Classifying depression using blood biomarkers: A large population study

Lin, Ziqiang; Lawrence, Wayne R.; Huang, Yanhong; Lin, Qiaoxuan; Gao, Yanhui

doi:10.1016/j.jpsychires.2021.05.070

Cited by 9 publications

(8 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ratio of family income to poverty was the most important feature across all models. This result accords with findings of recent ML studies [4,37], which reported the ratio of family income to poverty (or family income itself) as the most crucial feature in predicting depression among community-dwelling adults. Kang and Kim [38] also have noted that the associations of hypertension with symptoms and diagnosis of depression differ by income level.…”

Section: Plos Onesupporting

confidence: 92%

“…We identified several important biomarkers across the model: triglycerides, white blood cell count, and hemoglobin. In Lin et al's study [4] using random forest, triglycerides were an essential variable in building a depression prediction model that included the general population and individuals with a high body mass index. Sharma and Verbeke [14] observed that…”

Section: Plos Onementioning

confidence: 99%

“…Today, machine learning (ML) has been helpful for researchers in designing optimal predictive models within and across large datasets. In the United States, ML has been applied to train a classification model that could accurately identify depression based on several demographic, social, and clinical factors, either in the general population [4,5] or in people with chronic condition such as diabetes [4] or heart disease [6]. However, such efforts to identify depression in individuals with hypertension are lacking.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning-based predictive modeling of depression in hypertensive populations

Lee

Kim

2022

PLoS ONE

View full text Add to dashboard Cite

We aimed to develop prediction models for depression among U.S. adults with hypertension using various machine learning (ML) approaches. Moreover, we analyzed the mechanisms of the developed models. This cross-sectional study included 8,628 adults with hypertension (11.3% with depression) from the National Health and Nutrition Examination Survey (2011–2020). We selected several significant features using feature selection methods to build the models. Data imbalance was managed with random down-sampling. Six different ML classification methods implemented in the R package caret—artificial neural network, random forest, AdaBoost, stochastic gradient boosting, XGBoost, and support vector machine—were employed with 10-fold cross-validation for predictions. Model performance was assessed by examining the area under the receiver operating characteristic curve (AUC), accuracy, precision, sensitivity, specificity, and F1-score. For an interpretable algorithm, we used the variable importance evaluation function in caret. Of all classification models, artificial neural network trained with selected features (n = 30) achieved the highest AUC (0.813) and specificity (0.780) in predicting depression. Support vector machine predicted depression with the highest accuracy (0.771), precision (0.969), sensitivity (0.774), and F1-score (0.860). The most frequent and important features contributing to the models included the ratio of family income to poverty, triglyceride level, white blood cell count, age, sleep disorder status, the presence of arthritis, hemoglobin level, marital status, and education level. In conclusion, ML algorithms performed comparably in predicting depression among hypertensive populations. Furthermore, the developed models shed light on variables’ relative importance, paving the way for further clinical research.

show abstract

Section: Plos Onesupporting

confidence: 92%

Section: Plos Onementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning-based predictive modeling of depression in hypertensive populations

Lee

Kim

2022

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…However, the findings in this study show a very weak correlation between PLR and BDI II scores, which indicates that PLR values do not differ significantly between each level of depression. 14 In another study conducted by Kayhan et al 2017 found that patients with major depression with psychotic features had a higher PLR than other patients. Another important finding was the absence of a significant difference in parameters between inpatients and outpatients with major depression without psychotic features.…”

Section: Wika Hanida Lubis the Relationship Between Platelet Lymphocy...mentioning

confidence: 95%

The Relationship Between Platelet Lymphocyte Ratio (PLR) with Depressed Level in Patients with Chronic Kidney Disease (CKD) Undergoing Regular Hemodialysis at Haji Adam Malik General Hospital Medan

