{"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/deeptag-inferring-all-cause-diagnoses-from","title":"DeepTag: inferring all-cause diagnoses from clinical notes in under-resourced medical domain","arxiv_id":"1806.10722","date":"2018-06-28","proceeding":null,"authors":["Allen Nie","Ashley Zehnder","Rodney L. Page","Arturo L. Pineda","Manuel A. Rivas","Carlos D. Bustamante","James Zou"],"abstract":"Large scale veterinary clinical records can become a powerful resource for\npatient care and research. However, clinicians lack the time and resource to\nannotate patient records with standard medical diagnostic codes and most\nveterinary visits are captured in free text notes. The lack of standard coding\nmakes it challenging to use the clinical data to improve patient care. It is\nalso a major impediment to cross-species translational research, which relies\non the ability to accurately identify patient cohorts with specific diagnostic\ncriteria in humans and animals. In order to reduce the coding burden for\nveterinary clinical practice and aid translational research, we have developed\na deep learning algorithm, DeepTag, which automatically infers diagnostic codes\nfrom veterinary free text notes. DeepTag is trained on a newly curated dataset\nof 112,558 veterinary notes manually annotated by experts. DeepTag extends\nmulti-task LSTM with an improved hierarchical objective that captures the\nsemantic structures between diseases. To foster human-machine collaboration,\nDeepTag also learns to abstain in examples when it is uncertain and defers them\nto human experts, resulting in improved performance. DeepTag accurately infers\ndisease codes from free text even in challenging cross-hospital settings where\nthe text comes from different clinical settings than the ones used for\ntraining. It enables automated disease annotation across a broad range of\nclinical diagnoses with minimal pre-processing. The technical framework in this\nwork can be applied in other medical domains that currently lack medical coding\nresources.","url_abs":"http://arxiv.org/abs/1806.10722v2","url_pdf":"http://arxiv.org/pdf/1806.10722v2.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":"deeptag-inferring-all-cause-diagnoses-from","repo_url":"https://github.com/windweller/DeepTag","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"diagnostic","task_name":"Diagnostic"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}