{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T05:59:01Z","timestamp":1792735141875,"version":"4.5.0"},"reference-count":108,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100010661","name":"EC | Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["758985"],"award-info":[{"award-number":["758985"]}],"id":[{"id":"10.13039\/100010661","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>Patients who experienced postoperative delirium (POD) are at higher risk of poor outcomes like dementia or death. Previous machine learning models predicting POD mostly relied on time-aggregated features. We aimed to assess the potential of temporal patterns in clinical parameters during surgeries to predict POD.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Long short-term memory (LSTM) and transformer models, directly consuming time series, were compared to multi-layer perceptrons (MLPs) trained on time-aggregated features. We also fitted hybrid models, fusing either LSTM or transformer models with MLPs. Univariate Spearman\u2019s rank correlations and linear mixed-effect models establish the importance of individual features that we compared to transformers\u2019 attention weights.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Best performance is achieved by a transformer architecture ingesting 30\u2009min of intraoperative parameter sequences. Systolic invasive blood pressure and given opioids mark the most important input variables, in line with univariate feature importances.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Intraoperative temporal dynamics of clinical parameters, exploited by a transformer architecture named TRAPOD, are critical for the accurate prediction of POD.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1038\/s43856-024-00681-x","type":"journal-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T14:03:24Z","timestamp":1732716204000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Applying a transformer architecture to intraoperative temporal dynamics improves the prediction of postoperative delirium"],"prefix":"10.1038","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0808-3966","authenticated-orcid":false,"given":"Niklas","family":"Giesa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria","family":"Sekutowicz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kerstin","family":"Rubarth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudia Doris","family":"Spies","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1575-2056","authenticated-orcid":false,"given":"Felix","family":"Balzer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Haufe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7993-7901","authenticated-orcid":false,"given":"Sebastian Daniel","family":"Boie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"681_CR1","doi-asserted-by":"publisher","first-page":"4","DOI":"10.4097\/kja.d.18.00073.1","volume":"72","author":"S-T Oh","year":"2019","unstructured":"Oh, S.-T. & Park, J. Y. Postoperative delirium. Korean J. Anesthesiol. 72, 4\u201312 (2019).","journal-title":"Korean J. Anesthesiol."},{"key":"681_CR2","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1097\/EJA.0000000000000594","volume":"34","author":"C Aldecoa","year":"2017","unstructured":"Aldecoa, C. et al. European Society of Anaesthesiology evidence-based and consensus-based guideline on postoperative delirium. Eur. J. Anaesthesiol. 34, 192\u2013214 (2017).","journal-title":"Eur. J. Anaesthesiol."},{"key":"681_CR3","doi-asserted-by":"crossref","unstructured":"Trogrli\u0107, Z. et al. A systematic review of implementation strategies for assessment, prevention, and management of ICU delirium and their effect on clinical outcomes. Critical Care, 19, https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC4428250\/ (2015).","DOI":"10.1186\/s13054-015-0886-9"},{"key":"681_CR4","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1001\/jama.2010.1013","volume":"304","author":"J Witlox","year":"2010","unstructured":"Witlox, J. et al. Delirium in Elderly Patients and the Risk of Postdischarge Mortality, Institutionalization, and Dementia: A Meta-analysis. JAMA 304, 443 (2010).","journal-title":"JAMA"},{"key":"681_CR5","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1159\/000140804","volume":"26","author":"H Bickel","year":"2008","unstructured":"Bickel, H., Gradinger, R., Kochs, E. & F\u00f6rstl, H. High Risk of Cognitive and Functional Decline after Postoperative Delirium. Dement. Geriatr. Cogn. Disord. 26, 26\u201331 (2008).","journal-title":"Dement. Geriatr. Cogn. Disord."