{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:06:02Z","timestamp":1772136362041,"version":"3.50.1"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T00:00:00Z","timestamp":1767398400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:00:00Z","timestamp":1768867200000},"content-version":"vor","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Detecting out-of-distribution (OOD) data is critical for ensuring the reliability and safety of deployed machine learning systems by mitigating model overconfidence and misclassification. While existing OOD detection methods primarily focus on uni-modal inputs, such as images or text, their effectiveness in multi-modal settings, particularly documents, remains underexplored. Moreover, most approaches prioritize decision mechanisms over optimizing the underlying dense embedding representations for optimal separation. In this work, we introduce Attention Head Masking (AHM), a novel technique applied to Transformer-based models for both uni-modal and multi-modal OOD detection. Our empirical results demonstrate that AHM enhances embedding quality, significantly improving the separation between in-distribution and OOD data. Notably, our method reduces the false positive rate (FPR) by up to 10%, outperforming state-of-the-art approaches. Furthermore, AHM generalizes effectively to multi-modal document data, where textual and visual information are jointly modeled within a Transformer architecture. To encourage further research in this area, we introduce FinanceDocs, a high-quality, publicly available document AI dataset tailored for OOD detection. Our code and dataset is available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/constantinouchristos\/OOD-AHM\" ext-link-type=\"uri\">https:\/\/github.com\/constantinouchristos\/OOD-AHM<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1038\/s41598-025-32328-9","type":"journal-article","created":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T01:59:32Z","timestamp":1767491972000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Out of distribution detection with attention head masking for multimodal document classification"],"prefix":"10.1038","volume":"16","author":[{"given":"Christos","family":"Constantinou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Ioannides","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aman","family":"Chadha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron","family":"Elkins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edwin","family":"Simpson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,3]]},"reference":[{"key":"32328_CR1","unstructured":"Stanislav, F., Jie, R., &amp; Balaji, L. Exploring the Limits of Out-of-Distribution Detection. In M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan, editors, Advances in Neural Information Processing Systems, 34, 7068\u20137081. Curran Associates, Inc., (2021)."},{"key":"32328_CR2","unstructured":"Yarin, G. &amp; Zoubin, G. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In Maria Florina Balcan and Kilian Q. Weinberger, editors, Proceedings of The 33rd International Conference on Machine Learning, 48 of Proceedings of Machine Learning Research, 1050\u20131059, New York, New York, USA, 20\u201322  (2016)."},{"key":"32328_CR3","doi-asserted-by":"crossref","unstructured":"Sishuo, C., Xiaohan, B., Rundong, G., &amp; Xu,&nbsp;S. Holistic Sentence Embeddings for Better Out-of-Distribution Detection. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang, editors, Findings of the Association for Computational Linguistics: EMNLP 6676\u20136686, Abu Dhabi, United Arab Emirates, (2022).","DOI":"10.18653\/v1\/2022.findings-emnlp.497"},{"key":"32328_CR4","unstructured":"Jingkang, Y. et al. Openood: Benchmarking Generalized Out-of Distribution Detection. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Information Processing Systems, 35, 32598\u201332611. Curran Associates, Inc., (2022)."},{"key":"32328_CR5","doi-asserted-by":"crossref","unstructured":"Jiuxiang, G. et al. A critical Analysis of Document Out-of-Distribution Detection. In Houda Bouamor, Juan Pino, and Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023 4973\u20134999, (Association for Computational Linguistics, Singapore, 2023).","DOI":"10.18653\/v1\/2023.findings-emnlp.332"},{"key":"32328_CR6","doi-asserted-by":"crossref","unstructured":"Lewis, D. et&nbsp;al. Building a Test Collection for Complex Document Information Processing. In Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR \u201906, 665\u2013666, New York, NY, USA, (2006).","DOI":"10.1145\/1148170.1148307"},{"issue":"8","key":"32328_CR7","first-page":"9507","volume":"37","author":"Y Qiao","year":"2023","unstructured":"Qiao, Y. et al. Mutual-Enhanced Incongruity Learning Network for Multi-Modal Sarcasm Detection. Proc. AAAI Conf. Artif. Intell. 