{"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/temporal-convolutional-neural-networks-for","title":"Temporal Convolutional Neural Networks for Diagnosis from Lab Tests","arxiv_id":"1511.07938","date":"2015-11-25","proceeding":null,"authors":["Narges Razavian","David Sontag"],"abstract":"Early diagnosis of treatable diseases is essential for improving healthcare,\nand many diseases' onsets are predictable from annual lab tests and their\ntemporal trends. We introduce a multi-resolution convolutional neural network\nfor early detection of multiple diseases from irregularly measured sparse lab\nvalues. Our novel architecture takes as input both an imputed version of the\ndata and a binary observation matrix. For imputing the temporal sparse\nobservations, we develop a flexible, fast to train method for differentiable\nmultivariate kernel regression. Our experiments on data from 298K individuals\nover 8 years, 18 common lab measurements, and 171 diseases show that the\ntemporal signatures learned via convolution are significantly more predictive\nthan baselines commonly used for early disease diagnosis.","url_abs":"http://arxiv.org/abs/1511.07938v4","url_pdf":"http://arxiv.org/pdf/1511.07938v4.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":"temporal-convolutional-neural-networks-for","repo_url":"https://github.com/clinicalml/deepDiagnosis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":null}],"tasks":[{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}