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: Heart rate variability (HRV) extracted from electrocardiogram measured for a short period during a resting state is clinically used as a bio-signal reflecting the emotional state. However, as interest in wearable devices increases, greater attention is being paid to HRV extracted from long-term electrocardiogram, which may contain additional clinical information. The purpose of this study was to examine the characteristics of HRV parameters extracted through long-term electrocardiogram and explore the differences between participants with and without depression and anxiety symptoms. Methods: Long-term electrocardiogram was acquired from 354 adults with no psychiatric history who underwent Holter monitoring. Evening and nighttime HRV and the ratio of nighttime-to-evening HRV were compared between 127 participants with depressive symptoms and 227 participants without depressive symptoms. Comparisons were also made between participants with and without anxiety symptoms. Results: Absolute values of HRV parameters did not differ between groups based on the presence of depressive or anxiety symptoms. Overall, HRV parameters increased at nighttime compared to evening. Participants with depressive symptoms showed a significantly higher nighttime-to-evening ratio of high-frequency HRV than participants without depressive symptoms. The nighttime-to-evening ratio of HRV parameters did not show a significant difference depending on the presence of anxiety symptoms. Conclusion HRV extracted through long-term electrocardiogram showed circadian rhythm. Depression may be associated with changes in the circadian rhythm of parasympathetic tone.

Objective: This study compared the prognostic performance of the following five injury severity scores: the Geriatric Trauma Outcome Score (GTOS), the Injury Severity Score (ISS), the New Injury Severity Score (NISS), the Revised Trauma Score (RTS), and the Trauma and Injury Severity Score (TRISS) for in-hospital mortality in severe geriatric trauma patients. Methods: A retrospective, cross-sectional, observational study was conducted using a database of severe geriatric trauma patients (age ≥65 years and ISS ≥16) who presented to a single regional trauma center between November 2016 and October 2018. We compared the baseline characteristics between the survivor and mortality groups and the predictive ability of the five scoring systems. Results: A total of 402 patients were included in the analysis; the in-hospital mortality rate was 25.6% (n=103). The TRISS had the highest area under the curve of 0.953 (95% confidence interval [CI], 0.927-0.971); followed by RTS, 0.777 (95% CI, 0.733-0.817); NISS, 0.733 (95% CI, 0.687-0.776); ISS, 0.660 (95% CI, 0.612-0.707); and GTOS, 0.660 (95% CI, 0.611-0.706) in severe geriatric trauma. The TRISS also had the highest area under the curve of 0.961 (0.919-0.985) among the injury severity scoring systems in polytrauma. The predictive ability of TRISS was significantly higher than the other four scores with respect to overall trauma and polytrauma (P<0.001). Conclusion The TRISS showed the highest prognostic performance for predicting in-hospital mortality among all the injury severity scoring systems in severe geriatric trauma.

Objective: This study compared the prognostic performance of the following five injury severity scores: the Geriatric Trauma Outcome Score (GTOS), the Injury Severity Score (ISS), the New Injury Severity Score (NISS), the Revised Trauma Score (RTS), and the Trauma and Injury Severity Score (TRISS) for in-hospital mortality in severe geriatric trauma patients. Methods: A retrospective, cross-sectional, observational study was conducted using a database of severe geriatric trauma patients (age ≥65 years and ISS ≥16) who presented to a single regional trauma center between November 2016 and October 2018. We compared the baseline characteristics between the survivor and mortality groups and the predictive ability of the five scoring systems. Results: A total of 402 patients were included in the analysis; the in-hospital mortality rate was 25.6% (n=103). The TRISS had the highest area under the curve of 0.953 (95% confidence interval [CI], 0.927-0.971); followed by RTS, 0.777 (95% CI, 0.733-0.817); NISS, 0.733 (95% CI, 0.687-0.776); ISS, 0.660 (95% CI, 0.612-0.707); and GTOS, 0.660 (95% CI, 0.611-0.706) in severe geriatric trauma. The TRISS also had the highest area under the curve of 0.961 (0.919-0.985) among the injury severity scoring systems in polytrauma. The predictive ability of TRISS was significantly higher than the other four scores with respect to overall trauma and polytrauma (P<0.001). Conclusion The TRISS showed the highest prognostic performance for predicting in-hospital mortality among all the injury severity scoring systems in severe geriatric trauma.