},{"key":"681_CR6","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1097\/JGP.0b013e318172b418","volume":"16","author":"MC Tan","year":"2008","unstructured":"Tan, M. C. et al. Incidence and Predictors of Post-Cardiotomy Delirium. Am. J. Geriatr. Psychiatry 16, 575\u2013583 (2008).","journal-title":"Am. J. Geriatr. Psychiatry"},{"key":"681_CR7","doi-asserted-by":"publisher","DOI":"10.1186\/s13063-018-3148-8","volume":"20","author":"PAWEL Study group.","year":"2019","unstructured":"PAWEL Study group. et al. Patient safety, cost-effectiveness, and quality of life: reduction of delirium risk and postoperative cognitive dysfunction after elective procedures in older adults\u2014study protocol for a stepped-wedge cluster randomized trial (PAWEL Study). Trials 20, 71 (2019).","journal-title":"Trials"},{"key":"681_CR8","doi-asserted-by":"crossref","unstructured":"European Delirium Association & American Delirium Society. The DSM-5 criteria, level of arousal and delirium diagnosis: inclusiveness is safer. BMC Med. 12, 141 (2014).","DOI":"10.1186\/s12916-014-0141-2"},{"key":"681_CR9","doi-asserted-by":"crossref","unstructured":"Hosker, C. & Ward, D. Hypoactive delirium. BMJ j2047, https:\/\/www.bmj.com\/lookup\/doi\/10.1136\/bmj.j2047 (2017).","DOI":"10.1136\/bmj.j2047"},{"key":"681_CR10","unstructured":"Netzer, M., Hackl, W. O., Schaller, M., Alber, L. & Ammenwerth, E. Evaluating Performance and Interpretability of Machine Learning Methods for Predicting Delirium in Gerontopsychiatric Patients. Stud. Health Technol. Inform. 271, 121\u2013128 (2020)."},{"key":"681_CR11","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-020-1449-8","volume":"20","author":"A Iamaroon","year":"2020","unstructured":"Iamaroon, A. et al. Incidence of and risk factors for postoperative delirium in older adult patients undergoing noncardiac surgery: a prospective study. BMC Geriatrics 20, 40 (2020).","journal-title":"BMC Geriatrics"},{"key":"681_CR12","doi-asserted-by":"crossref","unstructured":"Hargrave, A. et al. Validation of a Nurse-Based Delirium Screening Tool for Hospitalized Patients (P6.220). Neurology 86, https:\/\/n.neurology.org\/content\/86\/16_Supplement\/P6.220 (2016).","DOI":"10.1212\/WNL.86.16_supplement.P6.220"},{"key":"681_CR13","doi-asserted-by":"publisher","DOI":"10.1186\/cc11407","volume":"16","author":"D Gusmao-Flores","year":"2012","unstructured":"Gusmao-Flores, D., Salluh, J. I. F., Chalhub, R. & Quarantini, L. C. The confusion assessment method for the intensive care unit (CAM-ICU) and intensive care delirium screening checklist (ICDSC) for the diagnosis of delirium: a systematic review and meta-analysis of clinical studies. Crit. Care 16, R115 (2012).","journal-title":"Crit. Care"},{"key":"681_CR14","first-page":"81","volume":"41","author":"C Aldecoa","year":"2024","unstructured":"Aldecoa, C. et al. Update of the European Society of Anaesthesiology and Intensive Care Medicine evidence-based and consensus-based guideline on postoperative delirium in adult patients. Eur. J. Anaesthesiol. 41, 81\u2013108 (2024).","journal-title":"Eur. J. Anaesthesiol."},{"key":"681_CR15","doi-asserted-by":"publisher","first-page":"e0296","DOI":"10.1097\/CCE.0000000000000296","volume":"2","author":"MM Ruppert","year":"2020","unstructured":"Ruppert, M. M. et al. ICU Delirium-Prediction Models: A Systematic Review. Crit. Care Explorations 2, e0296 (2020).","journal-title":"Crit. Care Explorations"},{"key":"681_CR16","doi-asserted-by":"publisher","first-page":"2383","DOI":"10.1111\/jgs.13138","volume":"62","author":"LCC van Meenen","year":"2014","unstructured":"van Meenen, L. C. C., van Meenen, D. M. P., de Rooij, S. E. & ter Riet, G. Risk Prediction Models for Postoperative Delirium: A Systematic Review and Meta-Analysis. J. Am. Geriatrics Soc. 62, 2383\u20132390 (2014).","journal-title":"J. Am. Geriatrics Soc."},{"key":"681_CR17","doi-asserted-by":"publisher","unstructured":"Evered L. A. Predicting delirium: are we there yet?. British journal of anaesthesia. 119, 281\u2013283. https:\/\/doi.org\/10.1093\/bja\/aex082 (2017).","DOI":"10.1093\/bja\/aex082"},{"key":"681_CR18","doi-asserted-by":"publisher","first-page":"ooac048","DOI":"10.1093\/jamiaopen\/ooac048","volume":"5","author":"A Bhattacharyya","year":"2022","unstructured":"Bhattacharyya, A. et al. Delirium prediction in the ICU: designing a screening tool for preventive interventions. JAMIA Open 5, ooac048 (2022).","journal-title":"JAMIA Open"},{"key":"681_CR19","first-page":"568","volume":"2017","author":"A Davoudi","year":"2017","unstructured":"Davoudi, A. et al. Delirium Prediction using Machine Learning Models on Preoperative Electronic Health Records Data. Proc. IEEE Int. Symp. Bioinforma. Bioeng. 2017, 568\u2013573 (2017).","journal-title":"Proc. IEEE Int. Symp. Bioinforma. Bioeng."