{"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/riddle-race-and-ethnicity-imputation-from","title":"RIDDLE: Race and ethnicity Imputation from Disease history with Deep LEarning","arxiv_id":"1707.01623","date":"2017-07-06","proceeding":null,"authors":["Ji-Sung Kim","Xin Gao","Andrey Rzhetsky"],"abstract":"Anonymized electronic medical records are an increasingly popular source of\nresearch data. However, these datasets often lack race and ethnicity\ninformation. This creates problems for researchers modeling human disease, as\nrace and ethnicity are powerful confounders for many health exposures and\ntreatment outcomes; race and ethnicity are closely linked to\npopulation-specific genetic variation. We showed that deep neural networks\ngenerate more accurate estimates for missing racial and ethnic information than\ncompeting methods (e.g., logistic regression, random forest). RIDDLE yielded\nsignificantly better classification performance across all metrics that were\nconsidered: accuracy, cross-entropy loss (error), and area under the curve for\nreceiver operating characteristic plots (all $p < 10^{-6}$). We made specific\nefforts to interpret the trained neural network models to identify, quantify,\nand visualize medical features which are predictive of race and ethnicity. We\nused these characterizations of informative features to perform a systematic\ncomparison of differential disease patterns by race and ethnicity. The fact\nthat clinical histories are informative for imputing race and ethnicity could\nreflect (1) a skewed distribution of blue- and white-collar professions across\nracial and ethnic groups, (2) uneven accessibility and subjective importance of\nprophylactic health, (3) possible variation in lifestyle, such as dietary\nhabits, and (4) differences in background genetic variation which predispose to\ndiseases.","url_abs":"http://arxiv.org/abs/1707.01623v2","url_pdf":"http://arxiv.org/pdf/1707.01623v2.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":"riddle-race-and-ethnicity-imputation-from","repo_url":"https://github.com/jisungk/riddle","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"imputation","task_name":"Imputation"}],"methods":[],"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}