{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/modeling-irregularly-sampled-clinical-time","title":"Modeling Irregularly Sampled Clinical Time Series","arxiv_id":"1812.00531","date":"2018-12-03","proceeding":null,"authors":["Satya Narayan Shukla","Benjamin M. Marlin"],"abstract":"While the volume of electronic health records (EHR) data continues to grow,\nit remains rare for hospital systems to capture dense physiological data\nstreams, even in the data-rich intensive care unit setting. Instead, typical\nEHR records consist of sparse and irregularly observed multivariate time\nseries, which are well understood to present particularly challenging problems\nfor machine learning methods. In this paper, we present a new deep learning\narchitecture for addressing this problem based on the use of a semi-parametric\ninterpolation network followed by the application of a prediction network. The\ninterpolation network allows for information to be shared across multiple\ndimensions during the interpolation stage, while any standard deep learning\nmodel can be used for the prediction network. We investigate the performance of\nthis architecture on the problems of mortality and length of stay prediction.","url_abs":"http://arxiv.org/abs/1812.00531v1","url_pdf":"http://arxiv.org/pdf/1812.00531v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"modeling-irregularly-sampled-clinical-time","repo_url":"https://github.com/mlds-lab/interp-net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"length-of-stay-prediction","task_name":"Length-of-Stay prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}