Related Experiment Video
Updated: May 15, 2025
Multi-Modal Home Sleep Monitoring in Older Adults
Published on: January 26, 2019
Development and validation of a polysomnography-based nomogram for predicting amnestic mild cognitive impairment in
Shunjie Liu1, Chuncao Ao2, Zheliang Li2
1Department of Neurology, Zhujiang Hospital, Southern Medical University, Guangzhou, 510282, China; Shenzhen Research Institute of Sun Yat-Sen University, Shenzhen, 518000, China; Department of Neurology, The Second People's Hospital of Foshan, Foshan, 528000, China.
Background:
Amnestic mild cognitive impairment (aMCI) is a subtype of mild cognitive impairment (MCI) that is considered an early stage of Alzheimer's disease (AD). Although early identification of aMCI is crucial for mitigating disease progression, objective and economic evaluation tools designed for aMCI prediction are lacking. Hence, we aimed to develop and validate a novel nomogram based on sleep characteristics to predict the risk of aMCI in middle-aged and elderly adults.
Methods:
This study included 817 eligible participants who underwent polysomnography (PSG), comprising 339 individuals diagnosed with aMCI. The participants were divided into a training cohort and a validation cohort using a 7:3 random split. Least absolute shrinkage and selection operator (LASSO) regression was employed to identify key predictive factors, followed by multivariable logistic regression to refine the predictors, which were subsequently used to construct a nomogram. The predictive performance of the nomogram was evaluated through receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA).
Results:
Among the 30 potential predictors, 9 independent sleep-related predictors were incorporated into the final nomogram: total sleep time (TST), sleep efficiency (SE), the proportions of nonrapid eye movement stage 1 (N1), nonrapid eye movement stage 3 (N3), and rapid eye movement (REM) sleep, the density and amplitude of fast spindles and the density and amplitude of K-complexes (KCs). The nomogram demonstrated excellent discriminative ability, with an area under the curve (AUC) of 0.968 in the training cohort and 0.953 in the validation cohort. Calibration curves indicated strong agreement between the predicted and observed outcomes, and DCA confirmed the clinical usefulness of the nomogram by showing consistent net benefits across a wide range of threshold probabilities.
Conclusion:
In this study, we developed and validated an innovative nomogram based on objective sleep characteristics to predict aMCI risk. By reducing the reliance on subjective or costly diagnostic tools, the nomogram offers a reliable, accessible, and practical method for the early identification of aMCI.
Insights
A novel nomogram using sleep characteristics can predict the risk of amnestic mild cognitive impairment (aMCI). This tool offers a practical and accessible method for early aMCI identification, aiding in Alzheimer's disease (AD) progression mitigation.
Area of Science:
- Neurology
- Sleep Medicine
- Gerontology
Background:
- Amnestic mild cognitive impairment (aMCI) is an early stage of Alzheimer's disease (AD).
- Early identification of aMCI is critical for managing disease progression.
- Objective and economical tools for aMCI prediction are currently lacking.
Purpose of the Study:
- To develop and validate a novel nomogram for predicting aMCI risk.
- To utilize objective sleep characteristics as predictive factors.
- To provide an accessible tool for early aMCI detection in middle-aged and elderly adults.
Main Methods:
- 817 participants (339 with aMCI) underwent polysomnography (PSG).
- Data split into training (70%) and validation (30%) cohorts.
- LASSO and logistic regression identified key sleep predictors for nomogram construction.
Main Results:
- A nomogram incorporating 9 sleep predictors (e.g., TST, SE, N1, N3, REM, spindle, and KCs characteristics) was developed.
- The nomogram showed excellent predictive performance (AUC: 0.968 training, 0.953 validation).
- Calibration curves and DCA confirmed strong agreement and clinical utility.
Conclusions:
- An innovative nomogram based on objective sleep characteristics effectively predicts aMCI risk.
- This tool reduces reliance on subjective or costly diagnostics.
- The nomogram provides a reliable, accessible, and practical method for early aMCI identification.
