{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T04:40:21Z","timestamp":1768538421533,"version":"3.49.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T00:00:00Z","timestamp":1685664000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T00:00:00Z","timestamp":1685664000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Faculty of Health at Witten\/Herdecke University"},{"DOI":"10.13039\/100010127","name":"J\u00fcrgen Manchot Stiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010127","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Financial support by the J\u00fcrgen Machnot Foundation"},{"name":"Leuk\u00e4mie Lymphom Liga e.V, Germany Spiess Stiftung, D\u00fcsseldorf, Germany"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Serious clinical complications (SCC; CTCAE grade\u2009\u2265\u20093) occur frequently in patients treated for hematological malignancies. Early diagnosis and treatment of SCC are essential to improve outcomes. Here we report a deep learning model-derived SCC-Score to detect and predict SCC from time-series data recorded continuously by a medical wearable. In this single-arm, single-center, observational cohort study, vital signs and physical activity were recorded with a wearable for 31,234\u2009h in 79 patients (54 Inpatient Cohort (IC)\/25 Outpatient Cohort (OC)). Hours with normal physical functioning without evidence of SCC (regular hours) were presented to a deep neural network that was trained by a self-supervised contrastive learning objective to extract features from the time series that are typical in regular periods. The model was used to calculate a SCC-Score that measures the dissimilarity to regular features. Detection and prediction performance of the SCC-Score was compared to clinical documentation of SCC (AUROC\u2009\u00b1\u2009SD). In total 124 clinically documented SCC occurred in the IC, 16 in the OC. Detection of SCC was achieved in the IC with a sensitivity of 79.7% and specificity of 87.9%, with AUROC of 0.91\u2009\u00b1\u20090.01 (OC sensitivity 77.4%, specificity 81.8%, AUROC 0.87\u2009\u00b1\u20090.02). Prediction of infectious SCC was possible up to 2\u2009days before clinical diagnosis (AUROC 0.90 at \u221224\u2009h and 0.88 at \u221248\u2009h). We provide proof of principle for the detection and prediction of SCC in patients treated for hematological malignancies using wearable data and a deep learning model. As a consequence, remote patient monitoring may enable pre-emptive complication management.<\/jats:p>","DOI":"10.1038\/s41746-023-00847-2","type":"journal-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T16:02:18Z","timestamp":1685721738000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Wearable based monitoring and self-supervised contrastive learning detect clinical complications during treatment of Hematologic malignancies"],"prefix":"10.1038","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0780-0003","authenticated-orcid":false,"given":"Malte","family":"Jacobsen","sequence":"first","affiliation":[]},{"given":"Rahil","family":"Gholamipoor","sequence":"additional","affiliation":[]},{"given":"Till A.","family":"Dembek","sequence":"additional","affiliation":[]},{"given":"Pauline","family":"Rottmann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3361-3722","authenticated-orcid":false,"given":"Marlo","family":"Verket","sequence":"additional","affiliation":[]},{"given":"Julia","family":"Brandts","sequence":"additional","affiliation":[]},{"given":"Paul","family":"J\u00e4ger","sequence":"additional","affiliation":[]},{"given":"Ben-Niklas","family":"Baermann","sequence":"additional","affiliation":[]},{"given":"Mustafa","family":"Kondakci","sequence":"additional","affiliation":[]},{"given":"Lutz","family":"Heinemann","sequence":"additional","affiliation":[]},{"given":"Anna L.","family":"Gerke","sequence":"additional","affiliation":[]},{"given":"Nikolaus","family":"Marx","sequence":"additional","affiliation":[]},{"given":"Dirk","family":"M\u00fcller-Wieland","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7861-3892","authenticated-orcid":false,"given":"Kathrin","family":"M\u00f6llenhoff","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9473-8262","authenticated-orcid":false,"given":"Melchior","family":"Seyfarth","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5317-5408","authenticated-orcid":false,"given":"Markus","family":"Kollmann","sequence":"additional","affiliation":[]},{"given":"Guido","family":"Kobbe","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,6,2]]},"reference":[{"key":"847_CR1","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1001\/jamaoncol.2019.0086","volume":"5","author":"V Jairam","year":"2019","unstructured":"Jairam, V. et al. Treatment-related complications of systemic therapy and radiotherapy. JAMA Oncol. 