},{"key":"681_CR20","doi-asserted-by":"crossref","unstructured":"Lee, S., Mueller, B., Street, W. N. & Carnahan, R. M. Machine learning algorithm to predict delirium from emergency department data. Emergency Med. http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2021.02.19.21251956 (2021).","DOI":"10.1101\/2021.02.19.21251956"},{"key":"681_CR21","doi-asserted-by":"publisher","first-page":"1048","DOI":"10.1007\/s00134-015-3777-2","volume":"41","author":"A Wassenaar","year":"2015","unstructured":"Wassenaar, A. et al. Multinational development and validation of an early prediction model for delirium in ICU patients. Intensive Care Med. 41, 1048\u20131056 (2015).","journal-title":"Intensive Care Med."},{"key":"681_CR22","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/s00134-013-3202-7","volume":"40","author":"M van den Boogaard","year":"2014","unstructured":"van den Boogaard, M. et al. Recalibration of the delirium prediction model for ICU patients (PRE-DELIRIC): a multinational observational study. Intensive Care Med. 40, 361\u2013369 (2014).","journal-title":"Intensive Care Med."},{"key":"681_CR23","doi-asserted-by":"publisher","first-page":"e3072","DOI":"10.1097\/MD.0000000000003072","volume":"95","author":"MY Kim","year":"2016","unstructured":"Kim, M. Y., Park, U. J., Kim, H. T. & Cho, W. H. DELirium Prediction Based on Hospital Information (Delphi) in General Surgery Patients. Medicine 95, e3072 (2016).","journal-title":"Medicine"},{"key":"681_CR24","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/s41999-019-00287-w","volume":"11","author":"R Vreeswijk","year":"2020","unstructured":"Vreeswijk, R., Kalisvaart, I., Maier, A. B. & Kalisvaart, K. J. Development and validation of the delirium risk assessment score (DRAS). Eur. Geriatr. Med. 11, 307\u2013314 (2020).","journal-title":"Eur. Geriatr. Med."},{"key":"681_CR25","doi-asserted-by":"publisher","first-page":"2753","DOI":"10.1007\/s40520-021-01792-4","volume":"33","author":"A Zucchelli","year":"2021","unstructured":"Zucchelli, A. et al. Development and validation of a delirium risk assessment tool in older patients admitted to the Emergency Department Observation Unit. Aging Clin. Exp. Res. 33, 2753\u20132758 (2021).","journal-title":"Aging Clin. Exp. Res."},{"key":"681_CR26","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1111\/psyg.12511","volume":"20","author":"H Xing","year":"2020","unstructured":"Xing, H., Xiang, D., Li, Y., Ji, X. & Xie, G. Preoperative prognostic nutritional index predicts postoperative delirium in elderly patients after hip fracture surgery. Psychogeriatrics 20, 487\u2013494 (2020).","journal-title":"Psychogeriatrics"},{"key":"681_CR27","doi-asserted-by":"publisher","first-page":"e212240","DOI":"10.1001\/jamanetworkopen.2021.2240","volume":"4","author":"B Xue","year":"2021","unstructured":"Xue, B. et al. Use of Machine Learning to Develop and Evaluate Models Using Preoperative and Intraoperative Data to Identify Risks of Postoperative Complications. JAMA Netw. Open 4, e212240 (2021).","journal-title":"JAMA Netw. Open"},{"key":"681_CR28","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-018-1109-0","volume":"42","author":"JP Corradi","year":"2018","unstructured":"Corradi, J. P., Thompson, S., Mather, J. F., Waszynski, C. M. & Dicks, R. S. Prediction of Incident Delirium Using a Random Forest classifier. J. Med. Syst. 42, 261 (2018).","journal-title":"J. Med. Syst."},{"key":"681_CR29","doi-asserted-by":"publisher","DOI":"10.1186\/s12871-021-01543-y","volume":"22","author":"A Bishara","year":"2022","unstructured":"Bishara, A. et al. Postoperative delirium prediction using machine learning models and preoperative electronic health record data. BMC Anesthesiol. 22, 8 (2022).","journal-title":"BMC Anesthesiol."},{"key":"681_CR30","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1093\/jamia\/ocac210","volume":"30","author":"S Liu","year":"2022","unstructured":"Liu, S. et al. New onset delirium prediction using machine learning and long short-term memory (LSTM) in electronic health record. J. Am. Med. Inform. Assoc. 30, 120\u2013131 (2022).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"681_CR31","doi-asserted-by":"crossref","unstructured":"Chen, T. & Guestrin, C. XGBoost: A Scalable Tree Boosting System. arxiv, https:\/\/arxiv.org\/abs\/1603.02754 (2016).","DOI":"10.1145\/2939672.2939785"},{"key":"681_CR32","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1145\/65943.65945","volume":"7","author":"V Raghavan","year":"1989","unstructured":"Raghavan, V., Bollmann, P. & Jung, G. S. A critical investigation of recall and precision as measures of retrieval system performance. ACM Trans. Inf. Syst. 7, 205\u2013229 (1989).","journal-title":"ACM Trans. Inf. Syst."