{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T04:30:04Z","timestamp":1794025804594,"version":"4.8.0"},"reference-count":49,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To simultaneously estimate how the risk of incident dementia nonlinearly varies with the administration period and cumulative dose of benzodiazepines, the duration of disorders with an indication for benzodiazepines, and other potential confounders, with the goal of settling the controversy over the role of benzodiazepines in the development of dementia.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The classical hazard model was extended using the techniques of multiple-kernel learning. Regularised maximum-likelihood estimation, including determination of hyperparameter values with 10-fold cross-validation, bootstrap goodness-of-fit test, and bootstrap estimation of confidence intervals, was applied to cohorts retrospectively extracted from electronic medical records of our university hospitals between 1 November 2004 and 31 July 2020. The analysis was mainly focused on 8160 patients aged 40 or older with new onset of insomnia, affective disorders, or anxiety disorders, who were followed up for [Formula: see text] years.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Besides previously reported risk associations, we detected significant nonlinear risk variations over 2\u20134 years attributable to the duration of insomnia and anxiety disorders, and to the administration period of short-acting benzodiazepines. After nonlinear adjustment for potential confounders, we observed no significant risk associations with long-term use of benzodiazepines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The pattern of the detected nonlinear risk variations suggested reverse causation and confounding. Their putative bias effects over 2\u20134 years suggested similar biases in previously reported results. These results, together with the lack of significant risk associations with long-term use of benzodiazepines, suggested the need to reconsider previous results and methods for future analysis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076231178577","type":"journal-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T03:30:00Z","timestamp":1686195000000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":6,"title":["Benzodiazepine-related dementia risks and protopathic biases revealed by multiple-kernel learning with electronic medical records"],"prefix":"10.1177","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8565-3486","authenticated-orcid":false,"given":"Takashi","family":"Hayakawa","sequence":"first","affiliation":[{"name":"Division of Pharmacology, Department of Biomedical Sciences, Nihon University School of Medicine, Tokyo, Japan"},{"name":"Division of Genomic Epidemiology and Clinical Trials, Clinical Trials Research Center, Nihon University School of Medicine, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takuya","family":"Nagashima","sequence":"additional","affiliation":[{"name":"Division of Pharmacology, Department of Biomedical Sciences, Nihon University School of Medicine, Tokyo, Japan"},{"name":"Division of Genomic Epidemiology and Clinical Trials, Clinical Trials Research Center, Nihon University School of Medicine, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hayato","family":"Akimoto","sequence":"additional","affiliation":[{"name":"Division of Pharmacology, Department of Biomedical Sciences, Nihon University School of Medicine, Tokyo, Japan"},{"name":"Division of Genomic Epidemiology and Clinical Trials, Clinical Trials Research Center, Nihon University School of Medicine, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kimino","family":"Minagawa","sequence":"additional","affiliation":[{"name":"Division of Genomic Epidemiology and Clinical Trials, Clinical Trials Research Center, Nihon University School of Medicine, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasuo","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Division of Genomic Epidemiology and Clinical Trials, Clinical Trials Research Center, Nihon University School of Medicine, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satoshi","family":"Asai","sequence":"additional","affiliation":[{"name":"Division of Pharmacology, Department of Biomedical Sciences, Nihon University School of Medicine, Tokyo, Japan"},{"name":"Division of Genomic Epidemiology and Clinical Trials, Clinical Trials Research Center, Nihon University School of Medicine, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2023,6,8]]},"reference":[{"key":"bibr1-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1016\/S0895-4356(01)00453-X"},{"key":"bibr2-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1093\/ageing\/afn277"},{"key":"bibr3-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1097\/JGP.0b013e3181a65210"},{"key":"bibr4-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1097\/JGP.0b013e3181e049ca"},{"key":"bibr5-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1136\/jech-2011-200314"},{"key":"bibr6-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0049113"},{"key":"bibr7-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.e6231"},{"key":"bibr8-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.g5205"},{"key":"bibr9-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-015-0319-3"},{"key":"bibr10-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2015.10.006"},{"key":"bibr11-