JMIR Publications

ABSTRACT

Background:

Delirium is a complex neuropsychiatric syndrome whose severe and lasting consequences in hospitalized patients are largely considered preventable. Prevention relies primarily on the early identification of high-risk patients prior to syndrome onset. However, this remains challenging in clinical practice due to the absence of a diagnostic gold standard and the considerable administrative burden associated with established screening tools such as the 4AT score.

Objective:

The aim of this study is to compare the 4AT score with an established AI-supported prognostic tool in applied clinical practice. Our goal is to demonstrate that shifting from a purely diagnostic approach toward AI-supported delirium risk prediction enables more efficient clinical workflows, reduces misclassification rates, facilitates earlier and more targeted interventions, and ultimately improves long-term patient outcomes.

Methods:

A total of 2002 patients from a trauma ward were screened and assessed for delirium risk using the 4AT score and the AI tool at admission, on the evening of admission, and on the following day. The AI tool based its predictions on clinical data automatically derived from electronic health records.

Results:

Of the 2002 processed patients, the AI prediction tool correctly predicted 87.3% (165 of 189) of patients with delirium onset as at-risk, compared to 28.0% (53 of 189) early detection rate achieved by the 4AT score. Moreover, the AI tool correctly classified 73.9% (1340 of 1813) non-delirium patients as not-at-risk, compared to 96.3% (1746 of 1813) for the 4AT score. Therefore, the AI tool achieved very good delirium predictions, with an area under the curve (AUROC) of 0.884 (95% CI: 0.8634 - 0.9039).

Conclusions:

The AI prediction tool demonstrates substantially better performance in detecting patients’ delirium risk, when compared to an established screening tool. The AI-tool enables proactive risk management and targeted risk reduction.