High glycemic variability (GV) is common in critically ill patients; however, the prevalence and mortality association with early GV in patients with sepsis remains unclear. This retrospective cohort study was conducted in a medical intensive care unit (ICU) in central Taiwan. Patients in the ICU with sepsis between January 2014 and December 2015 were included for analysis. All of these patients received protocol-based management, including blood sugar monitoring every 2 h for the first 24 h of ICU admission. Mean amplitude of glycemic excursions (MAGE) and coefficient of variation (CoV) were used to assess GV. A total of 452 patients (mean age 71.4 ± 14.7 years; 76.7% men) were enrolled for analysis. They were divided into high GV (43.4%, 196/452) and low GV (56.6%, 256/512) groups using MAGE 65 mg/dL as the cut-off point. Patients with high GV tended to have higher HbA1c (6.7 ± 1.8% vs. 5.9 ± 0.9%, p < 0.01) and were more likely to have diabetes mellitus (DM) (50.0% vs. 23.4%, p < 0.01) compared with those in the low GV group. Kaplan–Meier analysis showed that a high GV was associated with increased 30-day mortality (log-rank test, p = 0.018). The association remained strong in the non-DM (log-rank test, p = 0.035), but not in the DM (log-rank test, p = 0.254) group. Multivariate Cox proportional hazard regression analysis identified that high APACHE II score (adjusted hazard ratio (aHR) 1.045, 95% confidence interval (CI) 1.013–1.078), high serum lactate level at 0 h (aHR 1.009, 95% CI 1.003–1.014), having chronic airway disease (aHR 0.478, 95% CI 0.302–0.756), high mean day 1 glucose (aHR 1.008, 95% CI 1.000–1.016), and high MAGE (aHR 1.607, 95% CI 1.008–2.563) were independently associated with increased 30-day mortality. The association with 30-day mortality remained consistent when using CoV to assess GV. We found that approximately 40% of the septic patients had a high early GV, defined as MAGE > 65 mg/dL. Higher GV within 24 h of ICU admission was independently associated with increased 30-day mortality. These findings highlight the need to monitor GV in septic patients early during an ICU admission.

Introduction: Healthcare-associated pneumonia (HCAP) is a relatively new category of pneumonia. It refers to infections that occur prior to hospital admission in patients with specific risk factors following contact or exposure to a healthcare environment. There is currently no scoring index to predict the outcomes of HCAP patients. We applied and compared different community acquired pneumonia (CAP) scoring indices to predict 30-day mortality and 3-day and 14-day intensive care unit (ICU) admission in patients with HCAP. Methods: We conducted a retrospective cohort study based on an inpatient database from six medical centers, recruiting a total of 444 patients with HCAP between 1 January 2007 and 31 December 2007. Pneumonia severity scoring indices including PSI (pneumonia severity index), CURB 65 (confusion, urea, respiratory rate, blood pressure, age 65), IDSA/ATS (Infectious Diseases Society of America/American Thoracic Society), modified ATS rule, SCAP (severe community acquired pneumonia), SMART-COP (systolic blood pressure, multilobar involvement, albumin, respiratory rate, tachycardia, confusion, oxygenation, pH), SMRT-CO (systolic blood pressure, multilobar involvement, respiratory rate, tachycardia, confusion, oxygenation), and SOAR (systolic blood pressure, oxygenation, age, respiratory rate) were calculated for each patient. Patient characteristics, co-morbidities, pneumonia pathogen culture results, length of hospital stay (LOS), and length of ICU stay were also recorded. Results: PSI (>90) has the highest sensitivity in predicting mortality, followed by CURB-65 (≥2) and SCAP (>9) (SCAP score (area under the curve (AUC): 0.71), PSI (AUC: 0.70) and CURB-65 (AUC: 0.66)). Compared to PSI, modified ATS, IDSA/ATS, SCAP, and SMART-COP were easy to calculate. For predicting ICU admission (Day 3 and Day 14), modified ATS (AUC: 0.84, 0.82), SMART-COP (AUC: 0.84, 0.82), SCAP (AUC: 0.82, 0.80) and IDSA/ATS (AUC: 0.80, 0.79) performed better (statistically significant difference) than PSI, CURB-65, SOAR and SMRT-CO. Conclusions: The utility of the scoring indices for risk assessment in patients with healthcare-associated pneumonia shows that the scoring indices originally designed for CAP can be applied to HCAP.