5, 1028\u20131035 (2019).","journal-title":"JAMA Oncol."},{"key":"847_CR2","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1016\/j.jiac.2016.05.006","volume":"22","author":"U Sahin","year":"2016","unstructured":"Sahin, U., Toprak, S. K., Atilla, P. A., Atilla, E. & Demirer, T. An overview of infectious complications after allogeneic hematopoietic stem cell transplantation. J. Infect. Chemother. 22, 505\u2013514 (2016).","journal-title":"J. Infect. Chemother."},{"key":"847_CR3","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1200\/JOP.18.00269","volume":"15","author":"AJ Zimmer","year":"2019","unstructured":"Zimmer, A. J. & Freifeld, A. G. Optimal management of neutropenic fever in patients with cancer. J. Oncol. Pr. 15, 19\u201324 (2019).","journal-title":"J. Oncol. Pr."},{"key":"847_CR4","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-86911-x","volume":"11","author":"A Saxena","year":"2021","unstructured":"Saxena, A. et al. Hospitalization rates for complications due to systemic therapy in the United States. Sci. Rep. 11, 7385 (2021).","journal-title":"Sci. Rep."},{"key":"847_CR5","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1080\/07357900801905519","volume":"26","author":"MT Halpern","year":"2008","unstructured":"Halpern, M. T. & Yabroff, K. R. Prevalence of outpatient cancer treatment in the United States: estimates from the Medical Panel Expenditures Survey (MEPS). Cancer Invest 26, 647\u2013651 (2008).","journal-title":"Cancer Invest"},{"key":"847_CR6","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1038\/s41746-020-00351-x","volume":"3","author":"CA Low","year":"2020","unstructured":"Low, C. A. Harnessing consumer smartphone and wearable sensors for clinical cancer research. NPJ Digit Med 3, 140 (2020).","journal-title":"NPJ Digit Med"},{"key":"847_CR7","doi-asserted-by":"publisher","first-page":"e176","DOI":"10.1200\/JOP.2017.028191","volume":"14","author":"L Panattoni","year":"2018","unstructured":"Panattoni, L. et al. Characterizing potentially preventable cancer- and chronic disease-related emergency department use in the year after treatment initiation: a regional study. J. Oncol. Pr. 14, e176\u2013e185 (2018).","journal-title":"J. Oncol. Pr."},{"key":"847_CR8","doi-asserted-by":"publisher","first-page":"e259","DOI":"10.1200\/JOP.2016.017277","volume":"13","author":"LM Goodman","year":"2017","unstructured":"Goodman, L. M. et al. Improving the management of patients with low-risk neutropenic fever at the Cleveland Clinic Taussig Cancer Institute. J. Oncol. Pr. 13, e259\u2013e265 (2017).","journal-title":"J. Oncol. Pr."},{"key":"847_CR9","doi-asserted-by":"publisher","unstructured":"Jacobsen M, D. T., Kobbe G., Gaidzik P. W., and Heinemann L. Noninvasive continuous monitoring of vital signs with wearables: fit for medical use? J. Diabetes Sci. Technol. https:\/\/doi.org\/10.1177\/1932296820904947 (2020).","DOI":"10.1177\/1932296820904947"},{"key":"847_CR10","doi-asserted-by":"publisher","first-page":"e22006","DOI":"10.2196\/22006","volume":"8","author":"UL Beauchamp","year":"2020","unstructured":"Beauchamp, U. L., Pappot, H. & Hollander-Mieritz, C. The use of wearables in clinical trials during cancer treatment: systematic review. JMIR Mhealth Uhealth 8, e22006 (2020).","journal-title":"JMIR Mhealth Uhealth"},{"key":"847_CR11","doi-asserted-by":"publisher","unstructured":"Goldsack, J. A. A., Coravos, A., Economos, C. and Lyden K. The role of digital clinical measures in improving cancer care and research. J. Clin. Oncol. https:\/\/doi.org\/10.1200\/JCO.2021.39.15_suppl.e13584 (2021).","DOI":"10.1200\/JCO.2021.39.15_suppl.e13584"},{"key":"847_CR12","first-page":"1","volume":"2","author":"AA Wright","year":"2018","unstructured":"Wright, A. A. et al. The HOPE pilot study: harnessing patient-reported outcomes and biometric data to enhance cancer care. JCO Clin. Cancer Inf. 2, 1\u201312 (2018).","journal-title":"JCO Clin. Cancer Inf."},{"key":"847_CR13","doi-asserted-by":"publisher","first-page":"283rv283","DOI":"10.1126\/scitranslmed.aaa3487","volume":"7","author":"SR Steinhubl","year":"2015","unstructured":"Steinhubl, S. R., Muse, E. D. & Topol, E. J. The emerging field of mobile health. Sci. Transl. Med. 7, 283rv283 (2015).","journal-title":"Sci. Transl. Med."},{"key":"847_CR14","first-page":"11839","volume":"33","author":"J Tack","year":"2020","unstructured":"Tack, J., Mo, S., Jeong, J. & Shin, J. Csi: Novelty detection via contrastive learning on distributionally shifted instances. Adv. Neural Inf. Process. Syst. 33, 11839\u201311852 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"#cr-split#-847_CR15.1","unstructured":"Rafiee, N. et al. Artificial Neural Networks and Machine Learning-ICANN 2022: 31st International Conference on Artificial Neural Networks, Bristol, UK, September 6-9, 2022, Proceedings"},{"key":"#cr-split#-847_CR15.2","unstructured":"Part IV. 459-470 (Springer, 2022)."