RESUMO
Introduction: Gender variation in critically ill adults after resuscitation is reported in many studies. However, this variation is not well established when evaluating the physiological instability in this population. This study aimed to prospectively evaluate the gender variation in serious outcomes by the difficult airway physiological score (DAPS) among critically ill patients requiring endotracheal intubation (ETI). Methods: This is a cohort study conducted from August 2021 to December 2022 in the emergency department of Aga Khan University. The prospective validity of the difficult airway physiological score was derived using retrospective data and includes 12 variables: sex, age, time of intubation, hypotension, respiratory distress, vomiting, shock index >0.9, pH < 7.3, fever, anticipated decline, Glasgow Coma Scale (GCS) < 15, and agitation. The serious outcomes were cardiac arrest, mortality (within 1 hour after intubation in emergency), hypotension (systolic blood pressure <90 mmHg), and oxygen desaturation (SpO2 < 92%). The difference between males and females was assessed using the chi-square test, and the association of gender and serious outcomes was explored using Cox and logistic regression analysis. ROC curve analysis and area under the curve assessed score validity separately in males and females with serious outcomes. Results: We enrolled 326 patients with a mean age of 50.3 (±17.8), with 123 (33.7%) females and 203 (62.2%) males. 198 (60.7%) patients were >45 years old, of which 136 (67%) were male and 62 (50.4%) female. Cardiac arrest was observed in 56 (17.2%), with 24 (19.5%) females and 32 (15.8%) males, p value 0.348. Hypotension after intubation was observed in 132 (40.5%) patients, 56 (45.5%) females and 76 (37.4%) males, p value 0.149. Oxygen saturation (<92%) was observed in 80 (24.5%) patients, 32 (26%) females and 48 (23.6%) males, p value 0.630. In females, the DAPS of 11 had an area under the curve of 0.863 (0.74-0.91). The sensitivity of the score was 84.8%, the specificity was 71.9%, the PPV was 77.8%, and the NPV was 80.4% with an accuracy of 78.9%. In males, the DAPS score of 14 had an area under the curve of 0.892 (0.57-0.75). The sensitivity of the score was 67%, the specificity 93.8%, the PPV 92.2%, and the NPV 72.2% with an accuracy of 79.8%. Conclusions: The Difficult Airway Physiological Score (DAPS) predicts the risk of serious outcomes after intubation with high precision and reliability with different score cutoffs between the two sexes, highlighting the gender variation of a difficult airway.
RESUMO
BACKGROUND: The aim of our research was to design and evaluate an Artificial Neural Network (ANN) model using a systemic grid search for the early prediction of major adverse cardiac events (MACE) among patients presenting to the triage of an emergency department. METHODS: This is a single-center, cross-sectional study using electronic health records from January 2017 to December 2020. The research population consists of adults coming to our emergency department triage at Aga Khan University Hospital. The MACE during hospitalization was the main outcome. To enhance the architecture of an ANN using triage data, we used a systematic grid search strategy. Four hidden ANN layers were used, followed by an output layer. Following each hidden layer was back normalization and a dropout layer. MACE was predicted using three binary classifiers: ANN, Random Forests (RF), and logistic regression (LR). The overall accuracy, sensitivity, specificity, precision, and recall of these models were examined. Each model was evaluated using the receiver operating characteristic curve (ROC) and an F1-score with a 95% confidence interval. RESULTS: A total of 97,333 emergency department visits were recorded during the study period, with 33% of patients having cardiovascular symptoms. The mean age was 54.08 (19.18) years old. The MACE was observed in 23,052 (23.7%) of the patients, in-hospital (up to 30 days) mortality in 10,888 (11.2%) patients, and cardiac arrest in 5483 (5.6%) patients. The data used for training and validation were 77,866 and 19,467 in an 80:20 ratio, respectively. The AUC score for MACE with ANN was 0.97, which was greater than RF (0.96) and LR (0.96). Similarly, the precision-recall curve for MACE utilizing ANN was greater (0.94 vs. 0.93 for RF and 0.93 for LR). The sensitivity for MACE prediction using ANN, RF, and LR classifiers was 99.3%, 99.4%, and 99.2%, respectively, with the specificities being 94.5%, 94.2%, and 94.2%, respectively. CONCLUSION: When triage data is used to predict MACE, death, and cardiac arrest, ANN with systemic grid search gives precise and valid outcomes and will benefit in predicting MACE in emergency rooms with limited resources that have to deal with a substantial number of patients.
