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.

This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model’s performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52–17.77) and moderate (HR, 12.90; 95% CI, 9.92–16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42–1.95) and moderate (HR, 1.42; 95% CI, 0.99–2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.

This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model’s performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52–17.77) and moderate (HR, 12.90; 95% CI, 9.92–16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42–1.95) and moderate (HR, 1.42; 95% CI, 0.99–2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.

This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model’s performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52–17.77) and moderate (HR, 12.90; 95% CI, 9.92–16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42–1.95) and moderate (HR, 1.42; 95% CI, 0.99–2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.

This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model’s performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52–17.77) and moderate (HR, 12.90; 95% CI, 9.92–16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42–1.95) and moderate (HR, 1.42; 95% CI, 0.99–2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.

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.