Volume 10,Issue 9
Systematic Review of Delirium Risk Prediction Models in Adult ICU Patients
Objective: To systematically retrieve and evaluate delirium risk prediction models in adult intensive care unit (ICU) patients and provide evidence for model optimization and clinical practice. Methods: A systematic literature search was conducted in PubMed, Web of Science, Embase, Cochrane Library, CINAHL, CNKI, Wanfang Data, VIP, and CBM databases from inception to August 2025. Two independent researchers performed literature screening, data extraction, and quality assessment. Results: Seventeen studies involving 18 prediction models were included, with sample sizes ranging from 100 to 8,878 cases and outcome events from 21 to 4,431 cases. The area under curve (AUC) for model development ranged from 0.732 to 0.941. Twelve models reported calibration, 10 studies performed internal validation, and 6 studies conducted external validation. Overall applicability of the 17 studies was acceptable. The final models contained 3-15 predictors; however, all models exhibited high risk of bias. Conclusion: Existing models generally demonstrated acceptable discrimination, but were associated with high risk of bias, with insufficient evidence regarding external validation, calibration assessment, and clinical implementation. Future studies should strictly follow the PROBAST criteria, standardize procedures for model development and validation, improve model stability and clinical application value, and provide reliable evidence for clinical decision-making.
[1] American Geriatrics Society, 2015, Abstracted Clinical Practice Guideline for Postoperative Delirium in Older Adults. Journal of the American Geriatrics Society, 63(1): 142–150.
[2] Stollings J, Kotfis K, Chanques G, et al., 2021, Delirium in Critical Illness: Clinical Manifestations, Outcomes, and Management. Intensive Care Medicine, 47(10): 1089–1103.
[3] Wilcox M, Girard T, Hough C, 2021, Delirium and Long Term Cognition in Critically Ill Patients. BMJ (Clinical Research Ed), 373: n1007.
[4] Vickers A, Holland F, 2021, Decision Curve Analysis to Evaluate the Clinical Benefit of Prediction Models. The Spine Journal: Official Journal of the North American Spine Society, 21(10): 1643–1648.
[5] Wolff R, Moons K, Riley R, et al., 2019, PROBAST: A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies. Annals of Internal Medicine, 170(1): 51–58.
[6] Chen X, Zhang Y, Zhuang Y, et al., 2020, PROBAST: An Assessment Tool for Risk of Bias in Diagnostic or Prognostic Multivariable Prediction Model Studies. Chinese Journal of Evidence-Based Medicine, 20(6): 737–744.
[7] Sosa F, Roberti J, Franco M, et al., 2018, Assessment of Delirium Using the PRE-DELIRIC Model in an Intensive Care Unit in Argentina. Revista Brasileira de Terapia Intensiva, 30(1): 50–56.
[8] Chen D, Yang X, 2025, Developing a Nomogram to Predict the Risk of Delirium in ICU Patients: A Retrospective Cohort Study. Risk Management and Healthcare Policy, 18: 3221–3233.
[9] Fan H, Ji M, Huang J, et al., 2019, Development and Validation of a Dynamic Delirium Prediction Rule in Patients Admitted to the Intensive Care Units (DYNAMIC-ICU): A Prospective Cohort Study. International Journal of Nursing Studies, 93: 64–73.
[10] Moon K, Jin Y, Jin T, et al., 2018, Development and Validation of an Automated Delirium Risk Assessment System (Auto-DelRAS) Implemented in the Electronic Health Record System. International Journal of Nursing Studies, 77: 46–53.
[11] Cherak S, Soo A, Brown K, et al., 2020, Development and Validation of Delirium Prediction Model for Critically Ill Adults Parameterized to ICU Admission Acuity. PLoS One, 15(8): e0237639.
[12] Van Den Boogaard M, Pickkers P, Slooter A, et al., 2012, Development and Validation of PRE-DELIRIC (PREdiction of DELIRium in ICu Patients) Delirium Prediction Model for Intensive Care Patients: Observational Multicentre Study. BMJ (Clinical Research Ed), 344: e420.
[13] Chen Y, Du H, Wei B, et al., 2017, Development and Validation of Risk-Stratification Delirium Prediction Model for Critically Ill Patients: A Prospective, Observational, Single-Center Study. Medicine, 96(29): e7543.
