AI-Based Delirium Risk Prediction Compared With the Validated 4AT-Score Screening Tool in Patients With Trauma: Prospective Cohort Study.
6 affiliations
- 1Department of Orthopaedics and Trauma, Medical University of Graz, Graz, Styria, Austria, 43 31638581719.
- 2Directorate for Digitalisation, IT, Organisational Development and Innovations, Styrian Hospital Holding, Graz, Austria.
- 3Department of Psychiatry, Psychosomatics and Psychotherapeutic Medicine, Medical University of Graz, Graz, Austria.
- 4Department of Neurology, Medical University of Graz, Graz, Austria.
- 5Hospital Pharmacy, University Hospital of Graz, Styrian Hospital Holding, Graz, Austria.
- 6Research Unit for Safety and Sustainability in Health Care, c/o Division of Plastic, Aesthetic and Reconstructive Surgery, Department of Surgery, Medical University of Graz, Graz, Austria.
Abstract
Background
Delirium is a complex neuropsychiatric syndrome whose severe and lasting consequences in hospitalized patients are largely considered preventable. Prevention primarily relies 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
In this prospective study, a total of 2002 patients from a trauma ward were screened and assessed for delirium risk using the 4AT score and the AI-based tool at admission, on the evening of admission, and on the following day, with each assessment predicting the risk of delirium occurrence at any point during the remainder of the hospital stay. The AI tool based its predictions on clinical data automatically derived from electronic health records. The AI-based tool applied a previously developed and validated random forest model (not developed as part of this study).Results
Of the 2002 processed patients, the AI prediction tool correctly predicted 87.3% (165/189) of patients with delirium onset as at-risk, compared to an early detection rate of 28.0% (5/189) achieved by the 4AT score. Moreover, the AI-based tool correctly classified 73.9% (1340/1813) patients without delirium as not-at-risk, compared to 96.3% (1746/1813) for the 4AT score. Therefore, the AI-based tool achieved very good delirium predictions, with an area under the receiver operating characteristic curve of 0.884 (95% CI 0.8634-0.9039).Conclusions
The AI-based delirium prognostic tool demonstrated superior early predictive capacity for delirium risk at admission, compared with the 4AT score. The AI-based tool enables proactive risk management and targeted risk reduction.
Related
- Construction and validation of a nomogram prediction model for the risk of delirium after hip arthroplasty in elderly patients
- The association of C-Reactive Protein with Delirium Severity: An analysis of a prospective cohort study
- Lower Serum SCCA2 Detectability in Chronic Spontaneous Compared with Chronic Inducible Urticaria: A Prospective Observational Study
- Population Genetic Screening of Hemoglobinopathy Carrier Prevalence Compared to Medical Records
- A prospective pilot cohort study of hydrocyn gel as a dressing agent compared with conventional flavin-based pin-site care for infection prevention
BibTeX
@article{franceschini2026aibased,
title = {{AI-Based Delirium Risk Prediction Compared With the Validated 4AT-Score Screening Tool in Patients With Trauma: Prospective Cohort Study.}},
author = {Klaus Franceschini and Marisa Valentini and Andreas Leithner and Diether Kramer and Stefanie Jauk and Lena Delia Lorenzer and Karin Hasiba-Seebacher and Stefan Sumerauer and Viktoria Christin Godschachner and Magdalena Hellauer and Gerald Sendlhofer},
journal = {JMIR formative research},
year = {2026},
month = oct,
doi = {10.2196/104907},
url = {https://europepmc.org/article/MED/42906075},
note = {CC BY},
}
RIS
TY - JOUR
TI - AI-Based Delirium Risk Prediction Compared With the Validated 4AT-Score Screening Tool in Patients With Trauma: Prospective Cohort Study.
AU - Klaus Franceschini
AU - Marisa Valentini
AU - Andreas Leithner
AU - Diether Kramer
AU - Stefanie Jauk
AU - Lena Delia Lorenzer
AU - Karin Hasiba-Seebacher
AU - Stefan Sumerauer
AU - Viktoria Christin Godschachner
AU - Magdalena Hellauer
AU - Gerald Sendlhofer
PY - 2026
DA - 2026/10/21
JO - JMIR formative research
DO - 10.2196/104907
UR - https://europepmc.org/article/MED/42906075
AB - Background Delirium is a complex neuropsychiatric syndrome whose severe and lasting consequences in hospitalized patients are largely considered preventable. Prevention primarily relies 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 In this prospective study, a total of 2002 patients from a trauma ward were screened and assessed for delirium risk using the 4AT score and the AI-based tool at admission, on the evening of admission, and on the following day, with each assessment predicting the risk of delirium occurrence at any point during the remainder of the hospital stay. The AI tool based its predictions on clinical data automatically derived from electronic health records. The AI-based tool applied a previously developed and validated random forest model (not developed as part of this study).Results Of the 2002 processed patients, the AI prediction tool correctly predicted 87.3% (165/189) of patients with delirium onset as at-risk, compared to an early detection rate of 28.0% (5/189) achieved by the 4AT score. Moreover, the AI-based tool correctly classified 73.9% (1340/1813) patients without delirium as not-at-risk, compared to 96.3% (1746/1813) for the 4AT score. Therefore, the AI-based tool achieved very good delirium predictions, with an area under the receiver operating characteristic curve of 0.884 (95% CI 0.8634-0.9039).Conclusions The AI-based delirium prognostic tool demonstrated superior early predictive capacity for delirium risk at admission, compared with the 4AT score. The AI-based tool enables proactive risk management and targeted risk reduction.
SN - 2561-326X
ER -