Predicting Depression Risk in Physically Inactive Older Adults Using Dietary Antioxidants and Machine Learning: A SHAP ‐Interpretable Analysis of NHANES
Vorhersage des Depressionsrisikos bei körperlich inaktiven älteren Erwachsenen mit diätetischen Antioxidanzien und Machine Learning: eine SHAP-interpretierbare NHANES-Analyse
CNS Neuroscience & Therapeutics · 2026-06 · 32 (6)
DOI: 10.1002/cns.70961 ↗Auf einen Blick
Bei 2.496 körperlich inaktiven Erwachsenen ab 60 Jahren sagte ein Machine-Learning-Modell das Depressionsrisiko anhand von Antioxidanzien gut voraus. Das Random-Forest-Modell war am besten.
Fragestellung
Kann die Zufuhr diätetischer Antioxidanzien das Depressionsrisiko bei körperlich inaktiven Erwachsenen ab 60 Jahren vorhersagen?
Methode
Daten aus NHANES 2007–2010 und 2017–2018; 44 Antioxidanzien sowie CDAI und OBS; sechs Machine-Learning-Modelle, 10-fache Kreuzvalidierung, Bootstrap und SHAP-Analyse.
Ergebnisse
Das Random-Forest-Modell zeigte die beste Leistung: Accuracy 94,9 %, ROC-AUC 0,943, Sensitivität 99,96 %. Vitamin E, Luteolin, Gesamtflavonoide, Kupfer, Magnesium und Eisen waren die einflussreichsten Prädiktoren.
Schlussfolgerung der Autor:innen
Die Zufuhr diätetischer Antioxidanzien hatte einen deutlichen Wert für die Vorhersage des Depressionsrisikos bei körperlich inaktiven älteren Erwachsenen.
Kernaussagen
- Random Forest erzielte die beste Modellleistung
- Vitamin E, Luteolin und Flavonoide waren wichtige Prädiktoren
- Eine Online-Risikovorhersage wurde auf Basis des Modells entwickelt
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift CNS Neuroscience & Therapeutics, online erschienen am 30.05.2026. Verfasst von Yuwen ShangGuan und 6 weiteren Autor:innen. Beteiligte Einrichtung: Changzhou Maternal and Child Health Care Hospital, Changzhou Medical Center, Nanjing Medical University, Changzhou, China. Hauptthemen laut MEDLINE: Antioxidants, Machine Learning, Nutrition Surveys, Depression. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Jiangsu Health International Exchange Program(2026).
Themen: Künstliche Intelligenz in der Pflege, Gerontologische Pflege, Depression
Abstract (Originalsprache)
Background
Physically inactive older adults represent a high‐risk group for depression. However, whether dietary antioxidant intake profiles can help stratify depression risk within this population has not been well established. This study aims to evaluate the predictive ability of dietary antioxidant intake for depression risk in physically inactive adults aged 60 and older using machine learning methods.
Methods
This study utilized data from the 2007–2010 and 2017–2018 cycles of the National Health and Nutrition Examination Survey (NHANES), including 2,496 physically inactive adults aged 60 years and older. A total of 44 dietary antioxidants and two composite indices: The Composite Dietary Antioxidant Index (CDAI) and the Oxidative Balance Score (OBS) were assessed. Feature selection was performed using the random forest algorithm, followed by the development of six machine learning models: Random forest, XGBoost, k‐nearest neighbors, support vector machine, decision tree, and naïve Bayes. Model performance was evaluated using multiple metrics, including area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, F‐beta score, and area under the precision‐recall curve (PR AUC). Ten‐fold cross‐validation and bootstrap resampling were employed to validate model robustness. Additionally, Shapley Additive Explanations (SHAP) analysis was conducted to facilitate individualized risk interpretation.
Results
The random forest model demonstrated the best performance, with an accuracy of 94.9%, an ROC AUC of 0.943, and a sensitivity of 99.96%. SHAP analysis identified vitamin E, luteolin, total flavonoids, copper, magnesium, and iron as the most influential predictors, all of which showed a nonlinear inverse association with depression risk. Multivariable interaction analysis revealed synergistic protective effects between vitamin E and copper, as well as between luteolin and total flavonoids. In addition, an online risk prediction tool was developed based on the model, allowing for real‐time, personalized depression risk assessment upon input of key dietary antioxidant intake data.
Conclusions
Dietary antioxidant intake demonstrated significant value in predicting depression risk among physically inactive older adults. Key nutrients and their interactions identified through machine learning and SHAP analysis provide new evidence and practical tools for targeted nutritional interventions and early screening of depression.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Changzhou Maternal and Child Health Care Hospital, Changzhou Medical Center, Nanjing Medical University, Changzhou, China.
- Department of Exercise Physiology, Kunsan National University, Gunsan, Republic of Korea.
- School of Physical Education and Health, Zhaoqing University, Zhaoqing, China.
- Department of Global Sports Industry, Hanyang University, Seoul, Republic of Korea.
- Department of Articular Orthopedics, The First People's Hospital of Changzhou, The Third Affiliated Hospital of Soochow University, Changzhou, China.
ORCID-Profile: Zhenhao Lin, Litao Yan
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Jiangsu Health International Exchange Program(2026)
Zitieren
APA
ShangGuan, Y., Wu, K., Li, D., Sim, Y. J., Zhang, C., Lin, Z., & Yan, L. (2026). Predicting Depression Risk in Physically Inactive Older Adults Using Dietary Antioxidants and Machine Learning: A SHAP ‐Interpretable Analysis of NHANES. CNS Neuroscience & Therapeutics, 32(6). https://doi.org/10.1002/cns.70961
Vancouver
ShangGuan Y, Wu K, Li D, Sim YJ, Zhang C, Lin Z, et al. Predicting Depression Risk in Physically Inactive Older Adults Using Dietary Antioxidants and Machine Learning: A SHAP ‐Interpretable Analysis of NHANES. CNS Neuroscience & Therapeutics. 2026;32(6). doi:10.1002/cns.70961
BibTeX
@article{ShangGuan2026,
author = {ShangGuan, Yuwen and Wu, Kunpeng and Li, Dong and Sim, Young-Je and Zhang, Chuang and Lin, Zhenhao and Yan, Litao},
title = {Predicting Depression Risk in Physically Inactive Older Adults Using Dietary Antioxidants and Machine Learning: A SHAP ‐Interpretable Analysis of NHANES},
journal = {CNS Neuroscience & Therapeutics},
year = {2026},
volume = {32},
number = {6},
doi = {10.1002/cns.70961}
}
EUVIMED