Developing a machine-learning model for real-time prediction of successful extubation in mechanically ventilated patients using time-series ventilator-derived parameters.

Background: Successful 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. Methods: Patients 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. Results: In 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. Conclusion: The 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.

Glycemic Control with Thiazolidinedione Is Associated with Fracture of T2DM Patients.

OBJECTIVE: Diabetes 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. METHODS: We 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. RESULTS: We 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. CONCLUSIONS: We 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.

Spontaneous recovery of ventilator-associated pneumothorax.

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.

Simultaneous use of traditional Chinese medicine (si-ni-tang) to treat septic shock patients: study protocol for a randomized controlled trial.

BACKGROUND: Even though there are continually upgraded recommendations for managing sepsis, such as "Surviving Sepsis Campaign: international guidelines for management of severe sepsis and septic shock", mortality is still high. Si-ni-tang, a remedy documented in Shanghan Lun, a medical collection from ancient China, is used for treating patients with sepsis and septic shock. Using a well-designed clinical trial, we are eager to survey the effectiveness of the concurrent use of this remedy in restoring these patients' hemodynamic status, or "Yang Qi". METHODS/DESIGN: Patients admitted to our medical intensive care units with the diagnosis of septic shock, defined as persistent hypotension induced by sepsis despite adequate fluid resuscitation, are eligible for participation. The inclusion criteria include: age from 20 to 85 years, conditions meeting the definition of septic shock, use of vasopressors within 24 hours of entering the study, and use of a nasogastric tube for feeding. The enrolled patients are randomly allocated either to the si-ni-tang group or the placebo group. The prescription of the trial drugs (si-ni-tang/placebo) is 2.25 grams 4 times a day for 7 days or till shock reversal (if shock reversal occurs in less than 7 days). Data, including duration of vasopressor infusion, gender, age, co-morbidities, APACHE II score, predicted mortality, ICU mortality, ICU length of stay, hospital mortality, hospital length of stay, source of sepsis, and culture results, are collected for the following analysis. DISCUSSION: Si-ni-tang is composed of processed Zingiber officinale, Glycyrrhiza uralensis, and Aconitum carmichaeli. Zingiber officinale and Glycyrrhiza uralensis are found to have the ability to reduce pro-inflammatory cytokine production, to inhibit lipopolisaccharide-induced macrophage activation and function, and to lessen the bacterial load and suppress acute and chronic inflammation. Aconitum carmichaeli is known to have vasopressor activity, and positive chronotropic and inotropic effects. As this remedy has a potential benefit in treating septic shock patients, we designed a double-blind, prospective, randomized controlled trial and would like to publish the results and conclusions later. TRIAL REGISTRATION: ClinicalTrials.gov: NCT01223430.