{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T23:23:00Z","timestamp":1772580180218,"version":"3.50.1"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T00:00:00Z","timestamp":1765324800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Japan reports the highest global mortality rate from drowning among older adults, predominantly owing to bathtub-related incidents. Despite sustained public health interventions, this mortality has increased over several decades. Timely warnings advising older adults to avoid unsupervised bathing during high-risk conditions may mitigate this issue; however, no nationwide forecasting model currently exists.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We integrated death certificate records from 1995\u20132020 (99,930 bathtub-drowning deaths) with meteorological, temporal, and demographic data across all 47 prefectures (446,359 prefecture-days). Daily mortality counts were modeled using a distributed-lag non-linear model (DLNM), extreme gradient boosting (XGBoost), and long short-term memory network (LSTM). Data were partitioned chronologically into training (1995\u20132015), validation (2016\u20132018), and test (2019\u20132020) sets. Predictive accuracy was evaluated using root mean square error (RMSE) and mean absolute error (MAE), whereas feature importance was quantified via Shapley additive explanations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>During the test period, DLNM, XGBoost, and LSTM exhibited comparable predictive performance (RMSE = 0.577, 0.574, 0.575; MAE = 0.345, 0.333, 0.347, respectively). The most important features across all models were daily mean temperature, prefectural population, and binary prefecture indicators. Restricting DLNM meteorological inputs to routinely forecasted variables\u2014daily maximum and minimum temperatures\u2014did not reduce predictive accuracy [RMSE = 0.577 (95% confidence interval, 0.566\u20130.590); MAE = 0.344 (95% confidence interval, 0.340\u20130.349)].<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The DLNM-based framework provides a practical means of forecasting the daily bathtub-drowning deaths. Integration into routine meteorological broadcasts and mobile platforms may facilitate timely warnings, prompting older adults to avoid unsupervised bathing on high-risk days, thereby reducing Japan's ongoing preventable bath-related mortality.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2025.1715622","type":"journal-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T06:39:31Z","timestamp":1765348771000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Forecasting daily bathtub-drowning mortality in Japan: a comparative analysis of statistical, machine learning, and deep learning approaches"],"prefix":"10.3389","volume":"13","author":[{"given":"Yoshiaki","family":"Tai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenji","family":"Obayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Yamagami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keigo","family":"Saeki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e43","DOI":"10.1136\/injuryprev-2013-041110","article-title":"Unintentional drowning mortality, by age and body of water: an analysis of 60 countries","volume":"21","author":"Lin","year":"2015","journal-title":"Inj Prev."},{"key":"B2","unstructured":"Population Census: e-Stat, Portal Site of Official Statistics of Japan.\n          \n          2023"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1144","DOI":"10.1253\/circj.CJ-16-1066","article-title":"Sudden death phenomenon while bathing in Japan\u2014mortality data","volume":"81","author":"Suzuki","year":"2017","journal-title":"Circ J."},{"key":"B4","doi-asserted-by":"publisher","first-page":"S2352","DOI":"10.1016\/j.sleh.2025.07.008","article-title":"Association between before-bedtime hot-tub bathing and sleep quality in real-life settings among community-dwelling older adults","volume":"12","author":"Tai","year":"2025","journal-title":"Sleep Health"},{"key":"B5","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.smrv.2019.04.008","article-title":"Before-bedtime passive body heating by warm shower or bath to improve sleep: a systematic review and meta-analysis","volume":"46","author":"Haghayegh","year":"2019","journal-title":"Sleep Med Rev."},{"key":"B6","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.jagp.2021.07.004","article-title":"Commentary on: \u201cAssociation between passive body heating by hot water bathing before bedtime and depressive symptoms among community-dwelling older adults\u201d","volume":"30","author":"Mischoulon","year":"2022","journal-title":"Am J Geriatr Psychiatry."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1714","DOI":"10.1080\/07420528.2019.1675685","article-title":"Association between timing of hot water bathing before bedtime and night-\/sleep-time blood pressure and dipping in the elderly: a longitudinal analysis for repeated measurements in home settings","volume":"36","author":"Tai","year":"2019","journal-title":"Chronobiol Int."