Purpose: Early identification of patients at risk for acute respiratory failure (ARF) could help clinicians devise preventive strategies. Analyzing biosignals with artificial intelligence (AI) can uncover hidden information and variability within time series. We aimed to develop and validate AI models to predict ARF within 72 h after emergency department admission, primarily using highresolution biosignals collected within 4 h of arrival. Materials and Methods: Our AI model, built on convolutional recurrent neural networks, combines biosignal feature extraction and sequence modeling. The model was developed and internally validated with data from 5284 admissions [1085 (20.5%) positive for ARF], and externally validated using data from 144 admissions [7 (4.9%) positive for ARF] from another institution. We defined ARF as the application of advanced respiratory support devices. Results: Our AI model performed well in predicting ARF, achieving area under the receiver operating characteristic curve (AUROC) of 0.840 and 0.743 in internal and external validations, respectively. It outperformed the Modified Early Warning Score (MEWS) and XGBoost models built only with clinical variables. High predictive ability for mortality was observed, with AUROC up to 0.809. A 10% increase in AI prediction scores was associated with 1.44-fold and 1.42-fold increases in ARF risk and mortality risk, respectively, even after adjusting for MEWS and demographic variables. Conclusion Our AI model demonstrates high predictive accuracy and significant associations with clinical outcomes. Our AI model has the potential to promptly aid in triage decisions. Our study shows that using AI to analyze biosignals advances disease detection and prediction.

Purpose: Early identification of patients at risk for acute respiratory failure (ARF) could help clinicians devise preventive strategies. Analyzing biosignals with artificial intelligence (AI) can uncover hidden information and variability within time series. We aimed to develop and validate AI models to predict ARF within 72 h after emergency department admission, primarily using highresolution biosignals collected within 4 h of arrival. Materials and Methods: Our AI model, built on convolutional recurrent neural networks, combines biosignal feature extraction and sequence modeling. The model was developed and internally validated with data from 5284 admissions [1085 (20.5%) positive for ARF], and externally validated using data from 144 admissions [7 (4.9%) positive for ARF] from another institution. We defined ARF as the application of advanced respiratory support devices. Results: Our AI model performed well in predicting ARF, achieving area under the receiver operating characteristic curve (AUROC) of 0.840 and 0.743 in internal and external validations, respectively. It outperformed the Modified Early Warning Score (MEWS) and XGBoost models built only with clinical variables. High predictive ability for mortality was observed, with AUROC up to 0.809. A 10% increase in AI prediction scores was associated with 1.44-fold and 1.42-fold increases in ARF risk and mortality risk, respectively, even after adjusting for MEWS and demographic variables. Conclusion Our AI model demonstrates high predictive accuracy and significant associations with clinical outcomes. Our AI model has the potential to promptly aid in triage decisions. Our study shows that using AI to analyze biosignals advances disease detection and prediction.

Purpose: Early identification of patients at risk for acute respiratory failure (ARF) could help clinicians devise preventive strategies. Analyzing biosignals with artificial intelligence (AI) can uncover hidden information and variability within time series. We aimed to develop and validate AI models to predict ARF within 72 h after emergency department admission, primarily using highresolution biosignals collected within 4 h of arrival. Materials and Methods: Our AI model, built on convolutional recurrent neural networks, combines biosignal feature extraction and sequence modeling. The model was developed and internally validated with data from 5284 admissions [1085 (20.5%) positive for ARF], and externally validated using data from 144 admissions [7 (4.9%) positive for ARF] from another institution. We defined ARF as the application of advanced respiratory support devices. Results: Our AI model performed well in predicting ARF, achieving area under the receiver operating characteristic curve (AUROC) of 0.840 and 0.743 in internal and external validations, respectively. It outperformed the Modified Early Warning Score (MEWS) and XGBoost models built only with clinical variables. High predictive ability for mortality was observed, with AUROC up to 0.809. A 10% increase in AI prediction scores was associated with 1.44-fold and 1.42-fold increases in ARF risk and mortality risk, respectively, even after adjusting for MEWS and demographic variables. Conclusion Our AI model demonstrates high predictive accuracy and significant associations with clinical outcomes. Our AI model has the potential to promptly aid in triage decisions. Our study shows that using AI to analyze biosignals advances disease detection and prediction.

