A Novel Depression Risk Prediction Model Using NHANES Data With Mendelian Randomization Validation

ABSTRACT Background Despite depression's significant public health impact, efficient and accessible screening tools utilizing routine clinical indicators remain limited. This study aimed to develop and validate a practical depression risk prediction model based on commonly available biochemical...

Full description

Saved in:
Bibliographic Details
Main Authors: Lin Lin, Liqun Zhang, Jingdong Zhang, Dapeng Ding
Format: Article
Language:English
Published: Wiley 2025-07-01
Series:Brain and Behavior
Subjects:
Online Access:https://doi.org/10.1002/brb3.70674
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849729990044680192
author Lin Lin
Liqun Zhang
Jingdong Zhang
Dapeng Ding
author_facet Lin Lin
Liqun Zhang
Jingdong Zhang
Dapeng Ding
author_sort Lin Lin
collection DOAJ
description ABSTRACT Background Despite depression's significant public health impact, efficient and accessible screening tools utilizing routine clinical indicators remain limited. This study aimed to develop and validate a practical depression risk prediction model based on commonly available biochemical markers, facilitating widespread early screening and timely intervention in general clinical settings. Methods We formulated a model for depression, scrutinizing an assortment of biochemical indicators and their bidirectional interrelationships with depression, employing data derived from the National Health and Nutrition Examination Survey (NHANES) and leveraging the Mendelian randomization (MR) approach, a method that utilizes genetic variants as instrumental proxies to ascertain causal nexus between risk determinants and diseases. Results Using NHANES data (training cohort: n = 27,327; validation cohort: n = 4383), we developed two prediction models through LASSO and multivariate logistic regression. Both models demonstrated comparable performance in terms of discrimination (ROC curves), calibration (slope and Hosmer‐Lemeshow test), Brier score, decision curve analysis, net reclassification improvement, and integrated discrimination improvement. Given the similar performance metrics and more parsimonious nature, Model 2, with 14 variables, was selected as the final model. MR analysis revealed bidirectional relationships between biomarkers and depression. Higher body mass index level was associated with increased depression risk (odds ratio [OR]: 1.061, p = 0.008). Depression itself showed significant associations with increased ALP (OR: 1.048, p = 0.010), decreased BUN (OR: 0.966, p = 0.032), and TB (OR: 0.963, p = 0.044) levels. Conclusions Model 2, selected for its predictive accuracy and streamlined complexity, presents a pragmatic instrument for large‐scale population screenings, facilitating timely intervention and therapeutic strategies.
format Article
id doaj-art-d0ade5042b5d4c60b4a1f251ae0fbb5d
institution DOAJ
issn 2162-3279
language English
publishDate 2025-07-01
publisher Wiley
record_format Article
series Brain and Behavior
spelling doaj-art-d0ade5042b5d4c60b4a1f251ae0fbb5d2025-08-20T03:09:00ZengWileyBrain and Behavior2162-32792025-07-01157n/an/a10.1002/brb3.70674A Novel Depression Risk Prediction Model Using NHANES Data With Mendelian Randomization ValidationLin Lin0Liqun Zhang1Jingdong Zhang2Dapeng Ding3Department of Clinical Laboratory MedicineFirst Affiliated Hospital of Dalian Medical University, Zhongshan Road, Xigang District Dalian Liaoning Province ChinaSchool of Biomedical Engineering, Faculty of MedicineDalian University of Technology, No. 2 Linggong Road, Ganjingzi District Dalian Liaoning Province ChinaSchool of Biomedical Engineering, Faculty of MedicineDalian University of Technology, No. 2 Linggong Road, Ganjingzi District Dalian Liaoning Province ChinaDepartment of Clinical Laboratory MedicineFirst Affiliated Hospital of Dalian Medical University, Zhongshan Road, Xigang District Dalian Liaoning Province ChinaABSTRACT Background Despite depression's significant public health impact, efficient and accessible screening tools utilizing routine clinical indicators remain limited. This study aimed to develop and validate a practical depression risk prediction model based on commonly available biochemical markers, facilitating widespread early screening and timely intervention in general clinical settings. Methods We formulated a model for depression, scrutinizing an assortment of biochemical indicators and their bidirectional interrelationships with depression, employing data derived from the National Health and Nutrition Examination Survey (NHANES) and leveraging the Mendelian randomization (MR) approach, a method that utilizes genetic variants as instrumental proxies to ascertain causal nexus between risk determinants and diseases. Results Using NHANES data (training cohort: n = 27,327; validation cohort: n = 4383), we developed two prediction models through LASSO and multivariate logistic regression. Both models demonstrated comparable performance in terms of discrimination (ROC curves), calibration (slope and Hosmer‐Lemeshow test), Brier score, decision curve analysis, net reclassification improvement, and integrated discrimination improvement. Given the similar performance metrics and more parsimonious nature, Model 2, with 14 variables, was selected as the final model. MR analysis revealed bidirectional relationships between biomarkers and depression. Higher body mass index level was associated with increased depression risk (odds ratio [OR]: 1.061, p = 0.008). Depression itself showed significant associations with increased ALP (OR: 1.048, p = 0.010), decreased BUN (OR: 0.966, p = 0.032), and TB (OR: 0.963, p = 0.044) levels. Conclusions Model 2, selected for its predictive accuracy and streamlined complexity, presents a pragmatic instrument for large‐scale population screenings, facilitating timely intervention and therapeutic strategies.https://doi.org/10.1002/brb3.70674biochemical markersdepressionMendelian randomization (MR)national health and nutrition examination survey (NHANES)predictive modeling
spellingShingle Lin Lin
Liqun Zhang
Jingdong Zhang
Dapeng Ding
A Novel Depression Risk Prediction Model Using NHANES Data With Mendelian Randomization Validation
Brain and Behavior
biochemical markers
depression
Mendelian randomization (MR)
national health and nutrition examination survey (NHANES)
predictive modeling
title A Novel Depression Risk Prediction Model Using NHANES Data With Mendelian Randomization Validation
title_full A Novel Depression Risk Prediction Model Using NHANES Data With Mendelian Randomization Validation
title_fullStr A Novel Depression Risk Prediction Model Using NHANES Data With Mendelian Randomization Validation
title_full_unstemmed A Novel Depression Risk Prediction Model Using NHANES Data With Mendelian Randomization Validation
title_short A Novel Depression Risk Prediction Model Using NHANES Data With Mendelian Randomization Validation
title_sort novel depression risk prediction model using nhanes data with mendelian randomization validation
topic biochemical markers
depression
Mendelian randomization (MR)
national health and nutrition examination survey (NHANES)
predictive modeling
url https://doi.org/10.1002/brb3.70674
work_keys_str_mv AT linlin anoveldepressionriskpredictionmodelusingnhanesdatawithmendelianrandomizationvalidation
AT liqunzhang anoveldepressionriskpredictionmodelusingnhanesdatawithmendelianrandomizationvalidation
AT jingdongzhang anoveldepressionriskpredictionmodelusingnhanesdatawithmendelianrandomizationvalidation
AT dapengding anoveldepressionriskpredictionmodelusingnhanesdatawithmendelianrandomizationvalidation
AT linlin noveldepressionriskpredictionmodelusingnhanesdatawithmendelianrandomizationvalidation
AT liqunzhang noveldepressionriskpredictionmodelusingnhanesdatawithmendelianrandomizationvalidation
AT jingdongzhang noveldepressionriskpredictionmodelusingnhanesdatawithmendelianrandomizationvalidation
AT dapengding noveldepressionriskpredictionmodelusingnhanesdatawithmendelianrandomizationvalidation