},{"key":"681_CR33","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1037\/h0042519","volume":"65","author":"F Rosenblatt","year":"1958","unstructured":"Rosenblatt, F. The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Rev. 65, 386\u2013408 (1958).","journal-title":"Psychological Rev."},{"key":"681_CR34","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. & Schmidhuber, J. Long Short-Term Memory. Neural Comput. 9, 1735\u20131780 (1997).","journal-title":"Neural Comput."},{"key":"681_CR35","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1016\/j.procir.2021.03.088","volume":"99","author":"B Lindemann","year":"2021","unstructured":"Lindemann, B., M\u00fcller, T., Vietz, H., Jazdi, N. & Weyrich, M. A survey on long short-term memory networks for time series prediction. Procedia CIRP 99, 650\u2013655 (2021).","journal-title":"Procedia CIRP"},{"key":"681_CR36","unstructured":"Shahriar, S. & Hayawi, K. Let\u2019s have a chat! A Conversation with ChatGPT: Technology, Applications, and Limitations. arxiv, https:\/\/arxiv.org\/abs\/2302.13817 (2023)"},{"key":"681_CR37","unstructured":"Vaswani, A. et al. Attention Is All You Need. arxiv, https:\/\/arxiv.org\/abs\/1706.03762 (2017)."},{"key":"681_CR38","doi-asserted-by":"publisher","first-page":"65395","DOI":"10.1109\/ACCESS.2020.2985418","volume":"8","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Peng, R.-Q., Wang, J.-Q., Li, Z. & Qu, H.-B. NEWLSTM: An Optimized Long Short-Term Memory Language Model for Sequence Prediction. IEEE Access 8, 65395\u201365401 (2020).","journal-title":"IEEE Access"},{"key":"681_CR39","unstructured":"Nerella, S. et al. Transformers in Healthcare: A Survey. arxiv, https:\/\/arxiv.org\/abs\/2307.00067 (2023)."},{"key":"681_CR40","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-30820-8","volume":"13","author":"LL Guo","year":"2023","unstructured":"Guo, L. L. et al. EHR foundation models improve robustness in the presence of temporal distribution shift. Sci. Rep. 13, 3767 (2023).","journal-title":"Sci. Rep."},{"key":"681_CR41","doi-asserted-by":"crossref","unstructured":"Peng, X. et al. Temporal Self-Attention Network for Medical Concept Embedding. In 2019 IEEE International Conference on Data Mining (ICDM), 498\u2013507 https:\/\/ieeexplore.ieee.org\/document\/8970822\/ (IEEE, Beijing, China, 2019).","DOI":"10.1109\/ICDM.2019.00060"},{"key":"681_CR42","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-25472-z","volume":"12","author":"BP Bednarski","year":"2022","unstructured":"Bednarski, B. P. et al. Temporal convolutional networks and data rebalancing for clinical length of stay and mortality prediction. Sci. Rep. 12, 21247 (2022).","journal-title":"Sci. Rep."},{"key":"681_CR43","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-24271-9","volume":"8","author":"Z Che","year":"2018","unstructured":"Che, Z., Purushotham, S., Cho, K., Sontag, D. & Liu, Y. Recurrent neural networks for multivariate time series with missing values. Sci. Rep. 8, 6085 (2018).","journal-title":"Sci. Rep."},{"key":"681_CR44","doi-asserted-by":"publisher","first-page":"103980","DOI":"10.1016\/j.jbi.2021.103980","volume":"126","author":"F Xie","year":"2022","unstructured":"Xie, F. et al. Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies. J. Biomed. Inform. 126, 103980 (2022).","journal-title":"J. Biomed. Inform."},{"key":"681_CR45","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1016\/j.psym.2017.05.005","volume":"58","author":"A Hargrave","year":"2017","unstructured":"Hargrave, A. et al. Validation of a Nurse-Based Delirium-Screening Tool for Hospitalized Patients. Psychosomatics 58, 594\u2013603 (2017).","journal-title":"Psychosomatics"},{"key":"681_CR46","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1016\/j.jpainsymman.2004.07.009","volume":"29","author":"J-D Gaudreau","year":"2005","unstructured":"Gaudreau, J.-D., Gagnon, P., Harel, F., Tremblay, A. & Roy, M.-A. Fast, Systematic, and Continuous Delirium Assessment in Hospitalized Patients: The Nursing Delirium Screening Scale. J. Pain. Symptom Manag. 29, 368\u2013375 (2005).","journal-title":"J. Pain. Symptom Manag."},{"key":"681_CR47","doi-asserted-by":"publisher","DOI":"10.1186\/s41512-020-00077-0","volume":"4","author":"RHH Groenwold","year":"2020","unstructured":"Groenwold, R. H. H. Informative missingness in electronic health record systems: the curse of knowing. Diagnostic Prognostic Res. 4, 8 (2020).","journal-title":"Diagnostic Prognostic Res."