},{"key":"B8","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1136\/heartjnl-2019-315752","article-title":"Habitual tub bathing and risks of incident coronary heart disease and stroke","volume":"106","author":"Ukai","year":"2020","journal-title":"Heart."},{"key":"B9","unstructured":"2015"},{"key":"B10","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1265\/ehpm.23-00320","article-title":"Blood pressure, pulse rate, and skin temperature during hot-water bathing in real-world settings among community-dwelling older adults: the HEIJO-KYO Study","volume":"29","author":"Tai","year":"2024","journal-title":"Environ Health Prev Med."},{"key":"B11","doi-asserted-by":"publisher","first-page":"482","DOI":"10.2188\/jea.JE20250032","article-title":"Drowning and submersion deaths in bathtubs and associated factors: a descriptive and ecological study in Japan, 1995\u20132020","volume":"35","author":"Tai","year":"2025","journal-title":"J Epidemiol"},{"key":"B12","unstructured":"Bathing Risk Advisory"},{"key":"B13","doi-asserted-by":"publisher","first-page":"2277","DOI":"10.1038\/s41598-023-29400-7","article-title":"Development of prevention strategies against bath-related deaths based on epidemiological surveys of inquest records in Kagoshima Prefecture","volume":"13","author":"Katsuyama","year":"2023","journal-title":"Sci Rep."},{"key":"B14","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1265\/ehpm.25-00116","article-title":"Association between outdoor temperature and bath-related drowning deaths in Japan (1995-2020): modifying factors and the role of prefectural characteristics","volume":"30","author":"Tai","year":"2025","journal-title":"Environ Health Prev Med."},{"key":"B15","unstructured":"Past Weather Data Download (ObsDL portal)"},{"key":"B16","unstructured":"National holidays (Cabinet Office site)\n          \n          \n            \n              Cabinet\n              Office (Japan)"},{"key":"B17","unstructured":"Vital statistics in 2020\n          \n          \n          \n          2020"},{"key":"B18","volume-title":"mgcv: Mixed GAM Computation Vehicle with Automatic Smoothness Estimation","author":"Wood","year":"2021"},{"key":"B19","doi-asserted-by":"publisher","first-page":"2224","DOI":"10.1002\/sim.3940","article-title":"Distributed lag non-linear models","volume":"29","author":"Gasparrini","year":"2010","journal-title":"Stat Med."},{"key":"B20","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: a scalable tree boosting system","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chen","year":"2016"},{"key":"B21","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn."},{"key":"B22","first-page":"265","article-title":"TensorFlow: a system for large-scale machine learning","volume-title":"Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16).","author":"Abadi","year":"2016"},{"key":"B23","doi-asserted-by":"crossref","first-page":"2623","DOI":"10.1145\/3292500.3330701","article-title":"Optuna: a next-generation hyperparameter optimization framework","volume-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","author":"Akiba","year":"2019"},{"key":"B24","unstructured":"Average values of forecast accuracy and their characteristics"},{"key":"B25","doi-asserted-by":"publisher","first-page":"378","DOI":"10.32614\/RJ-2017-066","article-title":"glmmTMB balances speed and flexibility among packages for zero-inflated generalized linear mixed modeling","volume":"9","author":"Brooks","year":"2017","journal-title":"R J."},{"key":"B26","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.legalmed.2018.09.021","article-title":"Association between sudden unexpected deaths in bathtubs and ambient temperature among elderly Japanese adults: a time-series regression study","volume":"36","author":"Kanawaku","year":"2019","journal-title":"Leg Med."},{"key":"B27","doi-asserted-by":"publisher","first-page":"3173","DOI":"10.2169\/internalmedicine.9156-17","article-title":"Relationship between bath-related deaths and low air temperature","volume":"56","author":"Suzuki","year":"2017","journal-title":"Intern Med."},{"key":"B28","unstructured":"Heat-Shock Forecast (tenki.jp)"},{"key":"B29","unstructured":"What is the heat-shock forecast?"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1111\/ina.12708","article-title":"Disparities of indoor temperature in winter: a cross-sectional analysis of the nationwide smart wellness housing survey in Japan","volume":"30","author":"Umishio","year":"2020","journal-title":"Indoor Air."},{"key":"B31","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann Stat."},{"key":"B32","first-page":"177","article-title":"Large-scale machine learning with stochastic gradient descent","author":"Bottou","year":"2010"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1715622\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T06:39:33Z","timestamp":1765348773000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1715622\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,10]]},"references-count":32,"alternative-id":["10.3389\/fpubh.2025.1715622"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2025.1715622","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,10]]},"article-number":"1715622"}}