This study was performed to evaluate the efficacy of using a thin bronchoscope for the diagnosis of pulmonary tuberculosis (PTB). Between March 2019 and November 2021, we prospectively enrolled participants with suspected PTB whose sputum acid-fast bacilli (AFB) smear and tuberculosis (TB) polymerase chain reaction (PCR) tests were negative or who could not produce self-expectorated sputum. Participants were randomized to a control group (bronchial washing [BW] using a 5.9-mm conventional bronchoscope guided by chest computed tomography) or an investigational group (BW using a 4.0-mm thin bronchoscope under virtual bronchoscopic navigation guidance). The primary outcome was detection of TB in BW fluid, defined as a positive result in the Xpert MTB/RIF assay. The secondary outcomes included AFB smear and Mycobacterium tuberculosis culture positivity, time to treatment initiation, and bronchoscopy-related complications. In total, 85 participants were included in the final analysis (43 in the control group and 42 in the investigational group). Twenty-three and 29, respectively, were finally diagnosed with PTB. The TB detection rate in BW fluid was higher in the investigational group (72.4% vs 43.5%, P = .035). Mycobacterium tuberculosis culture positivity was also higher in the investigational group (79.3% vs 52.2%, P = .038). No participants required premature bronchoscopy termination because of complications. Of the participants with PTB, the time to treatment initiation was shorter in the investigational group (median, 2.0 days vs 4.0 days, P = .001). BW using a thin bronchoscope increases the TB detection rate in patients with PTB compared to conventional bronchoscopy. Clinical Trials Registration. NCT03802812.

The main purpose of this study was to develop a model predictive of dysphagia in hospital survivors with severe pneumonia who underwent tracheostomy during their hospital stay. The present study included 175 patients (72% male; mean age, 71.3 years) over 5 years. None of these patients had a history of deglutition disorder before hospital admission. Binary logistic regression analysis was performed to identify factors predicting dysphagia at hospital discharge. Dysphagia scores were calculated from β-coefficients and by assigning points to variables. Of the enrolled patients, 105 (60%) had dysphagia at hospital discharge. Factors prognostic of dysphagia at hospital discharge included being underweight (body mass index < 18.5 kg/m²), non-participation in a dysphagia therapy program, mechanical ventilation ≥ 15 days, age ≥ 74 years, and chronic neurologic diseases. Underweight and non-participation in a dysphagia therapy program were assigned +2 points and the other factors were assigned +1 point. Dysphagia scores showed acceptable discrimination (area under the receiver operating characteristic curve for dysphagia 0.819, 95% confidence interval: 0.754–0.873, p < 0.001) and calibration (Hosmer–Lemeshow chi-square = 9.585, with df 7 and p = 0.213). The developed dysphagia score was predictive of deglutition disorder at hospital discharge in tracheostomized patients with severe pneumonia.

Background and Objectives: In this study, we evaluated clinical factors associated with implementing a rehabilitation program for patients with COVID-19-associated acute respiratory distress syndrome (ARDS) requiring mechanical ventilation (MV) during the quarantine period. Materials and Methods: This observational study was conducted in the National Designated Isolated ICU, a dedicated COVID-19 center with 18 beds, from 30 December 2020 to 30 May 2022. One hundred and fifty-four patients (mean age: 67.3 ± 13.4 years; male: 59.7%) were enrolled. The ICU rehabilitation program included early mobilization, chest physiotherapy, and dysphagia treatment. Results: Forty-five patients (29.3%) participated in the rehabilitation program. Multivariate logistic regression identified three significant factors: tracheostomy (odds ratio [OR], 2.796; 95% confidence interval [CI], 1.238–6.316; p = 0.013), body mass index ≥ 25.0 kg/m² (OR, 2.724; 95% CI, 1.276–5.817; p = 0.010), and extracorporeal membrane oxygenation (OR, 2.931; 95% CI, 1.165–7.377; p = 0.022); patients with all three factors were younger (median 44 vs. 70 years, p < 0.001) and had significantly lower Acute Physiology and Chronic Health Evaluation II scores (median 12 vs. 16, p = 0.002) on the MV day. One-year cumulative mortality rates for patients with 0 to 3 factors were 66.7%, 50.8%, 38.9%, and 15.4%, respectively, with a significant difference among them (log-rank, p < 0.001). Conclusions: Three clinical factors associated with implementing a rehabilitation program during the quarantine period for COVID-19-associated ARDS patients were identified. The program was feasible and beneficial, particularly for younger patients with lower illness severity and fewer comorbidities on the day of MV.

