{"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/learning-to-detect-sepsis-with-a-multitask","title":"Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier","arxiv_id":"1706.04152","date":"2017-06-13","proceeding":"ICML 2017 8","authors":["Joseph Futoma","Sanjay Hariharan","Katherine Heller"],"abstract":"We present a scalable end-to-end classifier that uses streaming physiological\nand medication data to accurately predict the onset of sepsis, a\nlife-threatening complication from infections that has high mortality and\nmorbidity. Our proposed framework models the multivariate trajectories of\ncontinuous-valued physiological time series using multitask Gaussian processes,\nseamlessly accounting for the high uncertainty, frequent missingness, and\nirregular sampling rates typically associated with real clinical data. The\nGaussian process is directly connected to a black-box classifier that predicts\nwhether a patient will become septic, chosen in our case to be a recurrent\nneural network to account for the extreme variability in the length of patient\nencounters. We show how to scale the computations associated with the Gaussian\nprocess in a manner so that the entire system can be discriminatively trained\nend-to-end using backpropagation. In a large cohort of heterogeneous inpatient\nencounters at our university health system we find that it outperforms several\nbaselines at predicting sepsis, and yields 19.4% and 55.5% improved areas under\nthe Receiver Operating Characteristic and Precision Recall curves as compared\nto the NEWS score currently used by our hospital.","url_abs":"http://arxiv.org/abs/1706.04152v1","url_pdf":"http://arxiv.org/pdf/1706.04152v1.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":"learning-to-detect-sepsis-with-a-multitask","repo_url":"https://github.com/BorgwardtLab/mgp-tcn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-detect-sepsis-with-a-multitask","repo_url":"https://github.com/choltz95/MTGP-NN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"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":"https://app.syntology.ai/?focus=1706.04152","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}