Clinical Research Directory

Comparison of NEWS2 and Machine Learning for Early Sepsis Warning

This prospective observational study aims to objectively measure the lead-time (the time from the first KDS alert to sepsis diagnosis) of the NEWS2-based clinical decision support system (KDS) and compare its early warning performance with a machine learning model trained on 2000 patients and externally validated. The study seeks to answer the following main questions: How early does the NEWS2-based KDS provide an alert before sepsis diagnosis? Does a machine learning model, developed using logistic regression and externally validated in a prospective cohort, offer superior specificity and comparable sensitivity to KDS? Participants who are already receiving routine clinical care at Kocaeli City Hospital will have their vital signs and laboratory data monitored as part of standard practice. NEWS2 scores will be calculated automatically and the time of the first alert (T0) will be recorded. Sepsis diagnosis will be confirmed by an increase in SOFA score ≥ 2 (T1), evaluated by two independent and blinded physicians. Lead-time will be calculated as the difference between T1 (hours×60) and T0 (minutes). The machine learning model will be tested prospectively on this cohort, and its performance will be compared with KDS using sensitivity, specificity, F1 score, ROC-AUC, and accuracy.

Predictive Performance of NEWS-2 and NEWS-Calcium Scores for In-Hospital Mortality in Older Patients With Acute Pancreatitis

Acute pancreatitis is an important gastrointestinal emergency that may lead to mortality, particularly in older patients. This retrospective, single-center observational prognostic validation study aims to compare the predictive performance of the National Early Warning Score 2 (NEWS-2) and NEWS-Calcium scores for in-hospital mortality in patients aged 65 years and older diagnosed with acute pancreatitis in the emergency department. Electronic medical records of eligible patients will be reviewed retrospectively. Demographic characteristics, vital signs, serum calcium levels, clinical outcomes, intensive care unit admission, organ failure, length of hospital stay, and in-hospital mortality will be recorded. NEWS-2 will be calculated using vital parameters at admission, while the NEWS-Calcium score will be obtained by adding a calcium-based score to NEWS-2. The primary outcome will be in-hospital mortality. Secondary outcomes will include intensive care unit admission, severe acute pancreatitis, persistent organ failure, and length of hospital stay. The predictive performances of the scores will be compared using ROC curve analysis, AUC values, and the DeLong test. This study aims to identify the most appropriate early prognostic score for older patients with acute pancreatitis and to support clinical decision-making in emergency settings.