Comprehensive Machine Learning-Based Prediction Model for Delirium Risk in Older Patients with Dementia: Risk Factors Identification

Topic: Risk, prevention and care in population studies

The final analysis included 636 older dementia patients, with a mean age of 78.2 ± 6.3 years, of whom 187 (29.4%) developed delirium during hospitalization. The XGB model demonstrated the best performance, achieving the highest area under the receiver operating characteristic curve (0.930), accuracy (0.870), F1 score (0.892), and area under the precision-recall curve (0.989). The Brier score for the XGB model was 0.08. The SHAP method identified cerebrovascular disease, sedative drug use, hemoglobin levels, VAS score ≥4, superoxide dismutase, diabetes, hsCRP, hypertension, family presence, and hyperlipidemia as the most significant risk factors for delirium. The top 10 variables were used to construct a compact XGB model, which also exhibited good predictive performance. This study developed a machine learning-based prediction model for delirium risk in older dementia patients, with the XGB model demonstrating the best performance. The identified key risk factors provide insights for early intervention, potentially improving delirium management in clinical practice.

Key findings

• The final analysis included 636 older dementia patients, with a mean age of 78.2 ± 6.3 years, of whom 187 (29.4%) developed delirium during hospitalization.
• The XGB model demonstrated the best performance, achieving the highest area under the receiver operating characteristic curve (0.930), accuracy (0.870), F1 score (0.892), and area under the precision-recall curve (0.989).
• The Brier score for the XGB model was 0.08.
• The SHAP method identified cerebrovascular disease, sedative drug use, hemoglobin levels, VAS score ≥4, superoxide dismutase, diabetes, hsCRP, hypertension, family presence, and hyperlipidemia as the most significant risk factors for delirium.
• The top 10 variables were used to construct a compact XGB model, which also exhibited good predictive performance.

Why it matters

Among 636 older dementia patients, a machine learning model predicted delirium during hospitalization with an area under the curve of 0.930, and identified risk factors such as cerebrovascular disease, sedative drug use, and hemoglobin levels. This concerns delirium risk in people who already have dementia and does not treat, cure, or prevent Alzheimer's disease.

New to this subject? Start with our plain-English guide: Digital health →

Study details

• Participants636
• Effect size29.4%
• Evidence strengthLow

Read the original

• DOI: 10.2147/cia.s519366
• PubMed: 40395694
• Original source →
• Free full text: Clinical Interventions in Aging →

Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).

@article{xiao2025-40395694,
  author  = {Xiao, Qifan and Zhou, Shirui and Tang, Bin and Zhu, Yuqing},
  title   = {{Comprehensive Machine Learning-Based Prediction Model for Delirium Risk in Older Patients with Dementia: Risk Factors Identification}},
  journal = {Clinical Interventions in Aging},
  year    = {2025},
  doi     = {10.2147/cia.s519366},
  pmid    = {40395694},
  url     = {https://doi.org/10.2147/cia.s519366}
}

Studies this one cites

Referenced by this study and also in the alzhub library, so you can read them here.

• Delirium and incident dementia in hospital patients in New South Wales, Australia: retrospective cohort study BMJ · 2024-03-27 · usefulness score 72/100 · Prevention and risk

Related studies in Digital health tools

• Machine-learning-based COVID-19 mortality prediction model and identification of patients at low and high risk of dying Critical care (London, England) · 2021-09-08 · usefulness score 55/100
• Prediction of Postoperative Delirium in Geriatric Hip Fracture Patients: A Clinical Prediction Model Using Machine Learning Algorithms Geriatric orthopaedic surgery & rehabilitation · 2021-12-13 · usefulness score 52/100
• Machine Learning to Develop and Internally Validate a Predictive Model for Post-operative Delirium in a Prospective, Observational Clinical Cohort Study of Older Surgical Patients Journal of general internal medicine · 2020-10-19 · usefulness score 65/100
• Development of a novel dementia risk prediction model in the general population: A large, longitudinal, population-based machine-learning study EClinicalMedicine · 2022-09-23 · usefulness score 69/100
• A Risk Prediction Model Based on Machine Learning for Cognitive Impairment Among Chinese Community-Dwelling Elderly People With Normal Cognition: Development and Validation Study Journal of medical Internet research · 2021-02-24 · usefulness score 60/100
• Advancing Alzheimer’s disease risk prediction: development and validation of a machine learning-based preclinical screening model in a cross-sectional study BMJ Open · 2025-02-01 · usefulness score 52/100

Similar studies

• Enhancing Delirium Prediction and Prevention in Elderly Patients Through Machine Learning-Based Analysis 2025 · Clinical safety
• The risk of delirium or dementia‐related hospitalization among individuals living with dementia after long‐term care entry: A population‐based risk prediction model 2025 · Clinical safety
• Development and Validation of a Routine Electronic Health Record-Based Delirium Prediction Model for Surgical Patients Without Dementia: Retrospective Case-Control Study 2025 · Clinical safety
• Development and Validation of a Dementia Risk Prediction Model in the General Population: An Analysis of Three Longitudinal Studies 2019 · Long-term cohort studies
• Prevalence, Risk Factors, and Impact of Delirium on Hospitalized Older Adults With Dementia: A Systematic Review and Meta-Analysis 2022 · Clinical safety
• Leveraging explainable artificial intelligence with ensemble of deep learning model for dementia prediction to enhance clinical decision support systems 2025 · Digital health tools

More on Digital health tools

• A review that covers this ground Modifiable risk factors for dementia and dementia risk profiling. A user manual for Brain Health Services-part 2 of 6 Alzheimer's research & therapy · 2021-10-11 · usefulness score 51/100
• Newest in this subject Speaker-Wise Dementia Screening fromNaturalistic Speech with Lexical Entropy, Semantic Drift, and Multimodal Fusion Research Square · 2026-10-21 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Integrating Multisource Target Evidence with Machine-Learning Potency Prediction for Alzheimer’s Disease Drug Discovery bioRxiv · 2026-10-20 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Digital health tools →