},{"key":"681_CR48","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1007\/s00103-007-0283-x","volume":"50","author":"B Graubner","year":"2007","unstructured":"Graubner, B. ICD und OPS: Historische Entwicklung und aktueller Stand. Bundesgesundheitsblatt Gesundheitsforschung Gesundheitsschutz 50, 932\u2013943 (2007).","journal-title":"Bundesgesundheitsblatt Gesundheitsforschung Gesundheitsschutz"},{"key":"681_CR49","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1177\/1740774515602688","volume":"13","author":"JM Lachin","year":"2016","unstructured":"Lachin, J. M. Fallacies of last observation carried forward analyses. Clin. Trials 13, 161\u2013168 (2016).","journal-title":"Clin. Trials"},{"key":"681_CR50","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1016\/0013-4694(70)90143-4","volume":"29","author":"B Hjorth","year":"1970","unstructured":"Hjorth, B. EEG analysis based on time domain properties. Electroencephalogr. Clin. Neurophysiol. 29, 306\u2013310 (1970).","journal-title":"Electroencephalogr. Clin. Neurophysiol."},{"key":"681_CR51","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/BF01456326","volume":"69","author":"A Haar","year":"1910","unstructured":"Haar, A. Zur Theorie der orthogonalen Funktionensysteme: Erste Mitteilung. Mathematische Ann. 69, 331\u2013371 (1910).","journal-title":"Mathematische Ann."},{"key":"681_CR52","doi-asserted-by":"crossref","unstructured":"Patro, S. G. K. & Sahu, K. K. Normalization: A Preprocessing Stage. arxiv, http:\/\/arxiv.org\/abs\/1503.06462 (2015).","DOI":"10.17148\/IARJSET.2015.2305"},{"key":"681_CR53","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1016\/0920-5489(94)90017-5","volume":"16","author":"M Riedmiller","year":"1994","unstructured":"Riedmiller, M. Advanced supervised learning in multi-layer perceptrons \u2014 From backpropagation to adaptive learning algorithms. Computer Stand. Interfaces 16, 265\u2013278 (1994).","journal-title":"Computer Stand. Interfaces"},{"key":"681_CR54","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.neucom.2022.06.111","volume":"503","author":"SR Dubey","year":"2022","unstructured":"Dubey, S. R., Singh, S. K. & Chaudhuri, B. B. Activation functions in deep learning: A comprehensive survey and benchmark. Neurocomputing 503, 92\u2013108 (2022).","journal-title":"Neurocomputing"},{"key":"681_CR55","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/BF02551274","volume":"2","author":"G Cybenko","year":"1989","unstructured":"Cybenko, G. Approximation by superpositions of a sigmoidal function. Math. Control, Signals, Syst. 2, 303\u2013314 (1989).","journal-title":"Math. Control, Signals, Syst."},{"key":"681_CR56","unstructured":"Bahdanau, D., Cho, K. & Bengio, Y. Neural Machine Translation by Jointly Learning to Align and Translate. arXiv, https:\/\/arxiv.org\/abs\/1409.0473 (2014)."},{"key":"681_CR57","unstructured":"Aitken, K., Ramasesh, V. V., Cao, Y. & Maheswaranathan, N. Understanding How Encoder-Decoder Architectures Attend. arXiv, https:\/\/arxiv.org\/abs\/2110.15253 (2021)."},{"key":"681_CR58","unstructured":"Wen, Q. et al. Transformers in Time Series: A Survey. arXiv, https:\/\/arxiv.org\/abs\/2202.07125 (2022)."},{"key":"681_CR59","unstructured":"Paszke, A. et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. arXiv, http:\/\/arxiv.org\/abs\/1912.01703 (2019)."},{"key":"681_CR60","unstructured":"Chen, P.-C. et al. A Simple and Effective Positional Encoding for Transformers. arXiv, https:\/\/arxiv.org\/abs\/2104.08698 (2021)."},{"key":"681_CR61","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","volume":"30","author":"AP Bradley","year":"1997","unstructured":"Bradley, A. P. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit. 30, 1145\u20131159 (1997).","journal-title":"Pattern Recognit."},{"key":"681_CR62","unstructured":"Boyd, K., Costa, V. S., Davis, J. & Page, C. D. Unachievable region in precision-recall space and its effect on empirical evaluation. In Proc. International Conference on Machine Learning. International Conference on Machine Learning, p. 349 (NIH, 2012)."},{"key":"681_CR63","doi-asserted-by":"publisher","first-page":"115222","DOI":"10.1016\/j.eswa.2021.115222","volume":"182","author":"J Wainer","year":"2021","unstructured":"Wainer, J. & Cawley, G. Nested cross-validation when selecting classifiers is overzealous for most practical applications. Expert Syst. Appl. 182, 115222 (2021).","journal-title":"Expert Syst. Appl."},{"key":"681_CR64","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1214\/aop\/1176990862","volume":"18","author":"E Gine","year":"1990","unstructured":"Gine, E. & Zinn, J. Bootstrapping General Empirical Measures. Ann. Probab. 18, 851\u2013869 (1990).","journal-title":"Ann. Probab."},{"key":"681_CR65","doi-asserted-by":"crossref","unstructured":"Alibrahim, H. & Ludwig, S. A. Hyperparameter Optimization: Comparing Genetic Algorithm against Grid Search and Bayesian Optimization. In 2021 IEEE Congress on Evolutionary Computation (CEC), 1551\u20131559 (IEEE, 2021).","DOI":"10.1109\/CEC45853.2021.9504761"},{"key":"681_CR66","unstructured":"Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A. & Talwalkar, A. Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization 52 (2016)."},{"key":"681_CR67","unstructured":"Kuleshov, V. & Precup, D. Algorithms for multi-armed bandit problems. arXiv, https:\/\/arxiv.org\/abs\/1402.6028 (2014)."},{"key":"681_CR68","doi-asserted-by":"crossref","unstructured":"Ho, Y. & Wookey, S. The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabeling. arXiv, https:\/\/arxiv.org\/abs\/2001.00570 (2020).","DOI":"10.1109\/ACCESS.2019.2962617"},{"key":"681_CR69","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K. & Doll\u00e1r, P. Focal Loss for Dense Object Detection. arXiv, https:\/\/arxiv.org\/abs\/1708.02002 (2017).","DOI":"10.1109\/ICCV.2017.324"},{"key":"681_CR70","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s00365-006-0663-2","volume":"26","author":"Y Yao","year":"2007","unstructured":"Yao, Y., Rosasco, L. & Caponnetto, A. On Early Stopping in Gradient Descent Learning. Constructive Approximation 26, 289\u2013315 (2007).","journal-title":"Constructive Approximation"},{"key":"681_CR71","doi-asserted-by":"publisher","first-page":"e048008","DOI":"10.1136\/bmjopen-2020-048008","volume":"11","author":"GS Collins","year":"2021","unstructured":"Collins, G. S. et al. Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence. BMJ Open 11, e048008 (2021).","journal-title":"BMJ Open"},{"key":"681_CR72","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1016\/j.jmva.2013.02.007","volume":"117","author":"C Genest","year":"2013","unstructured":"Genest, C., Ne\u0161lehov\u00e1, J. G. & R\u00e9millard, B. On the estimation of Spearman\u2019s rho and related tests of independence for possibly discontinuous multivariate data. J. Multivar. Anal. 117, 214\u2013228 (2013).","journal-title":"J. Multivar. Anal."},{"key":"681_CR73","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1023\/A:1024068626366","volume":"52","author":"C Nadeau","year":"2003","unstructured":"Nadeau, C. Inference for the Generalization Error. Mach. Learn. 52, 239\u2013281 (2003).","journal-title":"Mach. Learn."},{"key":"681_CR74","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1080\/00031305.1991.10475767","volume":"45","author":"RA McLean","year":"1991","unstructured":"McLean, R. A., Sanders, W. L. & Stroup, W. W. A Unified Approach to Mixed Linear Models. Am. Statistician 45, 54 (1991).","journal-title":"Am. Statistician"},{"key":"681_CR75","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1111\/2041-210X.13434","volume":"11","author":"H Schielzeth","year":"2020","unstructured":"Schielzeth, H. et al. Robustness of linear mixed-effects models to violations of distributional assumptions. Methods Ecol. Evolution 11, 1141\u20131152 (2020).","journal-title":"Methods Ecol. Evolution"},{"key":"681_CR76","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","volume":"57","author":"Y Benjamini","year":"1995","unstructured":"Benjamini, Y. & Hochberg, Y. Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing. J. R. Stat. Soc.: Ser. B (Methodol.) 57, 289\u2013300 (1995).","journal-title":"J. R. Stat. Soc.: Ser. B (Methodol.)"},{"key":"681_CR77","doi-asserted-by":"crossref","unstructured":"Bouckaert, R. R. & Frank, E. Evaluating the Replicability of Significance Tests for Comparing Learning Algorithms. In Advances in Knowledge Discovery and Data Mining (eds Kanade, T. et al.) 3056, 3\u2013123 (Springer Berlin Heidelberg, 2004).","DOI":"10.1007\/978-3-540-24775-3_3"},{"key":"681_CR78","doi-asserted-by":"publisher","DOI":"10.1186\/1475-925X-5-51","volume":"5","author":"F Azuaje","year":"2006","unstructured":"Azuaje, F., Witten, I. H. & Frank, E. Data Mining: Practical Machine Learning Tools and Techniques 2nd edition: San Francisco: Morgan Kaufmann Publishers; 2005:560. Biomed. Eng. OnLine 5, 51, https:\/\/doi.org\/10.1186\/1475-925X-5-51 (2006).","journal-title":"Biomed. Eng. OnLine"},{"key":"681_CR79","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1080\/0952813X.2012.680252","volume":"25","author":"D Berrar","year":"2013","unstructured":"Berrar, D. & Lozano, J. A. Significance tests or confidence intervals: which are preferable for the comparison of classifiers? J. Exp. Theor. Artif. Intell. 25, 189\u2013206 (2013).","journal-title":"J. Exp. Theor. Artif. Intell."},{"key":"681_CR80","unstructured":"Giesa, N. TRAPOD GitHub Repository, https:\/\/github.com\/ngiesa\/TRAPOD (2023)."},{"key":"681_CR81","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1093\/bja\/aew475","volume":"119","author":"B Palanca","year":"2017","unstructured":"Palanca, B., Wildes, T., Ju, Y., Ching, S. & Avidan, M. Electroencephalography and delirium in the postoperative period. BJA: Br. J. Anaesth. 