Background: Prolonged intensive care unit (ICU) stays are associated with increased morbidity, resource utilization, and cost. Early identification of patients at risk for extended ICU length of stay (LOS) can support clinical decision-making and improve resource management. Objective: To develop and evaluate a machine learning model to predict ICU LOS using routine laboratory tests available early during admission. Methods: We conducted a retrospective study using electronic health record data from adult ICU patients. Evaluated the predictive performance of four machine learning (ML) models to choose the best model, which was trained on a set of demographic and laboratory tests’ results to predict LOS category. Model performance was assessed using accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, and specificity on a validation set. Results: The XGBoost model demonstrated the highest accuracy (90%) and Kappa (79%) among the four evaluated models. On the testing data, XGBoost had an accuracy of 87.5%, sensitivity 88%, specificity 87.1%, and AUC of 95.3%. The top five important predictor variables were blood glucose, arterial partial pressure of oxygen (PaO2), arterial partial pressure of carbon dioxide (PaCO2), body mass index (BMI), and age. Diagnostic accuracy measures on the validation data were: Accuracy = 83.9%, sensitivity = 79.4%, specificity = 88%, and AUC = 92.5% Conclusion: Machine learning can effectively predict ICU length of stay early in the course of admission. Such models could aid clinicians in identifying patients at risk for prolonged ICU stays, facilitating proactive discharge planning and ICU resource optimization. Future studies should focus on external validation and real-world implementation.
Timely thrombolytic therapy is vital for acute ischemic stroke and STEMI, as delays increase tissue damage, worsen recovery, and raise mortality. A 24×7 thrombolysis service within the Emergency Department can reduce door-to-needle times, improve access in resource-limited settings, and enhance outcomes. This review highlights the rationale, epidemiology, clinical evidence, infrastructure, training, implementation, cost-effectiveness, barriers, and future directions. A model for Uttar Pradesh is proposed, focusing on ED integration, task-sharing, point-of-care diagnostics, a “one-room unit,” and robust monitoring, governance, and research linkages, tailored to the Indian context.
Diastolic dysfunction is a common manifestation of sepsis-associated cardiomyopathy and has been associated with poorer outcomes in critically ill patients; however, the factors that contribute to its development during septic shock are not fully defined. This study aimed to determine the association between cumulative fluid balance and diastolic dysfunction in patients with septic shock admitted to the ICU. An observational, prospective, longitudinal, and analytical study was conducted that included 55 adult patients with a diagnosis of septic shock. Cumulative fluid balance and diastolic function were assessed by critical echocardiography using the E/A ratio at admission, 24, and 72 hours. The statistical analysis included descriptive and analytical methods; ROC curves and relative risk calculation were used. It was identified that 40% of the patients had diastolic dysfunction. The most frequent infectious process was abdominal (60%), followed by pulmonary (32.7%). A positive and significant correlation was observed between the accumulated water balance and the mitral E/A ratio at all times evaluated (admission: r=0.531; 24 h: r=0.560; 72 h: r=0.466; p<0.001). The relative risk of diastolic dysfunction increased with water balance: 5.4 times the risk at admission, 8.8 at 24 h, and 13.9 at 72 h. In conclusion, the risk of developing diastolic dysfunction consistently increases with the increase in accumulated water balance.
