Shin TR, et al. J Korean Med Sci. 2015 Oct;30(10):1459-1465. https://doi.org/10.3346/jkms.2015.30.10.1459

Jang SH, et al. J Korean Med Assoc. 2015 Apr;58(4):291-301. http://dx.doi.org/10.5124/jkma.2015.58.4.291

Discontinuing mechanical ventilation remains challenging. We developed a machine learning model to predict weaning outcomes using only continuous monitoring parameters obtained from ventilators during spontaneous breathing trials (SBTs). Patients who received mechanical ventilation in the medical intensive care unit at a tertiary university hospital from 2019–2021 were included in this study. During the SBTs, three waveforms and 25 numerical data were collected as input variables. The proposed convolutional neural network (CNN)-based weaning prediction model extracts features from input data with diverse lengths. Among 138 enrolled patients, 35 (25.4%) experienced weaning failure. The dataset was randomly divided into training and test sets (8:2 ratio). The area under the receiver operating characteristic curve for weaning success by the prediction model was 0.912 (95% confidence interval [CI], 0.795–1.000), with an area under the precision-recall curve of 0.767 (95% CI, 0.434–0.983). Furthermore, we used gradient-weighted class activation mapping technology to provide visual explanations of the model’s prediction, highlighting influential features. This tool can assist medical staff by providing intuitive information regarding readiness for extubation without requiring any additional data collection other than SBT data. The proposed predictive model can assist clinicians in making ventilator weaning decisions in real time, thereby improving patient outcomes.

SETTING: A tertiary care academic medical centre.OBJECTIVE: To evaluate the clinical usefulness of C-X-C motif chemokine receptor 3 (CXCR3) ligands in tuberculous pleural effusion (TPE).DESIGN: We recruited 336 patients with pleural effusion due to various causes. Concentrations of interferon-gamma (IFN-γ) and the CXCR3 ligands CXCL9 and CXCL11 were determined using enzyme immunoassays; adenosine deaminase (ADA) activity was measured in pleural fluid and serum.RESULTS: TPE was diagnosed in 106 patients. Non-TB conditions included lung cancer (n = 95), para-pneumonic effusion (n = 52), non-lung malignancy (n = 30), other exudate (n = 24) and transudate (n = 29) disorders. All marker levels in serum samples and pleural fluid were significantly higher in the TPE group. Analyses of receiver operating characteristic curves for differentiating TPE from non-TB effusions produced the following results for the area under the curve (AUC) for CXCL9, CXCL11, IFN-γ and ADA, respectively: 0.982, 0.952, 0.982, and 0.952. Marker AUCs in lymphocytic exudates were also high. Combining the levels of CXCL9, IFN-γ and ADA in pleural fluid improved the diagnostic performance. Serum levels of CXCL9 had the highest AUC (0.848) for diagnosing TPE.CONCLUSION: Levels of CXR3 ligands in pleural effusion are useful for diagnosing TPE.

OBJECTIVES: We aimed to determine the characteristics of the deceased victims of deaths caused by exposure to humidifier disinfectants, and present the distribution of the victims’ data submitted for damage application, demographic characteristics, imaging findings, characteristics of humidifier disinfectant exposure, and distribution of the causes of death.METHODS: An integrated database of victims was established using the medical records data of 1,413 victims submitted during the application for death damage caused by exposure to humidifier disinfectants, and the demographic characteristics, medical records, imaging findings, exposure characteristics, and cause of death were examined.RESULTS: The average numbers of data submissions of each applicant for death damage were 3.0 medical use records. A total of 608 (43.0%) victims had more than one finding of acute, subacute, or chronic interstitial lung diseases. The average daily and cumulative use times of the victims were 14.40 and 24,645.81 hours, respectively, indicating greater exposure in this group than in the survivors. The humidifier disinfectants’ components comprised polyhexamethylene guanidine (72.8%), chloromethylisothiazolinone/methylisothiazolinone (10.5%), other components (15.0%), and oligo-[2-(2-ethoxy)-ethoxyethyl] guanidine chloride (1.5%). The components’ distribution was 67.8% for single-component use, which was higher than that in the survivors (59.8%). The distribution of the causes of death were: respiratory diseases (54.4%), neoplasms (16.8%), and circulatory diseases (6.3%). Other interstitial lung diseases (65.5%) were the most common cause of death among those who died due to respiratory diseases.CONCLUSIONS: Careful discussions of appropriate remedies should be conducted based on a comprehensive understanding of the characteristics of the deceased victims, considering their specificities and limitations.

Background: COPD coexists with many concurrent comorbidities. Cardiovascular complications are deemed to be major causes of death in COPD. Although inhaler therapy is the main therapeutic intervention in COPD, cardiovascular events accompanying inhaler therapy require further investigation. Therefore, this study aimed to investigate new development of cardiovascular events according to each inhaler therapy and comorbidities. Methods: This study analyzed COPD patients (age ≥ 40 years, N = 199,772) from the Health Insurance Review and Assessment Service (HIRA) database in Korea. The development of cardiovascular events, from the index date to December 31, 2020, was investigated. The cohort was eventually divided into three arms: the LAMA/LABA group (N = 28,322), the ICS/LABA group (N = 11,812), and the triple group (LAMA/ICS/LABA therapy, N = 6174). Results: Multivariable Cox analyses demonstrated that, compared to ICS/LABA therapy, triple therapy was independently associated with the development of ischemic heart disease (HR: 1.22, 95% CI: 1.04– 1.43), heart failure (HR: 1.45, 95% CI: 1.14– 1.84), arrhythmia (HR: 1.72, 95% CI: 1.41– 2.09), and atrial fibrillation/flutter (HR: 2.31, 95% CI: 1.64– 3.25), whereas the LAMA/LABA therapy did not show a significant association. Furthermore, emergency room visit during covariate assessment window was independently associated with the development of ischemic heart disease, heart failure, arrhythmia, and atrial fibrillation/flutter (p < 0.05). Conclusion: Our data suggest that cardiovascular risk should be considered in COPD patients receiving triple therapy, despite the confounding bias resulting from disparities in each group.