Internal and emergency medicine
-
Randomized Controlled Trial
Real-time machine learning-assisted sepsis alert enhances the timeliness of antibiotic administration and diagnostic accuracy in emergency department patients with sepsis: a cluster-randomized trial.
Machine learning (ML) has been applied in sepsis recognition across different healthcare settings with outstanding diagnostic accuracy. However, the advantage of ML-assisted sepsis alert in expediting clinical decisions leading to enhanced quality for emergency department (ED) patients remains unclear. A cluster-randomized trial was conducted in a tertiary-care hospital. ⋯ The diagnostic performance of ML in prompt sepsis detection was superior to that of the rule-based system. Trial registration Thai Clinical Trials Registry TCTR20230120001. Registered 16 January 2023-Retrospectively registered, https://www.thaiclinicaltrials.org/show/TCTR20230120001 .
-
Observational Study
Site and duration of abdominal pain discriminate symptomatic uncomplicated diverticular disease from previous diverticulitis patients.
Abdominal pain in patients with diverticular disease (DD) can be challenging in clinical practice. Patients with symptomatic uncomplicated diverticular disease (SUDD) and patients with a previous acute diverticulitis (PD) may share a similar clinical pattern, difficult to differentiate from irritable bowel syndrome (IBS). We used standardized questionnaires for DD (short and long lasting abdominal pain) and IBS (following Rome III Criteria) to assess clinical features of abdominal pain, in terms of presence, severity and length, in SUDD and PD patients. ⋯ SUDD and PD patients presented different pattern of abdominal pain (length, number of long lasting episodes, site and associated features), with a third reporting overlap with IBS. Further observational studies are needed to better characterize abdominal symptoms in DD patients, especially in those not fulfilling IBS criteria. Trial registration: The REMAD Registry is registered as an observational study in ClinicalTrial.gov (ID: NCT03325829).