{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T01:33:07Z","timestamp":1716859987306},"reference-count":27,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Quant. Biol."],"published-print":{"date-parts":[[2022,6]]},"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Modern machine learning\u2010based models have not been harnessed to their total capacity for disease trend predictions prior to the COVID\u201019 pandemic. This work is the first use of the conditional RNN model in predicting disease trends that we know of during development that complemented classical epidemiological approaches.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We developed the long short\u2010term memory networks with quantile output (condLSTM\u2010Q) model for making quantile predictions on COVID\u201019 death tolls.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We verified that the condLSTM\u2010Q was accurately predicting fine\u2010scale, county\u2010level daily deaths with a two\u2010week window. The model\u2019s performance was robust and comparable to, if not slightly better than well\u2010known, publicly available models. This provides unique opportunities for investigating trends within the states and interactions between counties along state borders. In addition, by analyzing the importance of the categorical data, one could learn which features are risk factors that affect the death trend and provide handles for officials to ameliorate the risks.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The condLSTM\u2010Q model performed robustly, provided fine\u2010scale, county\u2010level predictions of daily deaths with a two\u2010week window. Given the scalability and generalizability of neural network models, this model could incorporate additional data sources with ease and could be further developed to generate other valuable predictions such as new cases or hospitalizations intuitively.<\/jats:p><\/jats:sec>","DOI":"10.15302\/j-qb-021-0276","type":"journal-article","created":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T08:38:12Z","timestamp":1657269492000},"page":"125-138","source":"Crossref","is-referenced-by-count":0,"title":["condLSTM\u2010Q: A novel deep learning model for predicting COVID\u201019\u00a0mortality in fine geographical scale"],"prefix":"10.1002","volume":"10","author":[{"given":"HyeongChan","family":"Jo","sequence":"first","affiliation":[{"name":"<!--1--> Division of Biology and Biological Engineering Caltech Pasadena CA 91125 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juhyun","family":"Kim","sequence":"additional","affiliation":[{"name":"<!--2--> The Division of Physics Mathematics and Astronomy Caltech Pasadena CA 91125 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tzu\u2010Chen","family":"Huang","sequence":"additional","affiliation":[{"name":"<!--3--> Walter Burke Institute for Theoretical Physics Caltech Pasadena CA 91125 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu\u2010Li","family":"Ni","sequence":"additional","affiliation":[{"name":"<!--1--> Division of Biology and Biological Engineering Caltech Pasadena CA 91125 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2022,6]]},"reference":[{"key":"e_1_2_7_2_2","doi-asserted-by":"crossref","unstructured":"IHME COVID\u201019 health service utilization forecasting team MurrayC. J.(2020)Forecasting COVID\u201019 impact on hospital bed\u2010days ICU\u2010days ventilator\u2010days and deaths by US state in the next 4 months. medRxiv doi:https:\/\/doi.org\/10.1101\/2020.03.27.20043752","DOI":"10.1101\/2020.03.27.20043752"},{"key":"e_1_2_7_3_2","unstructured":"Abu\u2010Mostafa Y.