Pei-Chen Lin1, Hsu-Cheng Huang2, Matthieu Komorowski3, Wei-Kai Lin4, Chun-Min Chang4, Kuan-Ta Chen4, Yu-Chuan Li5, Ming-Chin Lin6. 1. Graduate Institute of Biomedical Informatics, College of Medicine Science and Technology, Taipei Medical University, Taipei, Taiwan; Emergency Department, Taoyuan General Hospital, Ministry of Health and Welfare, Taoyuan, Taiwan. 2. Department of Medical Imaging, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan; Department of Radiology, Taipei City Hospital, Yangming Branch, Taipei, Taiwan. 3. Department of Surgery and Cancer, Imperial College London, London, UK; Department of Bioengineering, Imperial College London, London, UK; Laboratory of Computational Physiology, Harvard-MIT Division of Health Sciences & Technology, Cambridge, MA, USA. 4. Institute of Information Science, Academia Sinica, Taipei, Taiwan. 5. International Center for Health Information Technology, Taipei Medical University, Taipei, Taiwan; Department of Dermatology, Wan Fang Hospital, Taipei, Taiwan. 6. Graduate Institute of Biomedical Informatics, College of Medicine Science and Technology, Taipei Medical University, Taipei, Taiwan; Department of Neurosurgery, Shuang Ho Hospital, Taipei Medical University, New Taipei City, Taiwan; Taipei Neuroscience Institute, Taipei Medical University, Taipei, Taiwan. Electronic address: arbiter@tmu.edu.tw.
Abstract
BACKGROUND AND OBJECTIVE: To develop a machine learning model to predict urine output (UO) in sepsis patients after fluid resuscitation. METHODS: We identified sepsis patients in the Multiparameter Intelligent Monitoring in Intensive Care-III v1.4 database according to the Sepsis-3 criteria. We focused on two outcomes: whether the UO decreased after fluid administration and whether oliguria (defined as UO less than the threshold of 0.5 mL/kg/h) developed. A gradient tree-based machine learning model implemented with an eXtreme Gradient Boosting algorithm was used to integrate relevant physiological parameters for predicting the aforementioned outcomes. A confusion matrix was computed. RESULTS: A total of 232,929 events in 19,275 patients were included. Using decreased UO as the outcome measure, the optimal model achieved an area under the curve (AUC) of 0.86; for predicting oliguria, most models achieved an AUC greater than 0.86, and the highest sensitivity was 92.2% when the model was applied to patients with baseline oliguria. CONCLUSIONS: Machine learning could help clinicians evaluate fluid status in sepsis patients after fluid administration, thus preventing fluid overload-related complications.
BACKGROUND AND OBJECTIVE: To develop a machine learning model to predict urine output (UO) in sepsispatients after fluid resuscitation. METHODS: We identified sepsispatients in the Multiparameter Intelligent Monitoring in Intensive Care-III v1.4 database according to the Sepsis-3 criteria. We focused on two outcomes: whether the UO decreased after fluid administration and whether oliguria (defined as UO less than the threshold of 0.5 mL/kg/h) developed. A gradient tree-based machine learning model implemented with an eXtreme Gradient Boosting algorithm was used to integrate relevant physiological parameters for predicting the aforementioned outcomes. A confusion matrix was computed. RESULTS: A total of 232,929 events in 19,275 patients were included. Using decreased UO as the outcome measure, the optimal model achieved an area under the curve (AUC) of 0.86; for predicting oliguria, most models achieved an AUC greater than 0.86, and the highest sensitivity was 92.2% when the model was applied to patients with baseline oliguria. CONCLUSIONS: Machine learning could help clinicians evaluate fluid status in sepsispatients after fluid administration, thus preventing fluid overload-related complications.
Authors: Jessica M Schwartz; Amanda J Moy; Sarah C Rossetti; Noémie Elhadad; Kenrick D Cato Journal: J Am Med Inform Assoc Date: 2021-03-01 Impact factor: 4.497