Lubis

2023

Int J Res Rev

View full text Add to dashboard Cite

Background: Inflammation and stress levels associated with Chronic Kidney Disease (CKD) can lead to poor quality of life and adverse medical outcomes. Currently, the commonly used inflammatory tests in CKD patients are C-reactive protein (CRP), procalcitonin (PCT), and ferritin. Nonetheless, these tests have some drawbacks, such as being less specific, expensive, and difficult to access. Therefore, the platelet-lymphocyte ratio (PLR) can be considered as a promising alternative as a prognostic indicator in CKD patients with major depression. Methods: This research is an analytical study with a cross-sectional design carried out in February 2023 until the number of samples is fulfilled, at the Hemodialysis Installation of RSUP. H. Adam Malik to analyze the relationship of PLR in depressed patients with CKD undergoing regular hemodialysis. The data analysis used is the Pearson correlation test if the data is normally distributed. If the data is not normally distributed, Spearman's correlation test is performed. Statistical analysis used a 95% confidence level (p<0.05). Results: In this study, the demographic characteristics of 86 patients were obtained with a mean age of 49.08 years with a standard deviation of 14.11. Based on the Spearman rho test, it was found that there was no significant correlation between the PLR score and the BDI II score with a p value of 0.975. The r value is 0.003. This shows that there is a very weak correlation between the PLR score and the BD II score. Conclusion: There is no correlation between Depression level and Platelet Lymphocyte Ratio (PLR) in CKD patients undergoing regular hemodialysis. Keywords: Depression, Platelet Lymphocyte Ratio (PLR), chronic kidney disease (CKD), Inflammation

show abstract

“…For example, decreased total serum cholesterol, decrease in high-density lipoprotein (HDL), and increase in low-density lipoprotein (LDL) and LDL/HDL ratio, are associated with depression [ 2 – 9 ]. A study by the National Health and Nutrition Examination Survey (NHANES; 2015–2016) showed that the level of TG was one of the most important features in predicting depression [ 10 ]. However, conflicting results from previous analyses of NHANES (2009–2015) reported that low levels of total cholesterol (TC) were not associated with an increased risk of depression [ 11 ], while two other studies reported an inverse relationship between depression and levels of TC [ 12 – 14 ].…”

Section: Introductionmentioning

confidence: 99%

Depression and cognition are associated with lipid dysregulation in both a multigenerational study of depression and the National Health and Nutrition Examination Survey

Mehdi,

Costa,

Svob

et al. 2024

Transl Psychiatry

View full text Add to dashboard Cite

Chronic dysregulation of peripheral lipids has been found to be associated with depression and cognition, but their interaction has not been investigated. Growing evidence has highlighted the association between peripheral lipoprotein levels with depression and cognition with inconsistent results. We assessed the association between peripheral lipids, depression, and cognition while evaluating their potential interactions using robust clinically relevant predictors such as lipoprotein levels and chronic medical disorders that dysregulate lipoproteins. We report an association between peripheral lipids, depression, and cognition, suggesting a common underlying biological mechanism driven by lipid dysregulation in two independent studies. Analysis of a longitudinal study of a cohort at high or low familial risk for major depressive disorder (MDD) (n = 526) found metabolic diseases, including diabetes, hypertension, and other cardiovascular diseases, were associated with MDD and cognitive outcomes. Investigating a cross-sectional population survey of adults in the National Health and Nutrition Examination Survey 2011–2014 (NHANES) (n = 2377), depression was found to be associated with high density lipoprotein (HDL) and cognitive assessments. In the familial risk study, medical conditions were found to be associated with chronic lipid dysregulation and were significantly associated with MDD using the structural equation model. A positive association between chronic lipid dysregulation and cognitive scores was found in an exploratory analysis of the familial risk study. In a complementary study, analysis of NHANES revealed a positive association of HDL levels with cognition. Further analysis of the NHANES cohort indicated that depression status mediated the interaction between HDL levels and cognitive tests. Importantly, the protective effect of HDL on cognition was absent in those with depressive symptoms, which may ultimately result in worse outcomes leading to cognitive decline. These findings highlight the potential for the early predictive value of medical conditions with chronic lipid dyshomeostasis for the risk of depression and cognitive decline.

show abstract

Classifying depression using blood biomarkers: A large population study

Cited by 9 publications

References 75 publications

Machine learning-based predictive modeling of depression in hypertensive populations

Machine learning-based predictive modeling of depression in hypertensive populations

The Relationship Between Platelet Lymphocyte Ratio (PLR) with Depressed Level in Patients with Chronic Kidney Disease (CKD) Undergoing Regular Hemodialysis at Haji Adam Malik General Hospital Medan

Depression and cognition are associated with lipid dysregulation in both a multigenerational study of depression and the National Health and Nutrition Examination Survey

Contact Info

Product

Resources

About