119, 294\u2013307 (2017).","journal-title":"BJA: Br. J. Anaesth."},{"key":"681_CR82","doi-asserted-by":"publisher","first-page":"232","DOI":"10.5152\/TJAR.2015.93798","volume":"43","author":"EU Bilge","year":"2015","unstructured":"Bilge, E. U., Kaya, M., Senel, G. O. & Unver, S. The Incidence of Delirium at the Postoperative Intensive Care Unit in Adult Patients. Turkish J. Anesthesia Reanim. 43, 232\u2013239 (2015).","journal-title":"Turkish J. Anesthesia Reanim."},{"key":"681_CR83","doi-asserted-by":"publisher","first-page":"911088","DOI":"10.3389\/fnagi.2022.911088","volume":"14","author":"V R\u00f6hr","year":"2022","unstructured":"R\u00f6hr, V., Blankertz, B., Radtke, F. M., Spies, C. & Koch, S. Machine-learning model predicting postoperative delirium in older patients using intraoperative frontal electroencephalographic signatures. Front. Aging Neurosci. 14, 911088 (2022).","journal-title":"Front. Aging Neurosci."},{"key":"681_CR84","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-019-0167-0","volume":"2","author":"H Sun","year":"2019","unstructured":"Sun, H. et al. Automated tracking of level of consciousness and delirium in critical illness using deep learning. npj Digital Med. 2, 89 (2019).","journal-title":"npj Digital Med."},{"key":"681_CR85","doi-asserted-by":"crossref","unstructured":"von Dincklage, F., Jurth, C., Schneider, G., S Garc\u00eda, P. & Kreuzer, M. Technical considerations when using the EEG export of the SEDLine Root device. J. Clin. Monit. Comput. http:\/\/link.springer.com\/10.1007\/s10877-020-00578-9 (2020).","DOI":"10.1007\/s10877-020-00578-9"},{"key":"681_CR86","doi-asserted-by":"publisher","first-page":"1531","DOI":"10.1007\/s40520-023-02408-9","volume":"35","author":"L Bao","year":"2023","unstructured":"Bao, L. et al. The prediction of postoperative delirium with the preoperative bispectral index in older aged patients: a cohort study. Aging Clin. Exp. Res. 35, 1531\u20131539 (2023).","journal-title":"Aging Clin. Exp. Res."},{"key":"681_CR87","doi-asserted-by":"publisher","first-page":"103","DOI":"10.3389\/fnhum.2018.00103","volume":"12","author":"I Dowding","year":"2018","unstructured":"Dowding, I. & Haufe, S. Powerful Statistical Inference for Nested Data Using Sufficient Summary Statistics. Front. Hum. Neurosci. 12, 103 (2018).","journal-title":"Front. Hum. Neurosci."},{"key":"681_CR88","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/s40266-017-0455-9","volume":"34","author":"LM Swart","year":"2017","unstructured":"Swart, L. M., van der Zanden, V., Spies, P. E., de Rooij, S. E. & van Munster, B. C. The Comparative Risk of Delirium with Different Opioids: A Systematic Review. Drugs Aging 34, 437\u2013443 (2017).","journal-title":"Drugs Aging"},{"key":"681_CR89","doi-asserted-by":"publisher","first-page":"287","DOI":"10.2147\/JPR.S380616","volume":"ume 16","author":"R Sica","year":"2023","unstructured":"Sica, R. et al. The Relationship of Postoperative Pain and Opioid Consumption to Postoperative Delirium After Spine Surgery. J. Pain. Res. ume 16, 287\u2013294 (2023).","journal-title":"J. Pain. Res."},{"key":"681_CR90","first-page":"226","volume":"68","author":"P Ingelmo","year":"2002","unstructured":"Ingelmo, P., Barone, M. & Fumagalli, R. Importance of monitoring in high risk surgical patients. Minerva Anestesiologica 68, 226\u2013230 (2002).","journal-title":"Minerva Anestesiologica"},{"key":"681_CR91","unstructured":"Liu, L., Liu, X., Gao, J., Chen, W. & Han, J. Understanding the Difficulty of Training Transformers. arXiv, http:\/\/arxiv.org\/abs\/2004.08249 (2023)."},{"key":"681_CR92","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-023-02287-0","volume":"23","author":"A Ageno","year":"2023","unstructured":"Ageno, A., Catal\u00e0, N. & Pons, M. Acquisition of temporal patterns from electronic health records: an application to multimorbid patients. BMC Med. Inform. Decis. Mak. 23, 189 (2023).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"681_CR93","doi-asserted-by":"crossref","unstructured":"Duell, J., Fan, X., Fu, H. & Seisenberger, M. Batch Integrated Gradients: Explanations for Temporal Electronic Health Records. In Artificial Intelligence in Medicine, (eds Juarez, J. M., Marcos, M., Stiglic, G. & Tucker, A.) 13897, 120\u2013124 (Springer Nature Switzerland, Cham, 2023).","DOI":"10.1007\/978-3-031-34344-5_15"},{"key":"681_CR94","unstructured":"Kashefi, R., Barekatain, L., Sabokrou, M. & Aghaeipoor, F. Explainability of Vision Transformers: A Comprehensive Review and New Perspectives. arXiv, http:\/\/arxiv.org\/abs\/2311.06786 (2023)."