{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:56:28Z","timestamp":1782316588346,"version":"3.54.5"},"reference-count":52,"publisher":"American Geophysical Union (AGU)","issue":"6","license":[{"start":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:00:00Z","timestamp":1781222400000},"content-version":"vor","delay-in-days":11,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["NSTC CHRF Program 2025"],"award-info":[{"award-number":["NSTC CHRF Program 2025"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["114\u20102221\u2010E\u2010003\u2010008"],"award-info":[{"award-number":["114\u20102221\u2010E\u2010003\u2010008"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["agupubs.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["GeoHealth"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Short\u2010term variability in weather and air quality is known to influence cardiovascular emergencies, yet its day\u2010to\u2010day predictive value at the population level remains insufficiently understood. Using 23\u00a0years of nationwide data from Taiwan (2000\u20132022), we evaluated how weather and air quality conditions shape daily cardiovascular disease (CVD) emergency visits across geographic regions. We first applied unsupervised learning methods, including UMAP and K\u2010means clustering, to 184 environmental features to identify data\u2010driven environmental regimes and examine the distribution of high\u2010risk CVD days. We then trained eight supervised learning models to predict daily CVD emergency visits and used SHAP values to interpret key predictors. Unsupervised analyses revealed consistent seasonal and pollution\u2010related patterns. High\u2010risk days tended to cluster during cool conditions accompanied by elevated air pollution, with temperatures higher than in winter but substantially greater pollution levels. This pattern was particularly evident in northern Taiwan and among populations aged 65\u00a0years and older. Air\u2010pollution variables produced more clearly defined high\u2010risk clusters than meteorological variables alone, indicating a stronger pollution\u2010related contribution to acute CVD risk. In the supervised framework, tree\u2010based ensemble models (Random Forest, LightGBM, XGBoost) achieved the best performance, with\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    values up to 0.67 and mean absolute percentage errors of 7%\u20138%. Predictability was highest for elderly populations and northern Taiwan. SHAP analyses identified NO\n                    <jats:sub>x<\/jats:sub>\n                    \u2010related metrics as dominant predictors of CVD emergency visits. These results demonstrate that high\u2010resolution environmental data, combined with machine\u2010learning methods, can effectively predict CVD emergencies, delineate high\u2010risk environmental regimes, and support region\u2010specific early\u2010warning systems centered on air\u2010pollution monitoring, particularly NO\n                    <jats:sub>x<\/jats:sub>\n                    .\n                  <\/jats:p>","DOI":"10.1029\/2025gh001769","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T07:35:26Z","timestamp":1781249726000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting Daily Cardiovascular Emergencies Using Weather and Air Quality Data: A 23\u2010Year Machine\u2010Learning Analysis in Taiwan"],"prefix":"10.1029","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1329-3298","authenticated-orcid":false,"given":"Hsiang\u2010Han","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science and Information Engineering National Taiwan Normal University  Taipei Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4685-2223","authenticated-orcid":false,"given":"Pei\u2010Shan","family":"Tsai","sequence":"additional","affiliation":[{"name":"Department of Earth Sciences National Taiwan Normal University  Taipei Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu\u2010Chia","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering National Taiwan Normal University  Taipei Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng\u2010Yu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering National Taiwan Normal University  Taipei Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu\u2010Kai","family":"Lin","sequence":"additional","affiliation":[{"name":"The Department of Health and Welfare University of Taipei  Taipei Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2171-4075","authenticated-orcid":false,"given":"Wan\u2010Ru","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Earth Sciences National Taiwan Normal University  Taipei Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kate","family":"Huihsuan Chen","sequence":"additional","affiliation":[{"name":"Department of Earth Sciences National Taiwan Normal University  Taipei Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"13","published-online":{"date-parts":[[2026,6,12]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41569\u2010020\u20100371\u20102"},{"key":"e_1_2_9_3_1","volume-title":"Diagnosis and treatment in internal medicine","author":"Banerjee A.","year":"2018"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.envres.2022.112698"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.5334\/gh.1288"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.envres.2004.07.005"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","unstructured":"chenh2lab. (2026).chenh2lab\/TaiwanCVDPrediction: Journal_publication[Software].Zenodo.https:\/\/doi.org\/10.5281\/zenodo.19420106","DOI":"10.5281\/zenodo.19420106"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrcardio.2015.152"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm12062206"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1177\/2047487319878371"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1111\/joim.13467"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture15070766"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.lanwpc.2024.101138"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1970.10488634"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.atmosres.2018.08.004"},{"key":"e_1_2_9_19_1","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume":"30","author":"Ke G.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.envres.2008.10.002"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.5194\/acp\u201021\u201016893\u20102021"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12967\u2010025\u201006397\u20103"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.4209\/aaqr.220187"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2020.138012"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.5334\/gh.849"},{"key":"e_1_2_9_26_1","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg S. M.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep38328"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0166846"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.03426"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1136\/heartjnl\u20102015\u2010308769"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0063347"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.3574"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehw294"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10653\u2010021\u201001149\u2010w"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1515\/reveh.2008.23.3.167"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1101\/2023.03.03.23286765"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.118.037454"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcdd6020019"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2020.139512"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpcardiol.2023.102120"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrcardio.2017.76"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12933\u2010018\u20100703\u20102"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517\u20106161.1996.tb02080.x"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2010.01.044"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.3390\/atmos15121547"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ypmed.2020.105986"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0020166"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.74333"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010021\u201087051\u2010y"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2024.1321129"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2022.802167"},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12940\u2010025\u201001175\u20106"}],"container-title":["GeoHealth"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/pdf\/10.1029\/2025GH001769","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/full-xml\/10.1029\/2025GH001769","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/pdf\/10.1029\/2025GH001769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:33:31Z","timestamp":1782315211000},"score":1,"resource":{"primary":{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/10.1029\/2025GH001769"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":52,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1029\/2025GH001769"],"URL":"https:\/\/doi.org\/10.1029\/2025gh001769","archive":["Portico"],"relation":{"has-preprint":[{"id-type":"doi","id":"10.22541\/essoar.176538442.23019295\/v1","asserted-by":"object"}]},"ISSN":["2471-1403","2471-1403"],"issn-type":[{"value":"2471-1403","type":"print"},{"value":"2471-1403","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"2025-12-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2025GH001769"}}