Gradient boosting decision-tree-based algorithm with neuroimaging for personalized treatment in depression

Ali, Farzana; Wengler, Kenneth; He, Xiang; Nguyen, Marie; Parsey, Ramin V.; DeLorenzo, Christine

doi:10.1016/j.neuri.2022.100110

Cited by 9 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such a model can be expanded to include other demographics and measures of actigraphy time series data (e.g., energy expenditure, sleep duration, etc.) and activity related circadian genes 56 as well as clinical notes, lab values, and medical imaging 46 , 57 for a comprehensive clinical decision support tool. Continuous actigraphy data can be used to identify changes in circadian motor activity over time, by quantifying patterns in sequential time series data, which is also useful for forecasting 58 .…”

Section: Discussionmentioning

confidence: 99%

Circadian rhythm biomarker from wearable device data is related to concurrent antidepressant treatment response

et al. 2023

Self Cite

View full text Add to dashboard Cite

Major depressive disorder (MDD) is associated with circadian rhythm disruption. Yet, no circadian rhythm biomarkers have been clinically validated for assessing antidepressant response. In this study, 40 participants with MDD provided actigraphy data using wearable devices for one week after initiating antidepressant treatment in a randomized, double-blind, placebo-controlled trial. Their depression severity was calculated pretreatment, after one week and eight weeks of treatment. This study assesses the relationship between parametric and nonparametric measures of circadian rhythm and change in depression. Results show significant association between a lower circadian quotient (reflecting less robust rhythmicity) and improvement in depression from baseline following first week of treatment (estimate = 0.11, F = 7.01, P = 0.01). There is insufficient evidence of an association between circadian rhythm measures acquired during the first week of treatment and outcomes after eight weeks of treatment. Despite this lack of association with future treatment outcome, this scalable, cost-effective biomarker may be useful for timely mental health care through remote monitoring of real-time changes in current depression.

show abstract

Section: Discussionmentioning

confidence: 99%

Circadian rhythm biomarker from wearable device data is related to concurrent antidepressant treatment response

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…All participants provided informed consent. Data from this study has been previously published; however, the previous studies involved either FDG-PET ( Hill et al, 2021 , Jones et al, 2022 ), structural MRI ( Jones et al, 2022 ), Magnetic Resonance Spectroscopy ( Ali et al, 2022 , Narayan et al, 2022 ) or actigraphy ( Ali et al, 2023 ) measures and did not assess social anhedonia. Inclusion criteria were: ability to provide informed consent, age 18 years or older, diagnosis of current major depressive episode (major depressive episode; confirmed by Structured Clinical Interview for DSM-IV (SCID-IV) interview), and a score of at least 22 on the Montgomery-Asberg Depression Rating Scale (MADRS; 22 is considered moderate depression) ( Montgomery and Asberg, 1979 ).…”

Section: Methodsmentioning

confidence: 99%

Orbitofrontal and striatal metabolism, volume, thickness and structural connectivity in relation to social anhedonia in depression: A multimodal study

Donnelly,

Hsu,

Gardus

et al. 2024

NeuroImage: Clinical

Self Cite

View full text Add to dashboard Cite

“…This is consistent with previous studies showing placebo response is similar to SSRI response neurobiologically [ 24 ] and clinically [ 25 – 28 ]. Relatedly, in the APAT cohort, neurobiological changes with treatment [ 29 , 30 ] or prediction of treatment response [ 21 , 31 , 32 ] were not significantly affected by treatment type. Therefore, we pooled all participants from both treatment arms together to predict remission and included treatment assignment as a possible predictor.…”

Section: Methodsmentioning

confidence: 99%

Examining factors related to low performance of predicting remission in participants with major depressive disorder using neuroimaging data and other clinical features

Wang,

Wu,

DeLorenzo

et al. 2024

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Major depressive disorder (MDD), a prevalent mental health issue, affects more than 8% of the US population, and almost 17% in the young group of 18–25 years old. Since Covid-19, its prevalence has become even more significant. However, the remission (being free of depression) rates of first-line antidepressant treatments on MDD are only about 30%. To improve treatment outcomes, researchers have built various predictive models for treatment responses and yet none of them have been adopted in clinical use. One reason is that most predictive models are based on data from subjective questionnaires, which are less reliable. Neuroimaging data are promising objective prognostic factors, but they are expensive to obtain and hence predictive models using neuroimaging data are limited and such studies were usually in small scale (N<100). In this paper, we proposed an advanced machine learning (ML) pipeline for small training dataset with large number of features. We implemented multiple imputation for missing data and repeated K-fold cross validation (CV) to robustly estimate predictive performances. Different feature selection methods and stacking methods using 6 general ML models including random forest, gradient boosting decision tree, XGBoost, penalized logistic regression, support vector machine (SVM), and neural network were examined to evaluate the model performances. All predictive models were compared using model performance metrics such as accuracy, balanced accuracy, area under ROC curve (AUC), sensitivity and specificity. Our proposed ML pipeline was applied to a training dataset and obtained an accuracy and AUC above 0.80. But such high performance failed while applying our ML pipeline using an external validation dataset from the EMBARC study which is a multi-center study. We further examined the possible reasons especially the site heterogeneity issue.

show abstract

Gradient boosting decision-tree-based algorithm with neuroimaging for personalized treatment in depression

Cited by 9 publications

References 35 publications

Circadian rhythm biomarker from wearable device data is related to concurrent antidepressant treatment response

Circadian rhythm biomarker from wearable device data is related to concurrent antidepressant treatment response

Orbitofrontal and striatal metabolism, volume, thickness and structural connectivity in relation to social anhedonia in depression: A multimodal study

Examining factors related to low performance of predicting remission in participants with major depressive disorder using neuroimaging data and other clinical features

Contact Info

Product

Resources

About