[14] Wang M, Kuo Y, Kuo L, et al., 2023, Early Prediction of Delirium Upon Intensive Care Unit Admission: Model Development, Validation, and Deployment. Journal of Clinical Anesthesia, 88: 111121.
[15] Dai X, Xing Y, Guo D, et al., 2024, Construction and Application of Delirium Risk Prediction Model for ICU Patients with Respiratory Failure on Mechanical Ventilation. Heilongjiang Medical Journal, 48(5): 624–626.
[16] Zhang H, Gan X, Zhou W, et al., 2024, Construction and Validation of Dynamic Nomogram Prediction Model for Hypoactive Delirium Risk in ICU Patients. Chinese Journal of Critical Care & Emergency Nursing, 5(6): 485–492.
[17] Zhu X, 2017, Analysis of Risk Factors for ICU Delirium and Construction of Risk Prediction Model, thesis, Third Military Medical University.
[18] Shen X, Ma P, Feng G, et al., 2023, Analysis of Risk Factors and Prediction Model for Delirium in Critically Ill ICU Patients. China Modern Doctor, 61(4): 45–49.
[19] Wassenaar A, Van Den Boogaard M, Van Achterberg T, et al., 2015, Multinational Development and Validation of an Early Prediction Model for Delirium in ICU Patients. Intensive Care Medicine, 41(6): 1048–1056.
[20] Cao Y, Zhang M, Pan G, et al., 2023, Effectiveness and Predictive Performance of Delirium Management Model Based on E-PRE-DELIRIC Risk Stratification in Intensive Care Unit. Academic Journal of Chinese PLA Medical School, 44(5): 501–507 + 524.
[21] Zhang S, Liu L, Wu Y, 2025, Construction of Delirium Prediction Model for Middle-Aged and Elderly ICU Patients Based on Logistic Regression and Random Forest Algorithm. Journal of Nurses Training, 40(24): 2663–2670.
[22] Chang J, Ding S, Feng B, 2024, Impact of Delirium During Mechanical Ventilation on Prognosis in Elderly Patients with Severe Pneumonia and Construction of Prediction Model. Shandong Medical Journal, 64(31): 30–34.
[23] Huang B, Chen Y, Yang L, 2023, Construction and Validation of Nomogram Prediction Model for Delirium in Intensive Care Unit Patients. Chinese Evidence-Based Nursing, 9(14): 2601–2605.
[24] Song Q, Xu H, Cui H, et al., 2025, Current Status and Influencing Factors of ICU Delirium in Patients After Cardiac Surgery. Smart Healthcare, 11(12): 29–36.
[25] Shi Q, Mu X, Zhang C, et al., 2019, Risk Factors for Postoperative Delirium in Type A Aortic Dissection Patients: A Retrospective Study. Medical Science Monitor: International Medical Journal of Experimental and Clinical Research, 25: 3692–3699.
[26] Li C, Li D, Bai S, et al., 2019, Progress in Pathophysiological Mechanisms and Risk Factors Prevention and Treatment of Postoperative Delirium. Chinese Journal of Gerontology, 39(5): 1273–1277.
[27] Cortese G, Burger C, 2017, Neuroinflammatory Challenges Compromise Neuronal Function in the Aging Brain: Postoperative Cognitive Delirium and Alzheimer’s Disease. Behavioural Brain Research, 322(Pt B): 269–279.
[28] Jayaswal A, Sampath H, Soohinda G, et al., 2019, Delirium in Medical Intensive Care Units: Incidence, Subtypes, Risk Factors, and Outcome. Indian Journal of Psychiatry, 61(4): 352–358.
[29] Reznik M, Kalagara R, Moody S, et al., 2021, Common Biomarkers of Physiologic Stress and Associations with Delirium in Patients with Intracerebral Hemorrhage. Journal of Critical Care, 64: 62–67.
[30] Bulic D, Bennett M, Rodgers H, et al., 2017, Delirium After Mechanical Ventilation in Intensive Care Units: The Cognitive and Psychosocial Assessment (CAPA) Study Protocol. JMIR Research Protocols, 6(2): e31.
[31] Gao W, Zhang Y, Jin J, 2022, Validation of E-PRE-DELIRIC in Cardiac Surgical ICU Delirium: A Retrospective Cohort Study. Nursing in Critical Care, 27(2): 233–239.
