tabular learning. Proc. Conf. AAAI Artif. Intell. 35, 6679\u20136687 (2021).","journal-title":"Proc. Conf. AAAI Artif. Intell."},{"key":"2493_CR63","doi-asserted-by":"crossref","unstructured":"VanderWeele, T. Causality, 2nd edn. J. R. Stat. Soc. Ser. A Stat. Soc. 174, 243\u2013244 (2011).","DOI":"10.1111\/j.1467-985X.2010.00676_7.x"},{"key":"2493_CR64","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3543848","volume":"55","author":"WC Sleeman IV","year":"2023","unstructured":"Sleeman, W. C. IV, Kapoor, R. & Ghosh, P. Multimodal classification: current landscape, taxonomy and future directions. ACM Comput. Surv. 55, 1\u201331 (2023).","journal-title":"ACM Comput. Surv."},{"key":"2493_CR65","unstructured":"Girlanda, F., Demler, O., Menze, B. & Davoudi, N. Enhancing cardiovascular disease prediction through multi-modal self-supervised learning. (British Machine Vision Conference, 2024)."},{"key":"2493_CR66","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: transformers for image recognition at scale. In: Proc. International Conference on Learning Representations. (ICML, 2021)."},{"key":"2493_CR67","doi-asserted-by":"publisher","first-page":"102719","DOI":"10.1016\/j.artmed.2023.102719","volume":"147","author":"B Borsos","year":"2024","unstructured":"Borsos, B., Allaart, C. G. & van Halteren, A. Predicting stroke outcome: a case for multimodal deep learning methods with tabular and CT Perfusion data. Artif. Intell. Med. 147, 102719 (2024).","journal-title":"Artif. Intell. Med."},{"key":"2493_CR68","doi-asserted-by":"crossref","unstructured":"P\u00f6lsterl, S., Wolf, T. N. & Wachinger, C. Combining 3D image and tabular data via the dynamic affine feature map transform. In: Proc. International Conference on Medical Image Computing and Computer-assisted Intervention. (Springer, 2021).","DOI":"10.1007\/978-3-030-87240-3_66"},{"key":"2493_CR69","doi-asserted-by":"crossref","unstructured":"Xu, J. et al. RemixFormer: a transformer model for precision skin tumor differential diagnosis via multi-modal imaging and non-imaging data. In: Proc. International Conference On Medical Image Computing And Computer-assisted Intervention. (Springer, 2022).","DOI":"10.1007\/978-3-031-16437-8_60"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02493-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02493-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02493-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T13:03:40Z","timestamp":1775739820000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02493-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,3]]},"references-count":69,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2493"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02493-w","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,3]]},"assertion":[{"value":"5 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 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":"304"}}