{"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/a-knowledge-distillation-ensemble-framework","title":"A Knowledge Distillation Ensemble Framework for Predicting Short and Long-term Hospitalisation Outcomes from Electronic Health Records Data","arxiv_id":"2011.09361","date":"2020-11-18","proceeding":null,"authors":["Zina M Ibrahim","Daniel Bean","Thomas Searle","Honghan Wu","Anthony Shek","Zeljko Kraljevic","James Galloway","Sam Norton","James T Teo","Richard JB Dobson"],"abstract":"The ability to perform accurate prognosis of patients is crucial for proactive clinical decision making, informed resource management and personalised care. Existing outcome prediction models suffer from a low recall of infrequent positive outcomes. We present a highly-scalable and robust machine learning framework to automatically predict adversity represented by mortality and ICU admission from time-series vital signs and laboratory results obtained within the first 24 hours of hospital admission. The stacked platform comprises two components: a) an unsupervised LSTM Autoencoder that learns an optimal representation of the time-series, using it to differentiate the less frequent patterns which conclude with an adverse event from the majority patterns that do not, and b) a gradient boosting model, which relies on the constructed representation to refine prediction, incorporating static features of demographics, admission details and clinical summaries. The model is used to assess a patient's risk of adversity over time and provides visual justifications of its prediction based on the patient's static features and dynamic signals. Results of three case studies for predicting mortality and ICU admission show that the model outperforms all existing outcome prediction models, achieving PR-AUC of 0.891 (95$%$ CI: 0.878 - 0.969) in predicting mortality in ICU and general ward settings and 0.908 (95$%$ CI: 0.870-0.935) in predicting ICU admission.","url_abs":"https://arxiv.org/abs/2011.09361v2","url_pdf":"https://arxiv.org/pdf/2011.09361v2.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":"a-knowledge-distillation-ensemble-framework","repo_url":"https://github.com/zibrahim/KD-OP","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"icu-admission","task_name":"ICU Admission"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"management","task_name":"Management"},{"task_slug":"outlier-detection","task_name":"Outlier Detection"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"prognosis","task_name":"Prognosis"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"outlier-ensembles","task_name":"outlier ensembles"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}