Background: There is currently a lack of evidence-based postresuscitation or postmortem guidelines for patients with out-of-hospital cardiac arrest (OHCA) in the setting of an emerging infectious disease. This study aimed to develop and validate a multimodal screening tool that aids in predicting the disease confirmation in emergency situations and patients with OHCA during a coronavirus disease 2019 (COVID-19) outbreak. Materials and Methods: We conducted a retrospective, multicenter observational study of adult patients with OHCA in Daegu, Korea. To identify the potential predictors that could be used in screening tools in the emergency department, we applied logistic regression to data collected from March 1 to March 14. The prediction performance of the screening variables was then assessed and validated on the data of patients with OHCA who were treated between February 19 and March 31, 2020. General patient characteristics and hematological findings of the COVID-19-negative and COVID-19-positive groups were compared. We also evaluated confirmation test criteria as predictors for COVID-19 positivity in patients with OHCA. Results: Advanced age, body temperature, and abnormal chest X-ray (CXR) revealed significant predictive ability in the derivation cohort. Of the 184 adult patients with OHCA identified in the validation cohort, 80 patients were included in the analysis. Notably, 9 patients were positive and 71 were negative on the COVID-19 reverse transcription polymerase chain reaction test. Five patients (55.6%) in the COVID-19-positive group had a fever before OHCA, and 12 (16.9%) of the COVID-19-negative group had a fever before OHCA (P = 0.018).Eight patients (88.9%) in the COVID-19-positive group had a CXR indicating pneumonic infiltration. Of the criteria for predicting COVID-19, fever or an abnormal CXR had a sensitivity of 100% (95% confidence interval [CI]: 65.4 – 100) and a specificity of 22.5% (95% CI: 13.5 – 34.0). Conclusion The screening tools that combined fever or abnormal CXR had a good discriminatory ability for COVID-19 infection in adult patients with OHCA. Therefore, during the COVID-19 outbreak period, it is recommended to suspect COVID-19 infection and perform COVID-19 test if patients present with a history of fever or show abnormal findings in postmortem CXR

Background: There is currently a lack of evidence-based postresuscitation or postmortem guidelines for patients with out-of-hospital cardiac arrest (OHCA) in the setting of an emerging infectious disease. This study aimed to develop and validate a multimodal screening tool that aids in predicting the disease confirmation in emergency situations and patients with OHCA during a coronavirus disease 2019 (COVID-19) outbreak. Materials and Methods: We conducted a retrospective, multicenter observational study of adult patients with OHCA in Daegu, Korea. To identify the potential predictors that could be used in screening tools in the emergency department, we applied logistic regression to data collected from March 1 to March 14. The prediction performance of the screening variables was then assessed and validated on the data of patients with OHCA who were treated between February 19 and March 31, 2020. General patient characteristics and hematological findings of the COVID-19-negative and COVID-19-positive groups were compared. We also evaluated confirmation test criteria as predictors for COVID-19 positivity in patients with OHCA. Results: Advanced age, body temperature, and abnormal chest X-ray (CXR) revealed significant predictive ability in the derivation cohort. Of the 184 adult patients with OHCA identified in the validation cohort, 80 patients were included in the analysis. Notably, 9 patients were positive and 71 were negative on the COVID-19 reverse transcription polymerase chain reaction test. Five patients (55.6%) in the COVID-19-positive group had a fever before OHCA, and 12 (16.9%) of the COVID-19-negative group had a fever before OHCA (P = 0.018).Eight patients (88.9%) in the COVID-19-positive group had a CXR indicating pneumonic infiltration. Of the criteria for predicting COVID-19, fever or an abnormal CXR had a sensitivity of 100% (95% confidence interval [CI]: 65.4 – 100) and a specificity of 22.5% (95% CI: 13.5 – 34.0). Conclusion The screening tools that combined fever or abnormal CXR had a good discriminatory ability for COVID-19 infection in adult patients with OHCA. Therefore, during the COVID-19 outbreak period, it is recommended to suspect COVID-19 infection and perform COVID-19 test if patients present with a history of fever or show abnormal findings in postmortem CXR