Machine learning algorithms and traditional statistical models for detection of dementia: a population-based study.
Background Early detection of dementia can facilitate timely therapeutic interventions to mitigate the disease progression. We evaluate the performance of machine learning algorithms and traditional logistic regression (LR) model in diagnosing dementia amongst a rural Chinese older population. Metho...
| Publicado en: | Age & Ageing Vol. 54; no. 12; pp. 1 - 10 |
|---|---|
| Autores principales: | , , , , , , , , , |
| Formato: | Artículo |
| Publicado: |
Oxford University Press / USA
Dec2025
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=190592502&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 190592502 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 00020729 AGA jtl: Age & Ageing issn: 00020729 maglogo: N pubinfo: dt: Dec2025 vid: 54 iid: 12 pid: 622 pub: Oxford University Press / USA artinfo: ui: 190592502 10.1093/ageing/afaf085 ppf: 1 ppct: 9 formats: tig: atl: Machine learning algorithms and traditional statistical models for detection of dementia: a population-based study. aug: au: Li, Yuqi Hou, Tingting Dong, Jiaqi Liu, Cuicui Tian, Na Zhu, Min Dong, Yi Wang, Jiafeng Zhang, Guoqing Song, Lin affil: Department of Neurology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, China su: China Cross-sectional method Interviewing Classification of mental disorders Decision making Rural population Old age Diagnosis of dementia Statistical models Predictive tests Random forest algorithms Boosting algorithms Receiver operating characteristic curves Logistic regression analysis Probability theory Questionnaires Descriptive statistics Routine diagnostic tests Longitudinal method Machine learning Comparative studies Confidence intervals Data analysis software Algorithms Sensitivity & specificity (Statistics) sug: subj: Cross-sectional method Interviewing Classification of mental disorders Decision making Rural population Old age China Diagnosis of dementia Statistical models Predictive tests Random forest algorithms Boosting algorithms Receiver operating characteristic curves Logistic regression analysis Probability theory Questionnaires Descriptive statistics Routine diagnostic tests Longitudinal method Machine learning Comparative studies Confidence intervals Data analysis software Algorithms Sensitivity & specificity (Statistics) keyword: area under the curve (AUC) calibration plot decision curve analysis (DCA) dementia diagnostic model machine learning (ML) older people area under the curve (AUC) calibration plot decision curve analysis (DCA) dementia diagnostic model machine learning (ML) older people ab: Background Early detection of dementia can facilitate timely therapeutic interventions to mitigate the disease progression. We evaluate the performance of machine learning algorithms and traditional logistic regression (LR) model in diagnosing dementia amongst a rural Chinese older population. Methods In this population-based study, predictors for dementia in LR model were screened using the least absolute shrinkage and selection operator regression. We implemented random forest (RF) and eXtreme Gradient Boosting (XGBoost) models. We used isotonic regression for probability recalibration, the area under the receiver operating characteristic curve (AUC) and calibration plots to assess the model performance, and the decision curve analysis (DCA) to assess clinical usefulness of the models. Results Of the 5200 participants (mean age = 71.0 years, 57.1% females), 302 (5.8%) were diagnosed with dementia. The AUC of LR, RF and XGBoost models for detecting dementia were 0.88 [95% confidence interval (CI): 0.85–0.91], 0.88 (0.84–0.90) and 0.95 (0.94–0.98), respectively, in the validation set (n = 2080). Calibration plots and Brier scores showed that in the validation set, the three models had good overall alignment between the actual and predicted risks. The DCA showed better net benefit of the three models than the intervention for all or no intervention. Conclusion We developed and evaluated the performance of LR, RF and XGBoost models for dementia detection in a rural older population in China. All the three models showed excellent discrimination and calibration. The XGBoost model exhibited the best performance and clinical utility in dementia detection. These models are based on information readily available in routine clinical practice, which could be easily implemented amongst rural older populations for dementia detection. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|