},{"key":"847_CR16","doi-asserted-by":"crossref","first-page":"e2100126","DOI":"10.1200\/CCI.21.00126","volume":"6","author":"M Jacobsen","year":"2022","unstructured":"Jacobsen, M. et al. Feasibility of wearable-based remote monitoring in patients during intensive treatment for aggressive hematologic malignancies. JCO Clin. Cancer Inf. 6, e2100126 (2022).","journal-title":"JCO Clin. Cancer Inf."},{"key":"847_CR17","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-019-1466-7","volume":"17","author":"B Van Calster","year":"2019","unstructured":"Van Calster, B. et al. Calibration: the Achilles heel of predictive analytics. BMC Med. 17, 230 (2019).","journal-title":"BMC Med."},{"key":"847_CR18","doi-asserted-by":"publisher","first-page":"e006513","DOI":"10.1161\/CIRCHEARTFAILURE.119.006513","volume":"13","author":"J Stehlik","year":"2020","unstructured":"Stehlik, J. et al. Continuous wearable monitoring analytics predict heart failure hospitalization: the LINK-HF multicenter study. Circ. Heart Fail 13, e006513 (2020).","journal-title":"Circ. Heart Fail"},{"key":"847_CR19","unstructured":"Kaplan, J. et al. Scaling laws for neural language models. arXiv https:\/\/arxiv.org\/abs\/2001.08361 (2020)."},{"key":"847_CR20","unstructured":"Oord, A. et al. Wavenet: A generative model for raw audio. arXiv https:\/\/arxiv.org\/abs\/1609.03499 (2016)."},{"key":"847_CR21","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.spl.2013.10.018","volume":"85","author":"M Perez","year":"2014","unstructured":"Perez, M. & Pericchi, L. Changing statistical significance with the amount of information: the adaptive \u03b1 significance level. Stat. Probab. Lett. 85, 20\u201324 (2014).","journal-title":"Stat. Probab. Lett."},{"key":"847_CR22","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1200\/JOP.2016.016857","volume":"13","author":"MS Beg","year":"2017","unstructured":"Beg, M. S., Gupta, A., Stewart, T. & Rethorst, C. D. Promise of wearable physical activity monitors in oncology practice. J. Oncol. Pr. 13, 82\u201389 (2017).","journal-title":"J. Oncol. Pr."},{"key":"847_CR23","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1038\/s41591-021-01339-0","volume":"27","author":"J Dunn","year":"2021","unstructured":"Dunn, J. et al. Wearable sensors enable personalized predictions of clinical laboratory measurements. Nat. Med. 27, 1105\u20131112 (2021).","journal-title":"Nat. Med."},{"key":"847_CR24","unstructured":"National Cancer Institute. Common Terminology Criteria for Adverse Events. Version 4.03. https:\/\/ctep.cancer.gov\/protocoldevelopment\/electronic_applications\/ctc.htm (2010)."},{"key":"847_CR25","doi-asserted-by":"publisher","unstructured":"Ting Chen, S. K., Mohammad, N. & Geoffrey, H. A simple framework for contrastive learning of visual representations. arXiv https:\/\/doi.org\/10.48550\/arXiv.2002.05709 (2020).","DOI":"10.48550\/arXiv.2002.05709"},{"key":"847_CR26","doi-asserted-by":"crossref","unstructured":"Hong, S., et al. Holmes: health online model ensemble serving for deep learning models in intensive care units. In Proc. 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1614\u20131624 (ACM, 2020).","DOI":"10.1145\/3394486.3403212"},{"key":"847_CR27","unstructured":"Yang, J., Zhou, K., Li, Y. & Liu, Z. Generalized out-of-distribution detection: a survey. arXiv https:\/\/arxiv.org\/abs\/2110.11334 (2021)."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00847-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00847-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00847-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T16:21:45Z","timestamp":1702570905000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00847-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,2]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["847"],"URL":"https:\/\/doi.org\/10.1038\/s41746-023-00847-2","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,2]]},"assertion":[{"value":"5 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study was an Investigator Initiated trial. This research received funding from the internal grant program (Ph.D. and Dr. rer. nat. Program Biomedicine) of the Faculty of Health at Witten\/Herdecke University, Germany, by a grant from the Leuk\u00e4mie Lymphom Liga e.V, Germany, and by the Spiess Stiftung, D\u00fcsseldorf, Germany. The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"105"}}