Purpose: Early identification of patients at risk for acute respiratory failure (ARF) could help clinicians devise preventive strategies. Analyzing biosignals with artificial intelligence (AI) can uncover hidden information and variability within time series. We aimed to develop and validate AI models to predict ARF within 72 h after emergency department admission, primarily using highresolution biosignals collected within 4 h of arrival. Materials and Methods: Our AI model, built on convolutional recurrent neural networks, combines biosignal feature extraction and sequence modeling. The model was developed and internally validated with data from 5284 admissions [1085 (20.5%) positive for ARF], and externally validated using data from 144 admissions [7 (4.9%) positive for ARF] from another institution. We defined ARF as the application of advanced respiratory support devices. Results: Our AI model performed well in predicting ARF, achieving area under the receiver operating characteristic curve (AUROC) of 0.840 and 0.743 in internal and external validations, respectively. It outperformed the Modified Early Warning Score (MEWS) and XGBoost models built only with clinical variables. High predictive ability for mortality was observed, with AUROC up to 0.809. A 10% increase in AI prediction scores was associated with 1.44-fold and 1.42-fold increases in ARF risk and mortality risk, respectively, even after adjusting for MEWS and demographic variables. Conclusion Our AI model demonstrates high predictive accuracy and significant associations with clinical outcomes. Our AI model has the potential to promptly aid in triage decisions. Our study shows that using AI to analyze biosignals advances disease detection and prediction.

Purpose: Early identification of patients at risk for acute respiratory failure (ARF) could help clinicians devise preventive strategies. Analyzing biosignals with artificial intelligence (AI) can uncover hidden information and variability within time series. We aimed to develop and validate AI models to predict ARF within 72 h after emergency department admission, primarily using highresolution biosignals collected within 4 h of arrival. Materials and Methods: Our AI model, built on convolutional recurrent neural networks, combines biosignal feature extraction and sequence modeling. The model was developed and internally validated with data from 5284 admissions [1085 (20.5%) positive for ARF], and externally validated using data from 144 admissions [7 (4.9%) positive for ARF] from another institution. We defined ARF as the application of advanced respiratory support devices. Results: Our AI model performed well in predicting ARF, achieving area under the receiver operating characteristic curve (AUROC) of 0.840 and 0.743 in internal and external validations, respectively. It outperformed the Modified Early Warning Score (MEWS) and XGBoost models built only with clinical variables. High predictive ability for mortality was observed, with AUROC up to 0.809. A 10% increase in AI prediction scores was associated with 1.44-fold and 1.42-fold increases in ARF risk and mortality risk, respectively, even after adjusting for MEWS and demographic variables. Conclusion Our AI model demonstrates high predictive accuracy and significant associations with clinical outcomes. Our AI model has the potential to promptly aid in triage decisions. Our study shows that using AI to analyze biosignals advances disease detection and prediction.

BACKGROUND: Alternative medicines may be defined as forms of therapy or examination that have no scientific basis and where no effect or diagnostic reliability have been demonstrated by scientific methods. Many patients with atopic dermatitis try various forms of alternative medicine, and several studies about the use of alternative medicine in the patients of atopic dermatitis were performed in western countries but not in Korea. OBJECT: This study was performed to evaluate the use of alternative medicine in atopic dermatitis patients. METHODS: 188 patients of atopic dermatitis attending our outpatient clinic responded to questionnaires on the use of alternative medicine and the past history of atopic dermatitis. RESULTS: 136 of 188 patients(72%) reported previous or current use of one or more forms of alternative medicine. Herbal remedies(32.4%) were used most frequently, and health food preparations, spa therapy, and diet changes were also commonly used. The most common motif of using alternative medicine was "just want to try every possible treatment"(48.6%) and main information sources were people without same skin disease(relatives and friends)(50.0%). The majority(75.2%) reported they do not use the alternative medicine now because of the poor result. The use of the alternative medicine was related to the disease duration, and the cost of the atopic dermatitis treatment. CONCLUSIONS: The use of alternative medicine in atopic dermatitis is commonplace and should be of concern to dermatologists.
Ambulatory Care Facilities ; Complementary Therapies ; Dermatitis, Atopic* ; Diet ; Food, Organic ; Humans ; Korea ; Skin ; Surveys and Questionnaires