Background and Objectives: Timely recognition of deteriorating ward patients is critical to prevent adverse outcomes. The Deep learning–based Cardiac Arrest Risk Score (DeepCARS), an AI-based early warning system developed in Korea, has demonstrated high sensitivity and specificity, but its impact on real-world physician decision-making remains unclear, especially under healthcare resource constraints. Materials and Methods: We retrospectively analyzed 830 adult ward patients (March 2024–February 2025) who triggered DeepCARS alerts (score ≥ 91) at a tertiary hospital during a nationwide workforce shortage. Physician responses were classified as active intervention (ICU transfer, life-sustaining treatment [LST] decision, or specialty consultation) versus observation. Results: Among patients with DeepCARS ≥ 91, 58.9% received active intervention, with higher in-hospital mortality compared with those observed only (34.8% vs. 9.7%). ROC analysis suggested a cutoff of ≥94 for better intervention discrimination (AUC = 0.708). In multivariable analysis, DeepCARS ≥ 94 (OR 3.52) and chronic liver disease (OR 1.78) independently predicted active intervention. Multinomial analysis showed that patients admitted to medical departments were more often directed toward LST decisions rather than ICU transfer. Hemato-oncologic comorbidities were associated with both ICU transfer and LST decisions, while elevated respiratory rate consistently predicted either ICU transfer or LST discussions. Conclusions: DeepCARS alerts effectively triggered physician-driven decisions regarding ICU transfer and end-of-life care during a healthcare crisis. However, the ultimate clinical responses were shaped by comprehensive clinical judgment that integrated AI-generated risks with patient-specific factors, such as functional status and frailty, not captured by the algorithm. This underscores the indispensable role of individualized clinical assessment in interpreting and acting upon AI-based alerts in high-risk ward patients.

Patients who undergo tracheostomy and remain ventilator-dependent for over 21 days (defined as prolonged mechanical ventilation, PMV) represent a criticall

Background and Objectives: This study aimed to assess the value of a novel prognostic model, based on clinical variables, comorbidities, and demographic characteristics, to predict long-term prognosis in patients who received mechanical ventilation (MV) for over 14 days and who underwent a tracheostomy during the first 14 days of MV. Materials and Methods: Data were obtained from 278 patients (66.2% male; median age: 71 years) who underwent a tracheostomy within the first 14 days of MV from February 2011 to February 2021. Factors predicting 1-year mortality after the initiation of MV were identified by binary logistic regression analysis. The resulting prognostic model, known as the tracheostomy-ProVent score, was computed by assigning points to variables based on their respective ß-coefficients. Results: The overall 1-year mortality rate was 64.7%. Six factors were identified as prognostic indicators: platelet count < 150 × 10³/μL, PaO₂/FiO₂ < 200 mmHg, body mass index (BMI) < 23.0 kg/m², albumin concentration < 2.8 g/dL on day 14 of MV, chronic cardiovascular diseases, and immunocompromised status at admission. The tracheostomy-ProVent score exhibited acceptable discrimination, with an area under the receiver operating characteristic curve (AUC) of 0.786 (95% confidence interval: 0.733–0.833, p < 0.001) and acceptable calibration (Hosmer–Lemeshow chi-square: 2.753, df: 8, p = 0.949). Based on the maximum Youden index, the cut-off value for predicting mortality was set at ≥2, with a sensitivity of 67.4% and a specificity of 76.3%. Conclusions: The tracheostomy-ProVent score is a good predictive tool for estimating 1-year mortality in tracheostomized patients undergoing MV for >14 days. This comprehensive model integrates clinical variables and comorbidities, enhancing the precision of long-term prognosis in these patients.