ObjectiveDiabetes is a common diseases and a major problem worldwide. Diabetic osteopathy might be elevated in diabetic patients and is usually caused by bone fracture. Several diabetes medications, such as thiazolidinediones (TZDs), could lead to increased risks of fracture.MethodsWe used the nationwide database to identified 32466 patients who had developed type 2 diabetes from 2000 to 2010 as the diabetic cohort and, from that group, we selected 3427 diabetic patients who had developed bone fracture to survey the possible risk factors, includng commonly used diabetes medication.ResultsWe found that TZDs might present increased risks for fracture in patients who used it for an extended period (7 to 730 days before the index date), especially in female patients younger than 64 years old, for whom the risk was elevated from a 1.74- to a 2.58-fold odds ratio.ConclusionsWe recommend that clinics follow up with non-osteoporotic female patients younger than 64 years old who are using TZDs, to avoid the associated risks of fracture.

Background: The usual management of ventilator-associated pneumothorax (VPX) is tube thoracostomy. However, this recommendation is based on tradition rather than on solid evidence. Although it has been applied successfully to other types of pneumothoraces, observation has not been used in the management of VPX. Objectives: In this study, we investigated whether observation is a valid treatment strategy for VPX. Methods: We retrospectively analyzed data of 471 patients with VPX (2003-2010) and found that 27 did not receive tube thoracostomy. Most of those patients (89%) had documented do-not-resuscitate orders and had refused tube thoracostomy. For comparison, 54 patients with tube thoracostomy, matched by age and do-not-resuscitate status, were chosen as controls. Among patients without tube thoracostomy, we compared attribute differences between those recovered and those not recovered. Results: Thirteen patients (48%) without tube thoracostomy experienced spontaneous recovery of their pneumothoraces. This rate of chest tube-free recovery was higher than that of patients with tube thoracostomy (48 vs. 17%; p = 0.003). The patients did not differ in in-hospital mortality rate, time to ventilator discontinuation or survival. By univariate logistic regression, spontaneous recovery was associated with VPX caused by needle puncture, lack of respiratory distress, large tidal volume and low oxygen requirement following pneumothorax, as well as by physician recommendation against intubation. Conclusion: Observation under physician surveillance is an effective option of managing many VPXs, especially those caused by needle puncture, when patients are not in respiratory distress or when patients have acceptable tidal volumes and oxygen requirements following pneumothorax.

Background and objective: Successful weaning from mechanical ventilation is important for patients admitted to intensive care units (ICUs); however, models for predicting real-time weaning outcomes remain inadequate. Therefore, this study was designed to develop a machine learning model using time series ventilator-derived parameters with good accuracy for predicting successful extubation. Methods Patients with mechanical ventilation between August 2015 and November 2020 admitted Yuanlin Christian Hospital in Taiwan were retrospectively included. The ventilator-derived parameter time series dataset was collected before extubation. Recursive Feature Elimination (RFE) was applied to choose the most important features. Machine learning models of logistic regression, random forest (RF), and support vector machine were adopted for predicting extubation outcomes. In addition, the synthetic minority oversampling technique (SMOTE) was employed to address the data imbalance problem. Area under receiver operating characteristic (AUC), F1 score, and accuracy along with 10-fold cross-validation were used to evaluate prediction performance. Results In this study, 233 patients were included, of whom 28 (12.0%) failed extubation. Moreover, the six ventilatory variables per 180-s dataset had the optimal feature importance. The RF exhibited better performance than others with an AUC of 0.976 (95% confidence interval [CI], 0.975–0.976), an accuracy of 94.0% (95% CI, 93.8–94.3%), and an F1 score of 95.8% (95% CI, 95.7–96.0%). The difference in performance between the RF with original and SMOTE dataset was small. Conclusion The RF model demonstrated good performance for predicting successful extubation of mechanically ventilated patients. This algorithm makes a precise real-time extubation outcome prediction for a patient at different time points.

BackgroundSuccessful weaning from mechanical ventilation is important for patients admitted to intensive care units. However, models for predicting real-time weaning outcomes remain inadequate. Therefore, this study aimed to develop a machine-learning model for predicting successful extubation only using time-series ventilator-derived parameters with good accuracy.MethodsPatients with mechanical ventilation admitted to the Yuanlin Christian Hospital in Taiwan between August 2015 and November 2020 were retrospectively included. A dataset with ventilator-derived parameters was obtained before extubation. Recursive feature elimination was applied to select the most important features. Machine-learning models of logistic regression, random forest (RF), and support vector machine were adopted to predict extubation outcomes. In addition, the synthetic minority oversampling technique (SMOTE) was employed to address the data imbalance problem. The area under the receiver operating characteristic (AUC), F1 score, and accuracy, along with the 10-fold cross-validation, were used to evaluate prediction performance.ResultsIn this study, 233 patients were included, of whom 28 (12.0%) failed extubation. The six ventilatory variables per 180 s dataset had optimal feature importance. RF exhibited better performance than the others, with an AUC value of 0.976 (95% confidence interval [CI], 0.975–0.976), accuracy of 94.0% (95% CI, 93.8–94.3%), and an F1 score of 95.8% (95% CI, 95.7–96.0%). The difference in performance between the RF and the original and SMOTE datasets was small.ConclusionThe RF model demonstrated a good performance in predicting successful extubation in mechanically ventilated patients. This algorithm made a precise real-time extubation outcome prediction for patients at different time points.