37(8), 9507\u20139515 (2023).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"32328_CR8","doi-asserted-by":"crossref","unstructured":"Binghao, T., Boda, L., Haolong, Y. & Si, L. Leveraging Generative Large Language Models with Visual Instruction and Demonstration Retrieval for Multimodal Sarcasm Detection. In Kevin Duh, Helena Gomez, and Steven Bethard, editors, Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 1 1732\u20131742, (2024).","DOI":"10.18653\/v1\/2024.naacl-long.97"},{"key":"32328_CR9","volume-title":"and Ji-Rong Wen","author":"Y Niu","year":"2021","unstructured":"Niu, Y., Tang, K., Zhang, H., Zhiwu, L. & Hua, X.-S. and Ji-Rong Wen Counterfactual VQA: A Cause-Effect Look at Language Bias. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12700\u201312710, June (2021)."},{"key":"32328_CR10","doi-asserted-by":"crossref","unstructured":"Teng S. et al. Counterfactual Reasoning for Out-of-Distribution Multimodal Sentiment Analysis. In Proceedings of the 30th ACM International Conference on Multimedia, MM \u201922, 15\u201323. (ACM, 2022).","DOI":"10.1145\/3503161.3548211"},{"key":"32328_CR11","doi-asserted-by":"crossref","unstructured":"Teng, S. et al. General Debiasing for Multimodal Sentiment Analysis. In Proceedings of the 31st ACM International Conference on Multimedia, MM \u201923,  5861\u20135869, (2023).","DOI":"10.1145\/3581783.3612051"},{"key":"32328_CR12","unstructured":"Murat, S., Melih, K., & Lance,M. K. Evidential Deep Learning to Quantify Classification Uncertainty. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa Bianchi, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc., (2018)."},{"key":"32328_CR13","unstructured":"Pirzada, S., Rehna, A., & Amit, S. Network Inversion for Uncertainty-Aware Out-of-Distribution Detection. CoRR arXiv:2505.23448   (2025)."},{"key":"32328_CR14","doi-asserted-by":"crossref","unstructured":"Hugo, L. K., Sarah, E., &amp; Christopher, L. Halo: Robust Out-of-Distribution Detection via Joint Optimisation. In 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML),  402\u2013426, (2025).","DOI":"10.1109\/SaTML64287.2025.00029"},{"key":"32328_CR15","unstructured":"Eduardo, A., Bogdan, R.,  Petia, R. Multi-Label Out-of-Distribution Detection via Evidential Learning. In Alessio Del Bue, Cristian Canton, Jordi Pont-Tuset, and Tatiana Tommasi, editors, Computer Vision \u2013 ECCV 2024 Workshops,  202\u2013218, Cham, (2025)."},{"key":"32328_CR16","unstructured":"Leitian, T., Xuefeng, D., Xiaojin, Z., & Yixuan, L. Non-Parametric Outlier Dynthesis.CoRR arXiv:2303.02966  (2023)."},{"key":"32328_CR17","unstructured":"Sishuo, C., Wenkai, Y., Xiaohan, B., & Xu,&nbsp;S. Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features.CoRR arXiv:2301.12715  (2023)."},{"key":"32328_CR18","unstructured":"Dan, H. & Kevin, G. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks. CoRR arXiv:1610.02136 (2016)."},{"key":"32328_CR19","unstructured":"Dan, H. et al. A Benchmark for Anomaly Segmentation. CoRR arXiv:1911.11132 (2019)."},{"key":"32328_CR20","unstructured":"Rui, H., Andrew, G. & Yixuan, L. On the Importance of Gradients for Detecting Distributional Shifts in the Wild. In M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan, editors, Advances in Neural Information Processing Systems, 34,  677\u2013689. Curran Associates, Inc., (2021)."},{"key":"32328_CR21","unstructured":"Shiyu, L., Yixuan, L. & R. S. Principled Detection of Out-of-Distribution Examples in Neural Networks. CoRR arXiv:1706.02690 (2017)."},{"key":"32328_CR22","unstructured":"Yiyou, S. & Yixuan, L. On the Effectiveness of Sparsification for Detecting the Deep Unknowns. CoRR arXiv:2111.09805 (2021)."},{"key":"32328_CR23","unstructured":"Yiyou, S., Chuan, G. & Yixuan, L. React: Out-of-Distribution Detection with Rectified Activations. In M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan, editors, Advances in Neural Information Processing Systems, volume 34, pages 144\u2013157. Curran Associates, Inc., (2021)."},{"key":"32328_CR24","unstructured":"Haoqi, W., Zhizhong, L., Litong, F.  