Search

In hospitals, the deterioration of a patient's condition leading to death is often preceded by physiological abnormalities in the hours to days beforehand. Several risk‐scoring systems have been developed to identify patients at risk of major adverse events; however, such systems often exhibit low sensitivity and specificity. To identify the risk factors associated with in‐hospital cardiac arrest (IHCA), we conducted a retrospective cohort study at a tertiary medical center in Taiwan. Four machine learning algorithms were employed to identify the factors most predictive of IHCA. The support vector machine model was discovered to be the most effective at predicting IHCA. The ten most critical physiological parameters at 8 h prior to the event were pulse rate, age, white blood cell count, lymphocyte count, body temperature, body mass index, systolic and diastolic blood pressure, platelet count, and use of central nervous system‐active medication. Using these parameters, we can enhance early warning and rapid response systems in our hospital, potentially reducing the incidence of IHCA in clinical practice. [ABSTRACT FROM AUTHOR]

Background: Spontaneous intracerebral hemorrhage (ICH) is associated with high case fatality and significant healthcare costs. Recent studies emphasize the critical role of nutritional status in affecting outcomes in neurological disorders. This study investigates the relationship between the Prognostic Nutrition Index (PNI) and in-hospital complications and case fatality among patients with ICH. Methods: A retrospective analysis was performed using data from the Changhua Christian Hospital Clinical Research Database between January 2015 and December 2022. Patients under 20 or over 100 years of age or with incomplete medical data were excluded. We utilized restricted cubic spline models, Kaplan–Meier survival analysis, and ROC analysis to assess the association between PNI and clinical outcomes. Propensity score matching analysis was performed to balance these clinical variables between groups. Results: In this study, 2402 patients with spontaneous ICH were assessed using the median PNI value of 42.77. The cohort was evenly divided between low and high PNI groups, predominantly male (59.1%), with an average age of 64 years. Patients with lower PNI scores at admission had higher in-hospital complications and increased 28- and 90-day case fatality rates. Conclusions: Our study suggests that PNI could serve as a valuable marker for predicting medical complications and case fatality in patients with spontaneous ICH. [ABSTRACT FROM AUTHOR]

The oxygen saturation index (OSI), defined by FIO2/SpO2 multiplied by the mean airway pressure, has been reported to exceed the Berlin definition in predicting the mortality of acute respiratory distress syndrome (ARDS). The OSI has served as an alternative to the Berlin definition in categorizing pediatric ARDS. However, the use of the OSI for the stratification of adult ARDS has not been reported. A total of 379 invasively ventilated adult ARDS patients were retrospectively studied. The ARDS patients were classified into three groups by their incidence rate of mortality: mild (OSI < 14.69), moderate (14.69 < OSI < 23.08) and severe (OSI > 23.08). OSI-based categorization was highly correlated with the Berlin definition by a Kendall's tau of 0.578 (p < 0.001). The Kaplan–Meier curves of the three OSI-based groups were significantly different (p < 0.001). By the Berlin definition, the hazard ratio for 28-day mortality was 0.58 (0.33–1.05) and 0.95 (0.55–1.67) for the moderate and severe groups, respectively (compared to the mild group). In contrast, the corresponding hazard ratio was 1.01 (0.69–1.47) and 2.39 (1.71–3.35) for the moderate and severe groups defined by the OSI. By multivariate analysis, OSI-based severe ARDS was independently associated with 28-D or 90-D mortality. In conclusion, we report the first OSI-based stratification for adult ARDS and find that it serves well as an alternative to the Berlin definition. [ABSTRACT FROM AUTHOR]