A machine learning approach for predicting urine output after fluid administration. (August 2019)

• Record Type: Journal Article
• Authors: Lin, Pei-Chen; Huang, Hsu-Cheng; Komorowski, Matthieu; Lin, Wei-Kai; Chang, Chun-Min; Chen, Kuan-Ta; Li, Yu-Chuan; Lin, Ming-Chin
• Is Part Of: Computer methods and programs in biomedicine. Volume 177(2019)
• Page Start: 155
• Page End: 159
• Publication Date: 2019-08
• Subjects: Sepsis -- Prediction -- Machine learning -- Electronic health records -- Clinical decision support -- Fluid resuscitation; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2019.05.009
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We proposed a machine learning method to solve a clinical unmet need in predicting urine output in sepsis patients after fluid resuscitation. This study identified the important clinical features for predicting patient's urine output after fluid resuscitation. This study revealed that the machine models had different performance in patients with different baseline renal functions, therefore different threshold should be chosen to optimize clinical efficacy. 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.