(2020)Caltech CS156 COVID\u201019 Model.https:\/\/cs156.caltech.edu\/. Accessed: Accessed: February 1 2021"},{"key":"e_1_2_7_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.atmosres.2019.01.024"},{"key":"e_1_2_7_5_2","doi-asserted-by":"publisher","DOI":"10.1111\/1365-2664.12514"},{"key":"e_1_2_7_6_2","unstructured":"IHME. (2020)Institute for health metrics and evaluation COVID\u201019 estimate.http:\/\/www.healthdata.org\/covid\/data\u2010downloads. Accessed: February 1 2021"},{"key":"e_1_2_7_7_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_7_8_2","doi-asserted-by":"publisher","DOI":"10.3390\/app10186448"},{"key":"e_1_2_7_9_2","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare8020181"},{"key":"e_1_2_7_10_2","unstructured":"R\u00e9my P.. (2020)Conditional RNNs made easy with Tensorflow and Keras.https:\/\/github.com\/philipperemy\/cond_rnn. Accessed: February 1 2021"},{"key":"e_1_2_7_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_2_7_12_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_7_13_2","first-page":"177","article-title":"All models are wrong, but many are useful: Learning a variable\u2019s importance by studying an entire class of prediction models simultaneously","volume":"20","author":"Fisher A.","year":"2019","journal-title":"J. Mach. Learn Res."},{"key":"e_1_2_7_14_2","unstructured":"Analytics COVID(2020)DELPHI Model.https:\/\/www.covidanalytics.io\/projections\/. Accessed: February 1 2021"},{"key":"e_1_2_7_15_2","unstructured":"Los Alamos National Laboratory. (2020)LANL Model.https:\/\/covid\u201019.bsvgateway.org\/. Accessed: February 1 2021"},{"key":"e_1_2_7_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcard.2020.03.063"},{"key":"e_1_2_7_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2020.04.010"},{"key":"e_1_2_7_18_2","doi-asserted-by":"crossref","unstructured":"Chen Y. Gong X. Wang L.(2020)Effects of hypertension diabetes and coronary heart disease on COVID\u201019 diseases severity: a systematic review and meta\u2010analysis. medRxiv doi:10.1101\/2020.03.25.20043133","DOI":"10.1101\/2020.03.25.20043133"},{"key":"e_1_2_7_19_2","first-page":"567","article-title":"Analysis of myocardial injury in patients with COVID\u201019 and association between concomitant cardiovascular diseases and severity of COVID\u201019","volume":"48","author":"Chen C.","year":"2020","journal-title":"Zhonghua Xin Xue Guan Bing Za Zhi (in Chinese)"},{"key":"e_1_2_7_20_2","unstructured":"Zhang Y. Tian H. Zhang Y.(2020)Is the epidemic spread related to GDP? Visualizing the distribution of COVID\u201019 in Chinese mainland. arXiv 2004.04387"},{"key":"e_1_2_7_21_2","unstructured":"U.S. Bureau of Economic Analysis (BEA). (2020)Local area gross domestic product 2018.https:\/\/www.bea.gov\/system\/files\/2019\u201012\/lagdp1219.pdf. Accessed: February 1 2021"},{"key":"e_1_2_7_22_2","unstructured":"National Institutes of Health. (2019)COVID\u201019 treatment guidelines panel.Coronavirus disease 2019 (COVID\u201019) treatment guidelines. National Institutes of Health.https:\/\/www.covid19treatmentguidelines.nih.gov\/. Accessed: February 1 2021"},{"key":"e_1_2_7_23_2","unstructured":"U.S. Food and Drug Administration Pfizer\u2010BioNTech COVID\u201019 Vaccine.https:\/\/www.fda.gov\/emergencypreparedness\u2010and\u2010response\/coronavirus\u2010disease\u20102019\u2010covid\u201019\/pfizer\u2010biontech\u2010covid\u201019\u2010vaccine. Accessed: February 1 2021"},{"key":"e_1_2_7_24_2","unstructured":"Centers for Disease Control.COVID\u201019 vaccinations in the United States.https:\/\/covid.cdc.gov\/covid\u2010data\u2010tracker\/vaccinations. Accessed: February 1 2021"},{"key":"e_1_2_7_25_2","unstructured":"The Covidvis team. (2020)Covidvis.https:\/\/covidvis.berkeley.edu\/. Accessed: February 1 2021"},{"key":"e_1_2_7_26_2","unstructured":"Centers for Disease Control. (2020)Pneumonia and influenza mortality surveillance from the national center for health statistics mortality surveillance system.https:\/\/gis.cdc.gov\/grasp\/fluview\/mortality.html. Accessed: February 1 2021"},{"key":"e_1_2_7_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_37"},{"key":"e_1_2_7_28_2","unstructured":"Kingma D. P.(2017)Adam: A Method for Stochastic Optimization. arXiv 1412.6980"}],"container-title":["Quantitative Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.15302\/J-QB-021-0276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T07:44:14Z","timestamp":1703144654000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.15302\/J-QB-021-0276"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":27,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["10.15302\/J-QB-021-0276"],"URL":"https:\/\/doi.org\/10.15302\/j-qb-021-0276","archive":["Portico"],"relation":{},"ISSN":["2095-4689","2095-4697"],"issn-type":[{"value":"2095-4689","type":"print"},{"value":"2095-4697","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}