Home › Research › How common it is
Development and validation of a novel predictive model for dementia risk in middle-aged and elderly depression individuals: a large and longitudinal machine learning cohort study
Xuan Xiao, Yihui Li, Qiaoboyang Wu, Xinting Liu, Xu Cao, Maiping Li, Jing Liu, Lianggeng Gong et al.. Alzheimer s Research & Therapy, 2025-05-13
Topic: Risk, prevention and care in population studies
During a median follow-up of 7.98 years, 896 incident dementia cases were identified among study participants. In model development employing an 8:2 data split (fivefold cross-validation for training), the Adaboost classifier achieved the optimal performance (AUC 0.861 ± 0.003), followed by XGBoost (AUC 0.839 ± 0.005) and CatBoost (AUC 0.828 ± 0.007) classifiers. To facilitate community generalization and clinical applicability, we develop a simplified model through a forward feature subset selection algorithm, retaining 12 variables. The simplified model maintained robust performance, with AdaBoost achieving the highest discriminative ability (AUC 0.859 ± 0.002), followed by XGBoost (AUC 0.835 ± 0.001) and CatBoost (AUC 0.821 ± 0.005). The DeLong's test revealed no statistically significant difference in AUC values between models using 12 and 27 variables (p = 0.278). For practical implementation, we deployed the optimal model to a web application for visualization and dementia risk assessment, named DRP-Depression. We developed a practical and easy-to-promote risk prediction model based on machine learning algorithms, and deployed it to a web application to provide a new and convenient tool for dementia risk prediction in the middle-aged and elderly individuals with depression.
Key findings
- During a median follow-up of 7.98 years, 896 incident dementia cases were identified among study participants.
- In model development employing an 8:2 data split (fivefold cross-validation for training), the Adaboost classifier achieved the optimal performance (AUC 0.861 ± 0.003), followed by XGBoost (AUC 0.839 ± 0.005) and CatBoost (AUC 0.828 ± 0.007) classifiers.
- To facilitate community generalization and clinical applicability, we develop a simplified model through a forward feature subset selection algorithm, retaining 12 variables.
- The simplified model maintained robust performance, with AdaBoost achieving the highest discriminative ability (AUC 0.859 ± 0.002), followed by XGBoost (AUC 0.835 ± 0.001) and CatBoost (AUC 0.821 ± 0.005).
- The DeLong's test revealed no statistically significant difference in AUC values between models using 12 and 27 variables (p = 0.278).
Why it matters
This study developed and validated a machine learning model, deployed as a web application, to predict dementia risk in middle-aged and elderly people with depression. It is a risk prediction tool and does not test any treatment, cure, or prevention.
New to this subject? Start with our plain-English guide: Alzheimer's in numbers →
Study details
- Study designprospective cohort
- Participants31,587
- Effect sizeAUC 0.861; AUC 0.839; AUC 0.828
- Evidence strengthModerate
How this study scored 60/100
Published in a peer-reviewed journal, and it is a prospective cohort study, followed forward from enrollment. Scored zero for randomised / blinded because the record does not state it.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (Alzheimer s Research & Therapy) |
| Journal's citation record | 1 / 4 | Alzheimer s Research & Therapy: journal h-index 146 (OpenAlex, 2026-10-29) |
| Study design | 7 / 12 | A prospective cohort study, followed forward from enrollment |
| Strength of evidence | 3 / 5 | Rated “moderate” in our summary |
| Peer-review validation | 10 / 10 | Peer-reviewed. Published as an article in a named peer-reviewed journal. |
| How recent | 4 / 5 | 2025 — within 3 year(s) of the newest study here |
| Sample size | 4 / 4 | 31,587 participants |
| Effect reported | 3 / 3 | Effect reported with a statistic (interval, p-value, ratio or similar) |
| Studied in people | 3 / 3 | Studied in people (participant count stated) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 3 / 7 | Cited 23 times (OpenAlex, 2026-10-10) |
| Citations per year | 2 / 5 | 7.7 citations a year over 3 year(s) since 2025 |
| Impact for its field and year | 4 / 6 | Cited 14.6× the average for papers of its field and year (OpenAlex FWCI) |
| Cited by studies here | 0 / 6 | No other study in this library cites it |
| Still being cited | 2 / 4 | Cited 23 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 2 / 4 | Last-listed author Xi‐jian Dai: h-index 23 (OpenAlex, whole career) |
| Institution's track record | 0 / 3 | Nanchang University: institution h-index 361 (OpenAlex) |
| Multi-centre collaboration | 1 / 3 | OpenAlex lists 2 institution(s) in 1 country |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 40361211) |
| Free to read | 2 / 2 | Free to read |
| Total | 60 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
- DOI: 10.1186/s13195-025-01750-6
- PubMed: 40361211
- Original source →
- Free full text: Alzheimer s Research & Therapy →
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. The record's author list ends in “et al.”, so not every author is named. Check the citation against the original before you use it.
APA 7th
Xiao, X., Li, Y., Wu, Q., Liu, X., Cao, X., Li, M., et al. (2025). Development and validation of a novel predictive model for dementia risk in middle-aged and elderly depression individuals: a large and longitudinal machine learning cohort study. Alzheimer s Research & Therapy. https://doi.org/10.1186/s13195-025-01750-6
Vancouver
Xiao X, Li Y, Wu Q, Liu X, Cao X, Li M, et al. Development and validation of a novel predictive model for dementia risk in middle-aged and elderly depression individuals: a large and longitudinal machine learning cohort study. Alzheimer s Research & Therapy. 2025. doi:10.1186/s13195-025-01750-6. PMID: 40361211.
BibTeX
@article{xiao2025-40361211,
author = {Xiao, Xuan and Li, Yihui and Wu, Qiaoboyang and Liu, Xinting and Cao, Xu and Li, Maiping and Liu, Jing and Gong, Lianggeng and others},
title = {{Development and validation of a novel predictive model for dementia risk in middle-aged and elderly depression individuals: a large and longitudinal machine learning cohort study}},
journal = {Alzheimer s Research \& Therapy},
year = {2025},
doi = {10.1186/s13195-025-01750-6},
pmid = {40361211},
url = {https://doi.org/10.1186/s13195-025-01750-6}
}
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here. Showing 12 of 19.
Related studies in How common it is
Also tagged “biobank”
1,084 studies in the library carry the topic tag “biobank”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 1,084 tagged studies.