Wayne Zhang. Vim: Out-of-Distribution with Virtual-Logit Matching. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4921\u20134930,  (2022)."},{"key":"32328_CR25","unstructured":"Andrija, D., Nebojsa, B., Arjun, A. & Rosanne, L. Extremely Simple Activation Shaping for Out-of-Distribution Detection.CoRR arXiv:2209.09858  (2023)."},{"key":"32328_CR26","unstructured":"Weitang, L., Xiaoyun, W., John, O. & Yixuan, L. Energy-Based Out-of-Distribution Detection. In: Advances in Neural Information Processing Systems (eds H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin), 33,  21464\u201321475. (Curran Associates, Inc., 2020)."},{"key":"32328_CR27","unstructured":"Yifei, M., Yiyou, S., Ousmane, D., & Yixuan, L. How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?CoRR arXiv:2203.04450  (2023)."},{"key":"32328_CR28","unstructured":"Kimin, L., Kibok, L., Honglak, L. &amp; Jinwoo, S. A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, editors, Advances in Neural Information Processing Systems,  31. Curran Associates, Inc., (2018)."},{"key":"32328_CR29","unstructured":"Yiyou, S., Yifei, M., Xiaojin, Z. &amp; Yixuan, L. Out-of-Distribution Detection with Deep Nearest Neighbors. In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato, editors, Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research, 20827\u201320840. PMLR, 17\u201323 (2022)."},{"key":"32328_CR30","unstructured":"Yifei, M., Haoyue, B., Julian, K.-S. Yixuan, L. Hypo: Hyperspherical Out-of-Distribution Generalization.CoRR arXiv:2402.07785  (2024)."},{"key":"32328_CR31","unstructured":"Mou\u00efn, B. A., Nacim, B., Sebastian, P., Antoine, M. & Gianni, F. Neco: Neural Collapse Based Out-of-Distribution Detection.CoRR arXiv:2310.06823  (2024)."},{"key":"32328_CR32","doi-asserted-by":"crossref","unstructured":"Vardan, P., X.Y. H. & David,&nbsp;L. D. Prevalence of Neural Collapse During the Terminal Phase of Deep Learning Training. Proceedings of the National Academy of Sciences, 117(40):24652\u201324663, September 2020.","DOI":"10.1073\/pnas.2015509117"},{"key":"32328_CR33","unstructured":"Kaiyang, Z., Ziwei, L., Yu, Q., Tao, X. & Chen, C. L. Domain Generalization: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4396\u20134415 2023."},{"key":"32328_CR34","unstructured":"Haotian Y. et al. Towards a Theoretical Framework of Out-of-Distribution Generalization. In M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan, editors, Advances in Neural Information Processing Systems,  Curran Associates, Inc.  34, 23519\u201323531. (2021)."},{"key":"32328_CR35","unstructured":"Ting C., Simon, K., Mohammad, N. & Geoffrey, H. A Simple Framework for Contrastive Learning of Visual Representations. In: Proceedings of the 37th International Conference on Machine Learning (eds Hal, D. III & Aarti, S.) Proceedings of Machine Learning Research, 119 13\u201318 1597\u20131607. (2020)."},{"key":"32328_CR36","unstructured":"Junnan, L., Pan, Z., Caiming, X. &amp; Steven, C.&nbsp;H. H. Prototypical Contrastive Learning of Unsupervised Representations. (2021)."},{"key":"32328_CR37","unstructured":"Haodong, L. et al. Learning with Mixture of Prototypes for Out-of-Distribution Detection.CoRR arXiv:2402.02653  (2024)."},{"key":"32328_CR38","doi-asserted-by":"crossref","unstructured":"Yifan D. et al. Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations. In Jens Petersen and Vedrana Andersen Dahl, editors, Image Analysis, Springer Nature 166\u2013179, Cham, (2025).","DOI":"10.1007\/978-3-031-95918-9_12"},{"key":"32328_CR39","unstructured":"Jonathan, H., Ajay, J. & Pieter, A. Denoising Diffusion Probabilistic Models. In: Advances in Neural Information Processing Systems (eds Larochelle, H. et al.) 33, 6840\u20136851. (Curran Associates, Inc., 2020)."},{"key":"32328_CR40","unstructured":"Hongyang, Z. et al. Theoretically Principled Trade-off between Robustness and Accuracy. In Kamalika Chaudhuri and Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, 7472\u20137482 (2019)."},{"key":"32328_CR41","unstructured":"Xuefeng, D., Zhaoning, W., Mu.&nbsp;C. & Yixuan, L. Vos: Learning what You Don\u2019t Know by Virtual Outlier Synthesis.CoRR arXiv:2202.01197  (2022)."},{"key":"32328_CR42","doi-asserted-by":"crossref","unstructured":"Haowei, L. &amp; Yuntian, G. Flats: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Score. In Houda Bouamor, Juan Pino, and Kalika Bali, editors, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 8956\u20138963 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.554"},{"key":"32328_CR43","unstructured":"Jacob, D., Ming-Wei, C., Kenton, L. &amp; Kristina, T. