Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Sep 17;7(3):ooae091.
doi: 10.1093/jamiaopen/ooae091. eCollection 2024 Oct.

Machine learning-based delirium prediction in surgical in-patients: a prospective validation study

Stefanie Jauk  1   2 , Diether Kramer  1   2 , Stefan Sumerauer  3 , Sai Pavan Kumar Veeranki  1   2 , Michael Schrempf  2 , Paul Puchwein  4
Affiliations

Machine learning-based delirium prediction in surgical in-patients: a prospective validation study

Stefanie Jauk et al. JAMIA Open. .

Abstract

Objective: Delirium is a syndrome that leads to severe complications in hospitalized patients, but is considered preventable in many cases. One of the biggest challenges is to identify patients at risk in a hectic clinical routine, as most screening tools cause additional workload. The aim of this study was to validate a machine learning (ML)-based delirium prediction tool on surgical in-patients undergoing a systematic assessment of delirium.

Materials and methods: 738 in-patients of a vascular surgery, a trauma surgery and an orthopedic surgery department were screened for delirium using the DOS scale twice a day over their hospital stay. Concurrently, delirium risk was predicted by the ML algorithm in real-time for all patients at admission and evening of admission. The prediction was performed automatically based on existing EHR data and without any additional documentation needed.

Results: 103 patients (14.0%) were screened positive for delirium using the DOS scale. Out of them, 85 (82.5%) were correctly identified by the ML algorithm. Specificity was slightly lower, detecting 463 (72.9%) out of 635 patients without delirium. The AUROC of the algorithm was 0.883 (95% CI, 0.8523-0.9147).

Discussion: In this prospective validation study, the implemented machine-learning algorithm was able to detect patients with delirium in surgical departments with high discriminative performance.

Conclusion: In future, this tool or similar decision support systems may help to replace time-intensive screening tools and enable efficient prevention of delirium.

Keywords: clinical decision support; delirium; electronic health records; prediction algorithms; random forest.

PubMed Disclaimer

Conflict of interest statement

D.K. is CEO and co-founder of the start-up PH Predicting Health GmbH. S.J., S.P.K.V., and M.S. are employees of aforementioned company. Predicting Health aims to commercialize the software described. The other authors declare no conflict of interest.

Figures

Figure 1.
Figure 1.
Agreement between DOS results and EHR documentation for 110 patients. 103 patients were rated as DOS positive, 7 patients had a documentation of delirium in the EHR system (psychiatric consultation indicating delirium or discharge diagnosis for delirium).
Figure 2.
Figure 2.
(A) Discriminative performance illustrated with an ROC curve and (B) calibration plot for all patients included in the study (n = 738).
See this image and copyright information in PMC

References

    1. Leigheb M, de Sire A, Zeppegno P, et al. Delirium risk factors analysis post proximal femur fracture surgery in elderly. Acta Biomed Atenei Parm. 2022;92:e2021569. - PMC - PubMed
    1. Bruce AJ, Ritchie CW, Blizard R, et al. The incidence of delirium associated with orthopedic surgery: a meta-analytic review. Int Psychogeriatr. 2007;19:197-214. - PubMed
    1. Kat MG, de Jonghe JF, Vreeswijk R, et al. Mortality associated with delirium after hip-surgery: a 2-year follow-up study. Age Ageing. 2011;40:312-318. - PubMed
    1. Inouye SK, Westendorp RG, Saczynski JS.. Delirium in elderly people. Lancet. 2014;383:911-922. - PMC - PubMed
    1. Boogaard M V D, Pickkers P, Slooter AJC, et al. Development and validation of PRE-DELIRIC (PREdiction of DELIRium in ICu patients) delirium prediction model for intensive care patients: observational multicentre study. BMJ. 2012;344:e420. - PMC - PubMed

LinkOut - more resources