Abstract
Risk assessment of in-hospital mortality of patients at the time of hospitalization is necessary for determining the scale of required medical resources for the patient depending on the patient's severity. Because recent machine learning application in the clinical area has been shown to enhance prediction ability, applying this technique to this issue can lead to an accurate prediction model for in-hospital mortality prediction. In this study, we aimed to generate an accurate prediction model of in-hospital mortality using machine learning techniques. Patients 18 years of age or older admitted to the University of Tokyo Hospital between January 1, 2009 and December 26, 2017 were used in this study. The data were divided into a training/validation data set (n = 119,160) and a test data set (n = 33,970) according to the time of admission. The prediction target of the model was the in-hospital mortality within 14 days. To generate the prediction model, 25 variables (age, sex, 21 laboratory test items, length of stay, and mortality) were used to predict in-hospital mortality. Logistic regression, random forests, multilayer perceptron, and gradient boost decision trees were performed to generate the prediction models. To evaluate the prediction capability of the model, the model was tested using a test data set. Mean probabilities obtained from trained models with five-fold cross-validation were used to calculate the area under the receiver operating characteristic (AUROC) curve. In a test stage using the test data set, prediction models of in-hospital mortality within 14 days showed AUROC values of 0.936, 0.942, 0.942, and 0.938 for logistic regression, random forests, multilayer perceptron, and gradient boosting decision trees, respectively. Machine learning-based prediction of short-term in-hospital mortality using admission laboratory data showed outstanding prediction capability and, therefore, has the potential to be useful for the risk assessment of patients at the time of hospitalization.
Highlights
Mortality prediction models of patients have long been developed to objectively assess the severity of the patients and share it among the medical care team to achieve collaborative care [1, 2]
The data used in this study was not openly available due to the restriction imposed by the research ethics committee (Office for Human Research Studies (OHRS); Graduate School of Medicine and Faculty of Medicine, The University of Tokyo, Faculty of Medicine Bldg. 2 4F, 7-3-1, Hongo, Bunkyo-ku, Tokyo, 113–0033, JAPAN, https://utokyo-ohrs.jp/en/)
The area under the receiver operating characteristic (AUROC) was calculated from the results of predicting inhospital mortality using 23 items with trained machine learning models against test data
Summary
Mortality prediction models of patients have long been developed to objectively assess the severity of the patients and share it among the medical care team to achieve collaborative care [1, 2]. The accurate mortality risk assessment of patients at the time of hospitalization is necessary for determining the scale of required medical resources needed according to the patient’s severity. To determine the scale of required medical resources according to the patient’s severity at the time of hospitalization, the mortality prediction model that covers the overall hospitalized population is required. To generate the mortality prediction model, laboratory values have been known to be useful in achieving favorable prediction capability [11,12,13,14]. Recent machine learning applications using nonlinear feature extraction in the clinical setting have been shown to enhance prediction ability [15, 16], and applying these types of techniques to this issue can lead to generating an accurate prediction model for in-hospital mortality prediction. In this study, we generated machine learning models of in-hospital mortality prediction with nonlinear feature extraction using laboratory data, compared them with a logistic regression model that uses linear feature extraction, and tried to generate an accurate prediction model of in-hospital mortality at the time of hospitalization
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.