BACKGROUND: Adequate assessment and control of sedation play crucial roles in the proper performance of mechanical ventilation. METHODS: A total of 30 patients with various pulmonary diseases were prospectively enrolled. The study population was randomized into two groups. The sedation assessment group (SAG) received active protocol-based control of sedation, and in the empiric control group (ECG), the sedation levels were empirically adjusted. Subsequently, daily interruption of sedation (DIS) was conducted in the SAG. RESULTS: In the SAG, the dose of midazolam was significantly reduced by control of sedation (day 1, 1.3+/-0.5 microg/kg/min; day 2, 0.9+/-0.4 microg/kg/min; p<0.01), and was significantly lower than the ECG on day 2 (p<0.01). Likewise, on day 2, sedation levels were significantly lower in the SAG than in the ECG. Significant relationship was found between Ramsay sedation scale and Richmond agitation-sedation scale (RASS; rs=-0.57), Ramsay Sedation Scale and Bispectral Index (BIS; rs=0.77), and RASS and BIS (rs=-0.79). In 10 patients, who didn't require re-sedation after DIS, BIS showed the earliest and most significant changes among the sedation scales. Ventilatory parameters showed significant but less prominent changes, and hemodynamic parameters didn't show significant changes. No seriously adverse events ensued after the implementation of DIS. CONCLUSION: Active assessment and control of sedation significantly reduced the dosage of sedatives in patients receiving mechanical ventilation. DIS, conducted in limited cases, suggested its potential efficacy and tolerability.
Conscious Sedation ; Consciousness Monitors ; Electrocardiography ; Hemodynamics ; Humans ; Hypnotics and Sedatives ; Lung Diseases ; Midazolam ; Prospective Studies ; Respiration, Artificial ; Ventilators, Mechanical ; Weights and Measures

BACKGROUND: Adaptive support ventilation (ASV), an automated closed-loop ventilation mode, adapts to the mechanical characteristics of the respiratory system by continuous measurement and adjustment of the respiratory parameters. The adequacy of ASV was evaluated in the patients with acute lung injury (ALI). METHODS: A total of 36 patients (19 normal lungs and 17 ALIs) were enrolled. The patients' breathing patterns and respiratory mechanics parameters were recorded under the passive ventilation using the ASV mode. RESULTS: The ALI patients showed lower tidal volumes and higher respiratory rates (RR) compared to patients with normal lungs (7.1+/-0.9 mL/kg vs. 8.6+/-1.3 mL/kg IBW; 19.7+/-4.8 b/min vs. 14.6+/-4.6 b/min; p<0.05, respectively). The expiratory time constant (RCe) was lower in ALI patients than in those with normal lungs, and the expiratory time/RCe was maintained above 3 in both groups. In all patients, RR was correlated with RCe and peak inspiratory flow (rs=-0.40; rs=0.43; p<0.05, respectively). In ALI patients, significant correlations were found between RR and RCe (rs=-0.76, p<0.01), peak inspiratory flow and RR (rs=-0.53, p<0.05), and RCe and peak inspiratory flow (rs=-0.53, p<0.05). CONCLUSION: ASV was found to operate adequately according to the respiratory mechanical characteristics in the ALI patients. Discrepancies with the ARDS Network recommendations, such as a somewhat higher tidal volume, have yet to be addressed in further studies.
Acute Lung Injury ; Automation ; Humans ; Lung ; Respiration ; Respiratory Mechanics ; Respiratory Rate ; Respiratory System ; Tidal Volume ; Ventilation ; Ventilator-Induced Lung Injury ; Ventilators, Mechanical