},{"key":"681_CR95","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.neuroimage.2013.10.067","volume":"87","author":"S Haufe","year":"2014","unstructured":"Haufe, S. et al. On the interpretation of weight vectors of linear models in multivariate neuroimaging. NeuroImage 87, 96\u2013110 (2014).","journal-title":"NeuroImage"},{"key":"681_CR96","unstructured":"Wilming, R., Budding, C., M\u00fcller, K.-R. & Haufe, S. Scrutinizing XAI using linear ground-truth data with suppressor variables. arXiv, https:\/\/arxiv.org\/abs\/2111.07473 (2021)."},{"key":"681_CR97","unstructured":"Youssef, A. et al. External validation of AI models in health should be replaced with recurring local validation. Nat. Med. https:\/\/www.nature.com\/articles\/s41591-023-02540-z (2023)."},{"key":"681_CR98","doi-asserted-by":"publisher","first-page":"1730","DOI":"10.1093\/jamia\/ocad120","volume":"30","author":"AE Lewis","year":"2023","unstructured":"Lewis, A. E. et al. Electronic health record data quality assessment and tools: a systematic review. J. Am. Med. Inform. Assoc. 30, 1730\u20131740 (2023).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"681_CR99","doi-asserted-by":"publisher","first-page":"e0237639","DOI":"10.1371\/journal.pone.0237639","volume":"15","author":"SJ Cherak","year":"2020","unstructured":"Cherak, S. J. et al. Development and validation of delirium prediction model for critically ill adults parameterized to icu admission acuity. PLoS One 15, e0237639 (2020).","journal-title":"PLoS One"},{"key":"681_CR100","unstructured":"Association, A. P. Diagnostic and statistical manual of mental disorders: DSM-5, 5th ed. (American Psychiatric Association, 2013)."},{"key":"681_CR101","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1038\/s42256-020-0197-y","volume":"2","author":"M Prosperi","year":"2020","unstructured":"Prosperi, M. et al. Causal inference and counterfactual prediction in machine learning for actionable healthcare. Nat. Mach. Intell. 2, 369\u2013375 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"681_CR102","unstructured":"Wilming, R., Kieslich, L., Clark, B. & Haufe, S. Theoretical behavior of xai methods in the presence of suppressor variables. In International Conference on Machine Learning, 37091\u201337107 (PMLR, 2023)."},{"key":"681_CR103","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-92475-7","volume":"11","author":"G Lichtner","year":"2021","unstructured":"Lichtner, G. et al. Predicting lethal courses in critically ill COVID-19 patients using a machine learning model trained on patients with non-COVID-19 viral pneumonia. Sci. Rep. 11, 13205 (2021).","journal-title":"Sci. Rep."},{"key":"681_CR104","unstructured":"Wu, H. et al. Timesnet: Temporal 2d-variation modeling for general time series analysis. Proceedings in ICLR 2023. https:\/\/openreview.net\/forum?id=ju_Uqw384Oq (2022)."},{"key":"681_CR105","unstructured":"Grigsby, J., Wang, Z. & Qi, Y. Long-Range Transformers for Dynamic Spatiotemporal Forecasting. arXiv, https:\/\/arxiv.org\/abs\/2109.12218 (2021)."},{"key":"681_CR106","unstructured":"Zeng, A., Chen, M., Zhang, L. & Xu, Q. Are Transformers Effective for Time Series Forecasting? arXiv, http:\/\/arxiv.org\/abs\/2205.13504 (2022)."},{"key":"681_CR107","doi-asserted-by":"crossref","unstructured":"Gorbett, M., Shirazi, H. & Ray, I. Sparse Binary Transformers for Multivariate Time Series Modeling. arXiv, http:\/\/arxiv.org\/abs\/2308.04637 (2023).","DOI":"10.1145\/3580305.3599508"},{"key":"681_CR108","doi-asserted-by":"publisher","unstructured":"Giesa, N. Statistics TRAPOD, https:\/\/doi.org\/10.5061\/dryad.bvq83bkhv (2024).","DOI":"10.5061\/dryad.bvq83bkhv"}],"container-title":["Communications Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43856-024-00681-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43856-024-00681-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43856-024-00681-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T15:05:02Z","timestamp":1732719902000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43856-024-00681-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"references-count":108,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["681"],"URL":"https:\/\/doi.org\/10.1038\/s43856-024-00681-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4349783\/v1","asserted-by":"object"}]},"ISSN":["2730-664X"],"issn-type":[{"value":"2730-664X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"30 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare the following competing interests: S.B. is a salaried employee at Pfizer Pharma GmbH and a visiting researcher at IMI. The majority of this work occured while Sebastian was at IMI exclusively.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"251"}}