clinical study

Decreased Hospital Length of Stay for ICH and PE after Adoption of an Artificial Intelligence-Augmented Radiological Worklist Triage System

Materials & Methods

A longitudinal interventional study assessing differences between length of stay (LoS) for inpatients diagnosed with ICH or PE before and after implementation of AI triage software (Aidoc).  All patient non-contrast head computed tomography (CT) or CT chest angiogram (CTCA) procedures from April 2016 to April 2019 were included for ICH and PE. Three separate control groups were defined: (i) all remaining patients that underwent the designated imaging studies; (ii) patients diagnosed with hip fractures; and (iii) all hospital-wide encounters during the study period. 


ICH demonstrated an 11.9% (1.30 days) percentage decrease in LoS post-Aidoc implementation. PE demonstrated a 26.3% (2.07 days) percentage decrease in LoS post-Aidoc implementation. Control groups included all patients undergoing the same imaging, patients diagnosed with hip fractures (selected due to similar acuity and treatment-related factors), and all hospital-wide patient encounters. None of which showed clinically meaningful or significant decreases in length of stay.


The introduction of computer-aided triage and prioritization software into the radiological workflow was associated with a significant decrease in length of stay for patients diagnosed with ICH and PE.