Related Experiment Video
Updated: Jun 11, 2026
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Clinical performance of an ultra-brief delirium screening tool in hospitalized older adults
M M L Fochi1,2, I M Suetugo3, V B Villar3
1Faculdade de Medicina de São José do Rio Preto - FAMERP, São José do Rio Preto, SP, Brazil. mariana.fochi@edu.famerp.br.
Introduction:
Delirium is a clinical syndrome that frequently occurs in hospitalized patients, especially in the elderly and is associated with worse clinical outcomes. However, delirium remains underdiagnosed by healthcare teams. Standardized assessments increase the chance of identifying the condition. The Ultra-Brief 2-item Screener (UB-2) is an effective tool for rapid screening for delirium. Considering the importance, the main objective of this study is to validate the UB-2 evaluate its performance as a screening tool in real-world public healthcare settings.
Method:
This study included patients aged 65 years or older. Within the first 48 h after hospital admission, patients were assessed using the UB-2 by a trained evaluator to screen for delirium. At another time, a second evaluator applied the Confusion Assessment Method (CAM). The two tools were applied with a maximum interval of six hours between applications. Evaluators were blinded to the results of the other assessment tools.
Results:
97 patients met the criteria for the study. Considering CAM-control as a reference, the UB-2 test had a sensitivity of 87.1% and specificity of 87.9%. The positive predictive value was 0.77 (95% CI: 0.60-0.90), and the negative predictive value was 0.94 (95% CI: 0.84-0.98). Furthermore, the positive likelihood ratio was 7.19 (95% CI: 3.70-13.95), whereas the negative likelihood ratio was 0.15 (95% CI: 0.06-0.37).
Conclusion:
The UB-2 as a delirium screening tool appears to be feasible for clinical practice, and applicable in public healthcare setting of an middle-income country.
