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

Integration of multimodal imaging data with machine learning for improved diagnosis and prognosis in neuroimaging

Introduction

Combining many types of imaging data-especially structural MRI (sMRI) and functional MRI (fMRI)-may greatly assist in the diagnosis and treatment of brain disorders like Alzheimer's. Current approaches are less helpful for forecasting, however, as they do not always blend spatial and temporal patterns from different sources properly. This work presents a novel mixed deep learning (DL) method combining data from many sources using CNN, GRU, and attention techniques. This work introduces a novel hybrid deep learning method combining CNN, GRU, and a Dynamic Cross-Modality Attention Module to help more efficiently blend spatial and temporal brain data. Through working around issues with current multimodal fusion techniques, our approach increases the accuracy and readability of diagnoses.

Methods

Utilizing CNNs and models of temporal dynamics from fMRI connection measures utilizing GRUs, the proposed approach extracts spatial characteristics from sMRI. Strong multimodal integration is made possible by including an attention mechanism to give diagnostically important features top priority. Training and evaluation of the model took place using the Human Connectome Project (HCP) dataset including behavioral data, fMRI, and sMRI. Measures include accuracy, recall, precision and F1-score used to evaluate performance.

Results

It was correct 96.79% of the time using the combined structure. Regarding the identification of brain disorders, the proposed model was more successful than existing ones.

Discussion

These findings indicate that the hybrid strategy makes sense for using complimentary information from several kinds of photos. Attention to detail helped one choose which aspects to concentrate on, thereby enhancing the readability and diagnostic accuracy.

Conclusion

The proposed method offers a fresh benchmark for multimodal neuroimaging analysis and has great potential for use in real-world brain assessment and prediction. Researchers will investigate future applications of this technique to new picture kinds and clinical data.

Predicting adolescent psychopathology from early life factors: A machine learning tutorial

Objective

The successful implementation and interpretation of machine learning (ML) models in epidemiological studies can be challenging without an extensive programming background. We provide a didactic example of machine learning for risk prediction in this study by determining whether early life factors could be useful for predicting adolescent psychopathology.

Methods

In total, 9643 adolescents ages 9-10 from the Adolescent Brain and Cognitive Development (ABCD) Study were included in ML analysis to predict high Child Behavior Checklist (CBCL) scores (i.e., t-scores ≥ 60). ML models were constructed using a series of predictor combinations (prenatal, family history, sociodemographic) across 5 different algorithms. We assessed ML performance through sensitivity, specificity, F1-score, and area under the curve (AUC) metrics.

Results

A total of 1267 adolescents (13.1 %) were found to have high CBCL scores. The best performing algorithms were elastic net and gradient boosted trees. The best performing elastic net models included prenatal and family history factors (Sensitivity 0.654, Specificity 0.713; AUC 0.742, F1-score 0.401) and prenatal, family, history, and sociodemographic factors (Sensitivity 0.668, Specificity 0.704; AUC 0.745, F1-score 0.402). Across all 5 ML algorithms, family history factors (e.g., either parent had nervous breakdowns, trouble holding jobs/fights/police encounters, and counseling for mental issues) and sociodemographic covariates (e.g., maternal age, child's sex, caregiver income and caregiver education) tended to be better predictors of adolescent psychopathology. The most important prenatal predictors were unplanned pregnancy, birth complications, and pregnancy complications.

Conclusion

Our results suggest that inclusion of prenatal, family history, and sociodemographic factors in ML models can generate moderately accurate predictions of adolescent psychopathology. Issues associated with model overfitting, hyperparameter tuning, and system seed setting should be considered throughout model training, testing, and validation. Future early risk predictions models may improve with the inclusion of additional relevant covariates.

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

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.

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

BACKGROUND

Social anhedonia is common within major depressive disorder (MDD) and associated with worse treatment outcomes. The orbitofrontal cortex (OFC) is implicated in both reward (medial OFC) and punishment (lateral OFC) in social decision making. Therefore, to understand the biology of social anhedonia in MDD, medial/lateral OFC metabolism, volume, and thickness, as well as structural connectivity to the striatum, amygdala, and ventral tegmental area/nucleus accumbens were examined. A positive relationship between social anhedonia and these neurobiological outcomes in the lateral OFC was hypothesized, whereas an inverse relationship was hypothesized for the medial OFC. The association between treatment-induced changes in OFC neurobiology and depression improvement were also examined.

METHODS

85 medication-free participants diagnosed with MDD were assessed with Wisconsin Schizotypy Scales to assess social anhedonia and received pretreatment simultaneous fluorodeoxyglucose positron emission tomography (FDG-PET) and magnetic resonance imaging (MRI), including structural and diffusion. Participants were then treated in an 8-week randomized placebo-controlled double-blind course of escitalopram. PET/MRI were repeated following treatment. Metabolic rate of glucose uptake was quantified from dynamic FDG-PET frames using Patlak graphical analysis. Structure (volume and cortical thickness) was quantified from structural MRI using Freesurfer. To assess structural connectivity, probabilistic tractography was performed on diffusion MRI and average FA was calculated within the derived tracts. Linear mixed models with Bonferroni correction were used to examine the relationships between variables.

RESULTS

A significantly negative linear relationship between pretreatment social anhedonia score and structural connectivity between the medial OFC and the amygdala (estimated coefficient: -0.006, 95 % CI: -0.0108 - -0.0012, p-value = 0.0154) was observed. However, this finding would not survive multiple comparisons correction. No strong evidence existed to show a significant linear relationship between pretreatment social anhedonia score and metabolism, volume, thickness, or structural connectivity to any of the regions examined. There was also no strong evidence to suggest significant linear relationships between improvement in depression and percent change in these variables.

CONCLUSIONS

Based on these multimodal findings, the OFC likely does not underlie social anhedonia in isolation and therefore should not be the sole target of treatment for social anhedonia. This is consistent with previous reports that other areas of the brain such as the amygdala and the striatum are highly involved in this behavior. Relatedly, amygdala-medial OFC structural connectivity could be a future target. The results of this study are crucial as, to our knowledge, they are the first to relate structure/function of the OFC with social anhedonia severity in MDD. Future work may need to involve a whole brain approach in order to develop therapeutics for social anhedonia.

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

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.