{"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/shortfuse-biomedical-time-series","title":"ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information","arxiv_id":"1705.04790","date":"2017-05-13","proceeding":null,"authors":["Madalina Fiterau","Suvrat Bhooshan","Jason Fries","Charles Bournhonesque","Jennifer Hicks","Eni Halilaj","Christopher Ré","Scott Delp"],"abstract":"In healthcare applications, temporal variables that encode movement, health\nstatus and longitudinal patient evolution are often accompanied by rich\nstructured information such as demographics, diagnostics and medical exam data.\nHowever, current methods do not jointly optimize over structured covariates and\ntime series in the feature extraction process. We present ShortFuse, a method\nthat boosts the accuracy of deep learning models for time series by explicitly\nmodeling temporal interactions and dependencies with structured covariates.\nShortFuse introduces hybrid convolutional and LSTM cells that incorporate the\ncovariates via weights that are shared across the temporal domain. ShortFuse\noutperforms competing models by 3% on two biomedical applications, forecasting\nosteoarthritis-related cartilage degeneration and predicting surgical outcomes\nfor cerebral palsy patients, matching or exceeding the accuracy of models that\nuse features engineered by domain experts.","url_abs":"http://arxiv.org/abs/1705.04790v2","url_pdf":"http://arxiv.org/pdf/1705.04790v2.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":"shortfuse-biomedical-time-series","repo_url":"https://github.com/Jungguchoi/Hybrid_CNN_with_1DCAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"shortfuse-biomedical-time-series","repo_url":"https://github.com/MindSpore-scientific/code-8/tree/main/ShortFuse-Biomedical-Time-Series","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"shortfuse-biomedical-time-series","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/4/ShortFuse-Biomedical-Time-Series","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"shortfuse-biomedical-time-series","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/7/ShortFuse-Biomedical-Time-Series","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"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":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}