Open-box models in medical domain have high acceptance and demand by many medical examiners. Even though the accuracy predicted by most of convolutional neural network (CNN) models is high, it is still not convincing as the detail discussion regarding the outcome is semi-transparent in the functioning process. As pneumonia is one of the top contagious infection that makes most of the population affected due to low immunity. Therefore, the goal of this paper is to implement an interpretable classification of pneumonia infection using eXplainable AI (XAI-ICP). Thus, XAI-ICP is the highly efficient system designed to solve this challenge by adapting to the recent population health conditions. The aim is to design an interpretable deep classification and transfer learning based evaluation for pneumonia infection classification. The model is primarily pre-trained using the open Chest X-Ray (CXR) dataset from National Institutes of Health (NIH). Whereas, the training input and testing given to this system is Taichung Veterans General Hospital (TCVGH) for independent learning, Taiwan + VinDr open dataset for transfer learning of pneumonia affected patients with labelled CXR images possessing three features of infiltrate, cardiomegaly and effusion. The data labelling is performed by the medical examiners with the XAI human-in-the-loop approach. The XAI-ICP demonstrates the XAI based re-configurable DCNN with human-in-the-loop as a novel approach. The interpretable deep classification provides detail transparency analysis and transfer learning for competitive accuracy. The purpose of this work, to design a re-configurable model that can continuously improve itself by using feedback system and provide feasibility for the model deployment across multiple countries to provide an efficient system for the pneumonia infection classification. The designed model then provides detail decisions taken at each step as transparency and features used within the algorithm for the pneumonia classification during the hospitalization. Thus, the scope can be given as explainable AI usage for the diagnosis classification using data preprocessing and interpretable deep convolutional neural network by the CXR evaluation. The accuracy achieved by using independent learning classification is 92.14% and is further improved based on successive transfer learning based evaluation is 93.29%. The XAI-ICP model adapts to the different population by using transfer learning, while providing competitive results to the affected conditions.

Background: Machine learning (ML) model is increasingly used to predict short-term outcome in critically ill patients, but the study for long-term outcome is sparse. We used explainable ML approach to establish 30-day, 90-day and 1-year mortality prediction model in critically ill ventilated patients. Methods: We retrospectively included patients who were admitted to intensive care units during 2015–2018 at a tertiary hospital in central Taiwan and linked with the Taiwanese nationwide death registration data. Three ML models, including extreme gradient boosting (XGBoost), random forest (RF) and logistic regression (LR), were used to establish mortality prediction model. Furthermore, we used feature importance, Shapley Additive exPlanations (SHAP) plot, partial dependence plot (PDP), and local interpretable model-agnostic explanations (LIME) to explain the established model. Results: We enrolled 6994 patients and found the accuracy was similar among the three ML models, and the area under the curve value of using XGBoost to predict 30-day, 90-day and 1-year mortality were 0.858, 0.839 and 0.816, respectively. The calibration curve and decision curve analysis further demonstrated accuracy and applicability of models. SHAP summary plot and PDP plot illustrated the discriminative point of APACHE (acute physiology and chronic health exam) II score, haemoglobin and albumin to predict 1-year mortality. The application of LIME and SHAP force plots quantified the probability of 1-year mortality and algorithm of key features at individual patient level. Conclusions: We used an explainable ML approach, mainly XGBoost, SHAP and LIME plots to establish an explainable 1-year mortality prediction ML model in critically ill ventilated patients.

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.