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.i90"},{"key":"bibr12-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1007\/s40263-016-0404-x"},{"key":"bibr13-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1177\/1060028019882037"},{"key":"bibr14-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1176\/appi.ajp.2019.19030315"},{"key":"bibr15-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0127836"},{"key":"bibr16-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1159\/000454881"},{"key":"bibr17-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1002\/phar.2170"},{"key":"bibr18-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwz073"},{"key":"bibr19-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1002\/trc2.12041"},{"key":"bibr20-20552076231178577","first-page":"27","volume":"5","author":"Lanckriet GR","year":"2004","journal-title":"J Mach Learn Res"},{"key":"bibr21-20552076231178577","first-page":"1179","volume":"9","author":"Bach FR","year":"2008","journal-title":"J Mach Learn Res"},{"key":"bibr22-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1214\/09-AOS692"},{"key":"bibr23-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1214\/10-AOS825"},{"key":"bibr24-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1214\/13-AOS1095"},{"key":"bibr25-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1002\/uog.8813"},{"key":"bibr26-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2011.11.001"},{"key":"bibr27-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2016.03.008"},{"key":"bibr28-20552076231178577","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez-S\u00e1nchez J, Soguero-Ruiz C, de Miguel-Bohoyo P et al. Clinical risk groups analysis for chronic hypertensive patients in terms of icd9-cm diagnosis codes. In\n                      PhyCS\n                      . pp.13\u201322.","DOI":"10.5220\/0006218700130022"},{"key":"bibr29-20552076231178577","doi-asserted-by":"crossref","unstructured":"Chakraborty P, Farooq F. A robust framework for accelerated outcome-driven risk factor identification from ehr. In\n                      Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining\n                      . pp.1800\u20131808.","DOI":"10.1145\/3292500.3330718"},{"key":"bibr30-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-98144-z"},{"key":"bibr31-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1248\/bpb.b21-00407"},{"key":"bibr32-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.2573"},{"key":"bibr33-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9096-9"},{"key":"bibr34-20552076231178577","doi-asserted-by":"crossref","unstructured":"Bach FR, Lanckriet GR, Jordan MI. Multiple kernel learning, conic duality, and the smo algorithm. In\n                      Proceedings of the twenty-first international conference on machine learning\n                      . p. 6.","DOI":"10.1145\/1015330.1015424"},{"key":"bibr35-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X19873661"},{"key":"bibr36-20552076231178577","unstructured":"For Drug Statistics Methodology WCC. Anatomical therapeutic chemical classification system. www.whocc.no."},{"key":"bibr37-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1001\/archgenpsychiatry.2011.1481"},{"key":"bibr38-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.07.016"},{"key":"bibr39-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-publhealth-040119-094437"},{"key":"bibr40-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-14-137"},{"key":"bibr41-20552076231178577","unstructured":"Suzuki T. Pac-Bayesian bound for Gaussian process regression and multiple kernel additive model. In\n                      Conference on Learning Theory\n                      . JMLR Workshop and Conference Proceedings, pp.8\u20131."},{"key":"bibr42-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-019-1280-2"},{"key":"bibr43-20552076231178577","first-page":"S142","volume":"61","author":"Campbell N","year":"2013","journal-title":"J Am Geriatr Soc"},{"key":"bibr44-20552076231178577","unstructured":"World Health Organization.\n                      International Classification of Diseases 10th Revision\n                      . https:\/\/icd.who.int\/browse10\/2019\/en."},{"key":"bibr45-20552076231178577","unstructured":"Lu C, Goeman J, Putter H. Maximum likelihood estimation in the additive hazards model.\n                      arXiv preprint arXiv:200406156\n                      2020."},{"key":"bibr46-20552076231178577","volume-title":"Dynamic regression models for survival data","author":"Martinussen T","year":"2006"},{"key":"bibr47-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5252-9"},{"key":"bibr48-20552076231178577","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"bibr49-20552076231178577","first-page":"1","volume":"3","author":"Bach F","year":"2002","journal-title":"J Mach Learn Res"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076231178577","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076231178577","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076231178577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:53:22Z","timestamp":1777398802000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076231178577"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":49,"alternative-id":["10.1177\/20552076231178577"],"URL":"https:\/\/doi.org\/10.1177\/20552076231178577","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]},"article-number":"20552076231178577"}}