{"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/patient2vec-a-personalized-interpretable-deep","title":"Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record","arxiv_id":"1810.04793","date":"2018-10-10","proceeding":null,"authors":["Jinghe Zhang","Kamran Kowsari","James H. Harrison","Jennifer M. Lobo","Laura E. Barnes"],"abstract":"The wide implementation of electronic health record (EHR) systems facilitates\nthe collection of large-scale health data from real clinical settings. Despite\nthe significant increase in adoption of EHR systems, this data remains largely\nunexplored, but presents a rich data source for knowledge discovery from\npatient health histories in tasks such as understanding disease correlations\nand predicting health outcomes. However, the heterogeneity, sparsity, noise,\nand bias in this data present many complex challenges. This complexity makes it\ndifficult to translate potentially relevant information into machine learning\nalgorithms. In this paper, we propose a computational framework, Patient2Vec,\nto learn an interpretable deep representation of longitudinal EHR data which is\npersonalized for each patient. To evaluate this approach, we apply it to the\nprediction of future hospitalizations using real EHR data and compare its\npredictive performance with baseline methods. Patient2Vec produces a vector\nspace with meaningful structure and it achieves an AUC around 0.799\noutperforming baseline methods. In the end, the learned feature importance can\nbe visualized and interpreted at both the individual and population levels to\nbring clinical insights.","url_abs":"http://arxiv.org/abs/1810.04793v3","url_pdf":"http://arxiv.org/pdf/1810.04793v3.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":"patient2vec-a-personalized-interpretable-deep","repo_url":"https://github.com/BarnesLab/Patient2Vec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"patient2vec-a-personalized-interpretable-deep","repo_url":"https://github.com/MindSpore-scientific/code-1/tree/main/Patient2Vec-A-Personalized-Interpretable","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"patient2vec-a-personalized-interpretable-deep","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/4/Patient2Vec-A-Personalized-Interpretable","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"patient2vec-a-personalized-interpretable-deep","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/7/Patient2Vec-A-Personalized-Interpretable","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"feature-importance","task_name":"Feature Importance"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}