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Jill Burstein, Christy Doran, and Thamar Solorio, editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 1  4171\u20134186 (2019)."},{"key":"32328_CR44","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A Robustly Optimized BERT Pretraining Approach. CoRR, arXiv:1907.11692, (2019)."},{"key":"32328_CR45","doi-asserted-by":"crossref","unstructured":"Yupan, H., Tengchao, L., Lei, C., Yutong, L. &amp; Furu, W. Layoutlmv3: Pre-training for Document AI with Unified Text and Image Masking. In Proceedings of the 30th ACM International Conference on Multimedia, MM \u201922,  Association for Computing Machinery.4083\u20134091, (2022).","DOI":"10.1145\/3503161.3548112"},{"issue":"56","key":"32328_CR46","first-page":"1929","volume":"15","author":"Nitish Srivastava","year":"2014","unstructured":"Srivastava, Nitish, Hinton, Geoffrey, Krizhevsky, Alex, Sutskever, Ilya & Salakhutdinov, Ruslan. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. J. Mach. Learn. Res. 15(56), 1929\u20131958 (2014).","journal-title":"J. Mach. Learn. Res."},{"key":"32328_CR47","unstructured":"Ashish, V. et al. Attention Is All You Need. In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, Curran Associates, Inc.30 (2017)."},{"key":"32328_CR48","unstructured":"Danny, W. et al. A Unified Theory of Diversity in Ensemble Learning. Journal of Machine Learning Research, 24 (359), 1\u201349 (2023)."},{"key":"32328_CR49","doi-asserted-by":"crossref","unstructured":"Jayant, K., Peng, Y. & David, Do. Structural Similarity for Document Image Classification and Retrieval. Pattern Recognit. Lett. 43, 119\u2013126 (2014).","DOI":"10.1016\/j.patrec.2013.10.030"},{"key":"32328_CR50","unstructured":"Annual Reports. Annual Reports. https:\/\/www.annualreports.com\/Browse\/Industry. (2024)."},{"key":"32328_CR51","unstructured":"SEC EDGAR Database. SEC EDGAR Database. https:\/\/www.sec.gov\/edgar\/search\/. (2024)."},{"key":"32328_CR52","unstructured":"Companies House Service. Companies House Service. https:\/\/find-and-update.company-information.service.gov.uk\/. (2024)."},{"key":"32328_CR53","unstructured":"ACL Anthology. ACL Anthology. https:\/\/aclanthology.org\/. (2024)."},{"key":"32328_CR54","unstructured":"Resume Dataset. Resume Dataset. https:\/\/www.kaggle.com\/datasets\/snehaanbhawal\/resume-dataset.(2024)."},{"key":"32328_CR55","doi-asserted-by":"crossref","unstructured":"Richard, S. et al. Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank. In David Yarowsky, Timothy Baldwin, Anna Korhonen, Karen Livescu, and Steven Bethard, editors, Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, 1631\u20131642 (2013).","DOI":"10.18653\/v1\/D13-1170"},{"key":"32328_CR56","unstructured":"Andrew L. M. et al. Learning Word Vectors for Sentiment Analysis. In Dekang Lin, Yuji Matsumoto, and Rada Mihalcea, editors, Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies,142\u2013150 (2011)."},{"key":"32328_CR57","doi-asserted-by":"crossref","unstructured":"Ken, L. Newsweeder: Learning to Filter Netnews. In: Machine Learning Proceedings 1995 (ed Armand, P. & Stuart, R.) 331\u2013339. (Morgan Kaufmann, San Francisco (CA), 1995).","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"32328_CR58","doi-asserted-by":"crossref","unstructured":"Jingkang, Y., Kaiyang Z., Yixuan L. &amp; Ziwei L. Generalized Out-of-Distribution Detection: A survey. International Journal of Computer Vision, 132 (12), 5635\u20135662, (2024).","DOI":"10.1007\/s11263-024-02117-4"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-32328-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-32328-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-32328-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T11:17:48Z","timestamp":1768907868000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-32328-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,3]]},"references-count":58,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["32328"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-32328-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-6602601\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,3]]},"assertion":[{"value":"6 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"2449"}}