This study aimed to develop an early prediction model for identifying patients with bloodstream infections. The data resource was taken from 2015 to 2019 at Taichung Veterans General Hospital, and a total of 1647 bloodstream infection episodes and 3552 non-bloodstream infection episodes in the intensive care unit (ICU) were included in the model development and evaluation. During the data analysis, 30 clinical variables were selected, including patients’ basic characteristics, vital signs, laboratory data, and clinical information. Five machine learning algorithms were applied to examine the prediction model performance. The findings indicated that the area under the receiver operating characteristic curve (AUROC) of the prediction performance of the XGBoost model was 0.825 for the validation dataset and 0.821 for the testing dataset. The random forest model also presented higher values for the AUROC on the validation dataset and testing dataset, which were 0.855 and 0.851, respectively. The tree-based ensemble learning model enabled high detection ability for patients with bloodstream infections in the ICU. Additionally, the analysis of importance of features revealed that alkaline phosphatase (ALKP) and the period of the central venous catheter are the most important predictors for bloodstream infections. We further explored the relationship between features and the risk of bloodstream infection by using the Shapley Additive exPlanations (SHAP) visualized method. The results showed that a higher prothrombin time is more prominent in a bloodstream infection. Additionally, the impact of a lower platelet count and albumin was more prominent in a bloodstream infection. Our results provide additional clinical information for cut-off laboratory values to assist clinical decision-making in bloodstream infection diagnostics.

Fluid balance is an essential issue in critical care; however, the impact of early fluid balance on the long-term mortality in critically ill surgical patients remains unknown. This study aimed to address the impact of day 1–3 and day 4–7 fluid balance on the long-term mortality in critically ill surgical patients. We enrolled patients who were admitted to surgical intensive care units (ICUs) during 2015–2019 at a tertiary hospital in central Taiwan and retrieved date-of-death from the Taiwanese nationwide death registration profile. We used a Log-rank test and a multivariable Cox proportional hazards regression model to determine the independent mortality impact of early fluid balance. A total of 6978 patients were included for analyses (mean age: 60.9 ± 15.9 years; 63.9% of them were men). In-hospital mortality, 90-day mortality, 1-year and overall mortality was 10.3%, 15.8%, 23.8% and 31.7%, respectively. In a multivariable Cox proportional hazard regression model adjusted for relevant covariates, we found that positive cumulative day 4–7 fluid balance was independently associated with long-term mortality (aHR 1.083, 95% CI 1.062–1.105), and a similar trend was found on day 1–3 fluid balance, although to a lesser extent (aHR 1.027, 95% CI 1.011–1.043). In conclusion, the fluid balance in the first week of ICU stay, particularly day 4–7 fluid balance, may affect the long-term outcome in critically ill surgical patients.

Acute kidney injury (AKI) refers to rapid decline of kidney function and is manifested by decreasing urine output or abnormal blood test (elevated serum creatinine). Electronic health records (EHRs) is fundamental for clinicians and machine learning algorithms to predict the clinical outcome of patients in the Intensive Care Unit (ICU). Early prediction of AKI could automatically warn the clinicians to review the possible risk factors and act in advance to prevent it. However, the enormous amount of patient data usually consists of a relatively incomplete data set and is very challenging for supervised machine learning process. In this paper, we propose an entropy-based feature engineering framework for vital signs based on their frequency of records. In particular, we address the missing at random (MAR) and missing not at random (MNAR) types of missing data according to different clinical scenarios. Regarding its applicability, we applied it to establish a prediction model for future AKI in ICU patients using 4278 ICU admissions from a tertiary hospital. Our result shows that the proposed entropy-based features are feasible to be used in the AKI prediction model and its performance improves as the data availability increases. In addition, we study the performance of AKI prediction model by comparing different time gaps and feature windows with the proposed vital sign entropy features. This work could be used as a guidance for feature windows selection and missing data processing during the development of a prediction model in ICU.