Kwon J, et al. J Korean Med Sci. 2022 Nov;37(50):e349. https://doi.org/10.3346/jkms.2022.37.e349

Background: Trauma is a major cause of mortality, disability, and health care costs worldwide. The establishment of a trauma system is known to solve these problems, but few studies have objectively evaluated the impact of a trauma system on outcomes. Since 2012, South Korea has established a national trauma system based on the implementation of 17 regional trauma centers nationwide and the improvement of the prehospital transfer system. This study aimed to measure the changes in performance and outcome according to the established national trauma system. Material and Methods: In this national cohort-based, retrospective follow-up observational study, the authors calculated the preventable trauma death rate (PTDR) by conducting a multipanel review of patients who died in 2015, 2017, and 2019. Furthermore, the authors constructed a risk-adjusted mortality prediction model of 4 767 876 patients between 2015 and 2019 using the extended-International Classification of Disease Injury Severity Scores to compare outcomes. Results: The PTDR was lower in 2019 than in 2015 (15.7 vs. 30.5, P <0.001) and 2017 (15.7 vs. 19.9%, P<0.001) representing 1247 additional lives saved in 2019 compared to that in 2015. In the risk-adjusted model, total trauma mortality was highest in 2015 at 0.56%, followed by that in 2016 and 2017 (0.50%), 2018 (0.51%), and 2019 (0.48%), revealing a significant decrease in mortality over the years (P<0.001 for trend), representing nearly 800 additional lives saved. The number of deaths for more severe patients with a probability of survival less than 0.25 significantly decreased from 81.50% in 2015 to 66.17% in 2019 (P<0.001). Conclusions: The authors observed a significant reduction in the PTDR and risk-adjusted trauma mortality in the 5-year follow-up since 2015 when the national trauma system was established. These findings could serve as a model for low-income and middle-income countries, where trauma systems are not yet established.

Background: Delirium in intensive care unit (ICU) patients poses a significant challenge, affecting patient outcomes and health care efficiency. Developing an accurate, real-time prediction model for delirium represents an advancement in critical care, addressing needs for timely intervention and resource optimization in ICUs. Objective: We aimed to create a novel machine learning model for delirium prediction in ICU patients using only continuous physiological data. Methods: We developed models integrating routinely available clinical data, such as age, sex, and patient monitoring device outputs, to ensure practicality and adaptability in diverse clinical settings. To confirm the reliability of delirium determination records, we prospectively collected results of Confusion Assessment Method for the ICU (CAM-ICU) evaluations performed by qualified investigators from May 17, 2021, to December 23, 2022, determining Cohen κ coefficients. Participants were included in the study if they were aged ≥18 years at ICU admission, had delirium evaluations using the CAM-ICU, and had data collected for at least 4 hours before delirium diagnosis or nondiagnosis. The development cohort from Yongin Severance Hospital (March 1, 2020, to January 12, 2022) comprised 5478 records: 5129 (93.62%) records from 651 patients for training and 349 (6.37%) records from 163 patients for internal validation. For temporal validation, we used 4438 records from the same hospital (January 28, 2022, to December 31, 2022) to reflect potential seasonal variations. External validation was performed using data from 670 patients at Ajou University Hospital (March 2022 to September 2022). We evaluated machine learning algorithms (random forest [RF], extra-trees classifier, and light gradient boosting machine) and selected the RF model as the final model based on its performance. To confirm clinical utility, a decision curve analysis and temporal pattern for model prediction during the ICU stay were performed. Results: The κ coefficient between labels generated by ICU nurses and prospectively verified by qualified researchers was 0.81, indicating reliable CAM-ICU results. Our final model showed robust performance in internal validation (area under the receiver operating characteristic curve [AUROC]: 0.82; area under the precision-recall curve [AUPRC]: 0.62) and maintained its accuracy in temporal validation (AUROC: 0.73; AUPRC: 0.85). External validation supported its effectiveness (AUROC: 0.84; AUPRC: 0.77). Decision curve analysis showed a positive net benefit at all thresholds, and the temporal pattern analysis showed a gradual increase in the model scores as the actual delirium diagnosis time approached. Conclusions: We developed a machine learning model for delirium prediction in ICU patients using routinely measured variables, including physiological waveforms. Our study demonstrates the potential of the RF model in predicting delirium, with consistent performance across various validation scenarios. The model uses noninvasive variables, making it applicable to a wide range of ICU patients, with minimal additional risk.

Huh Y, et al. J Korean Med Sci. 2021 May;36(22):e149. https://doi.org/10.3346/jkms.2021.36.e149

Background: We evaluated the accuracy of the prehospital Field Triage Decision Scheme, which has recently been applied in the Korean trauma system, and the factors associated with severe injury and prognosis at a regional trauma center in Korea. Methods: From 2016 to 2018, prehospital data of injured patients were obtained from the emergency medical services of the national fire agency and matched with trauma outcomes at our institution. Severe injury (Injury Severity Score > 15), overtriage/undertriage rate, positive predictive value, negative predictive value, and accuracy were reviewed according to the triage protocol steps. A multivariate logistic regression analysis was performed to identify influencing factors in the field triage. Results: Of the 2438 patients reviewed, 853 (35.0%) were severely injured. The protocol accuracy was as follows: step 1, 72.3%; step 2, 65.0%; step 3, 66.2%; step 1 or 2, 70.2%; and step 1, 2, or 3, 66.4%. Odds ratios (OR) (95% confidence interval [CIfor systolic blood pressure < 90 mmHg (3.535 [1.920–6.509]; p < 0.001), altered mental status (17.924 [8.980–35.777]; p < 0.001), and pedestrian injuries (2.473 [1.339–4.570], p = 0.04) were significantly associated with 24-h mortality. Penetrating torso injuries (7.108 [4.108–12.300]; p < 0.001); two or more proximal long bone fractures (4.134 [2.316–7.377]); p < 0.001); crushed, degloved, and mangled extremities (8.477 [4.068–17.663]; p < 0.001); amputation proximal to the wrist or ankle (42.964 [5.764–320.278]; p < 0.001); and fall from height (2.141 [1.497–3.062]; p < 0.001) were associated with 24-h surgical intervention. Conclusion: The Korean field triage protocol is not yet accurate, with only some factors reflecting injury severity, making reevaluation necessary.

Kang BH, et al. J Korean Med Sci. 2025 May;40:e165. https://doi.org/10.3346/jkms.2025.40.e165