BACKGROUND: Adaptive support ventilation (ASV), an automated closed-loop ventilation mode, adapts to the mechanical characteristics of the respiratory system by continuous measurement and adjustment of the respiratory parameters. The adequacy of ASV was evaluated in the patients with acute lung injury (ALI). METHODS: A total of 36 patients (19 normal lungs and 17 ALIs) were enrolled. The patients' breathing patterns and respiratory mechanics parameters were recorded under the passive ventilation using the ASV mode. RESULTS: The ALI patients showed lower tidal volumes and higher respiratory rates (RR) compared to patients with normal lungs (7.1+/-0.9 mL/kg vs. 8.6+/-1.3 mL/kg IBW; 19.7+/-4.8 b/min vs. 14.6+/-4.6 b/min; p<0.05, respectively). The expiratory time constant (RCe) was lower in ALI patients than in those with normal lungs, and the expiratory time/RCe was maintained above 3 in both groups. In all patients, RR was correlated with RCe and peak inspiratory flow (rs=-0.40; rs=0.43; p<0.05, respectively). In ALI patients, significant correlations were found between RR and RCe (rs=-0.76, p<0.01), peak inspiratory flow and RR (rs=-0.53, p<0.05), and RCe and peak inspiratory flow (rs=-0.53, p<0.05). CONCLUSION: ASV was found to operate adequately according to the respiratory mechanical characteristics in the ALI patients. Discrepancies with the ARDS Network recommendations, such as a somewhat higher tidal volume, have yet to be addressed in further studies.
Acute Lung Injury ; Automation ; Humans ; Lung ; Respiration ; Respiratory Mechanics ; Respiratory Rate ; Respiratory System ; Tidal Volume ; Ventilation ; Ventilator-Induced Lung Injury ; Ventilators, Mechanical

BACKGROUND: Apoptosis plays a role in the development of pleural effusion. Caspase-cleaved cytokeratin 18, a marker for epithelial cell apoptosis, was evaluated in pleural effusion. METHODS: A total of 79 patients with pleural effusion were enrolled. The underlying causes were lung cancer (n=24), parapneumonic effusion (n=15), tuberculous effusion (n=28), and transudates (n=12). The levels of M30, an epitope of caspase-cleaved cytokeratin 18, were measured in blood and pleural fluids using enzyme-linked immunosorbent assay along with routine cellular and biochemical parameters. The expression of M30 was evaluated in the pleural tissues using immunohistochemistry for M30. RESULTS: The M30 levels in pleural fluid were significantly higher in patients with tuberculosis (2,632.1+/-1,467.3 U/mL) than in patients with lung cancer (956.5+/-618.5 U/mL), parapneumonic effusion (689.9+/-413.6 U/mL), and transudates (273.6+/-144.5 U/mL; all p<0.01). The serum levels were not significantly different among the disease groups. Based on receiver operating characteristics analysis, the area under the curve of M30 for differentiating tuberculous pleural effusion from all other effusions was 0.93. In the immunohistochemical analysis of M30, all pathologic types of cancer cells showed moderate to high expression, and the epithelioid cells in granulomas showed high expression in tuberculous pleural tissues. CONCLUSION: Caspase-cleaved cytokeratin 18 was most prominently observed in tuberculous pleural effusion and showed utility as a clinical marker. The main source of M30 was found to be the epithelioid cells of granulomas in tuberculous pleural tissues.
Apoptosis ; Biomarkers ; Cytoskeleton ; Enzyme-Linked Immunosorbent Assay ; Epithelial Cells ; Epithelioid Cells ; Exudates and Transudates ; Granuloma ; Humans ; Immunohistochemistry ; Keratin-18* ; Keratins* ; Lung Neoplasms ; Pleural Effusion* ; ROC Curve ; Tuberculosis ; Tuberculosis, Pleural