{"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/early-hospital-mortality-prediction-using","title":"Early hospital mortality prediction using vital signals","arxiv_id":"1803.06589","date":"2018-03-18","proceeding":null,"authors":["Reza Sadeghi","Tanvi Banerjee","William Romine"],"abstract":"Early hospital mortality prediction is critical as intensivists strive to\nmake efficient medical decisions about the severely ill patients staying in\nintensive care units. As a result, various methods have been developed to\naddress this problem based on clinical records. However, some of the laboratory\ntest results are time-consuming and need to be processed. In this paper, we\npropose a novel method to predict mortality using features extracted from the\nheart signals of patients within the first hour of ICU admission. In order to\npredict the risk, quantitative features have been computed based on the heart\nrate signals of ICU patients. Each signal is described in terms of 12\nstatistical and signal-based features. The extracted features are fed into\neight classifiers: decision tree, linear discriminant, logistic regression,\nsupport vector machine (SVM), random forest, boosted trees, Gaussian SVM, and\nK-nearest neighborhood (K-NN). To derive insight into the performance of the\nproposed method, several experiments have been conducted using the well-known\nclinical dataset named Medical Information Mart for Intensive Care III\n(MIMIC-III). The experimental results demonstrate the capability of the\nproposed method in terms of precision, recall, F1-score, and area under the\nreceiver operating characteristic curve (AUC). The decision tree classifier\nsatisfies both accuracy and interpretability better than the other classifiers,\nproducing an F1-score and AUC equal to 0.91 and 0.93, respectively. It\nindicates that heart rate signals can be used for predicting mortality in\npatients in the ICU, achieving a comparable performance with existing\npredictions that rely on high dimensional features from clinical records which\nneed to be processed and may contain missing information.","url_abs":"http://arxiv.org/abs/1803.06589v2","url_pdf":"http://arxiv.org/pdf/1803.06589v2.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":"early-hospital-mortality-prediction-using","repo_url":"https://github.com/RezaSadeghiWSU/Early-Hospital-Mortality-Prediction-using-Vital-Signals","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"icu-admission","task_name":"ICU Admission"},{"task_slug":"mortality-prediction","task_name":"Mortality Prediction"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"},{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"Random Forest","rank_in_archive_order":1,"of":13,"metrics":{"F1 score":"0.97","Precision":"0.97","Recall":"0.97"},"uses_additional_data":false},{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"Gaussian SVM","rank_in_archive_order":2,"of":13,"metrics":{"F1 score":"0.96","Precision":"0.95","Recall":"0.96"},"uses_additional_data":false},{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"Decision Tree","rank_in_archive_order":3,"of":13,"metrics":{"F1 score":"0.91","Precision":"0.90","Recall":"0.92"},"uses_additional_data":false},{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"Boosted Trees","rank_in_archive_order":4,"of":13,"metrics":{"F1 score":"0.87","Precision":"0.91","Recall":"0.83"},"uses_additional_data":false},{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"K-NN","rank_in_archive_order":5,"of":13,"metrics":{"F1 score":"0.82","Precision":"0.80","Recall":"0.85"},"uses_additional_data":false},{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"Logistic regression","rank_in_archive_order":6,"of":13,"metrics":{"F1 score":"0.72","Precision":"0.77","Recall":"0.67"},"uses_additional_data":false},{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"Linear Discriminant","rank_in_archive_order":7,"of":13,"metrics":{"F1 score":"0.71","Precision":"0.78","Recall":"0.66"},"uses_additional_data":false},{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"Linear SVM","rank_in_archive_order":8,"of":13,"metrics":{"F1 score":"0.70","Precision":"0.80","Recall":"0.63"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1803.06589","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}