Identifying suicide attempts, ideation, and non-ideation in major depressive disorder from structural MRI data using deep learning

Transcriptional Patterns of Brain Structural Covariance Network Abnormalities Associated With Suicidal Thoughts and Behaviors in Major Depressive Disorder

BACKGROUND

Although brain structural covariance network (SCN) abnormalities have been associated with suicidal thoughts and behaviors (STBs) in individuals with major depressive disorder (MDD), previous studies have reported inconsistent findings based on small sample sizes, and underlying transcriptional patterns remain poorly understood.

METHODS

Using a multicenter magnetic resonance imaging dataset including 218 MDD patients with STBs, 230 MDD patients without STBs, and 263 healthy control participants, we established individualized SCNs based on regional morphometric measures and assessed network topological metrics using graph theoretical analysis. Machine learning methods were applied to explore and compare the diagnostic value of morphometric and topological features in identifying MDD and STBs at the individual level. Brainwide relationships between STBs-related connectomic alterations and gene expression were examined using partial least squares regression.

RESULTS

Group comparisons revealed that SCN topological deficits associated with STBs were identified in the prefrontal, anterior cingulate, and lateral temporal cortices. Combining morphometric and topological features allowed for individual-level characterization of MDD and STBs. Topological features made a greater contribution to distinguishing between patients with and without STBs. STBs-related connectomic alterations were spatially correlated with the expression of genes enriched for cellular metabolism and synaptic signaling.

CONCLUSIONS

These findings revealed robust brain structural deficits at the network level, highlighting the importance of SCN topological measures in characterizing individual suicidality and demonstrating its linkage to molecular function and cell types, providing novel insights into the neurobiological underpinnings and potential markers for prediction and prevention of suicide.

Interpretable deep learning model for major depressive disorder assessment based on functional near-infrared spectroscopy

BACKGROUND

Major depressive disorder (MDD) affects a substantial number of individuals worldwide. New approaches are required to improve the diagnosis of MDD, which relies heavily on subjective reports of depression-related symptoms.

AIM

Establish an objective measurement and evaluation of MDD.

METHODS

Functional near-infrared spectroscopy (fNIRS) was used to investigate the brain activity of MDD patients and healthy controls (HCs). Leveraging a sizeable fNIRS dataset of 263 HCs and 251 patients with MDD, including mild to moderate MDD (mMDD; n = 139) and severe MDD (sMDD; n = 77), we developed an interpretable deep learning model for screening MDD and staging its severity.

RESULTS

The proposed deep learning model achieved an accuracy of 80.9% in diagnostic classification and 78.6% in severity staging for MDD. We discerned five channels with the most significant contribution to MDD identification through Shapley additive explanations (SHAP), located in the right medial prefrontal cortex, right dorsolateral prefrontal cortex, right superior temporal gyrus, and left posterior superior frontal cortex. The findings corresponded closely to the features of haemoglobin responses between HCs and individuals with MDD, as we obtained a good discriminative ability for MDD using cortical channels that are related to the disorder, namely the frontal and temporal cortical channels with areas under the curve of 0.78 and 0.81, respectively.

CONCLUSION

Our study demonstrated the potential of integrating the fNIRS system with artificial intelligence algorithms to classify and stage MDD in clinical settings using a large dataset. This approach can potentially enhance MDD assessment and provide insights for clinical diagnosis and intervention.

A multimodal prediction model for suicidal attempter in major depressive disorder

Background

Suicidal attempts in patients with major depressive disorder (MDD) have become an important challenge in global mental health affairs. To correctly distinguish MDD patients with and without suicidal attempts, a multimodal prediction model was developed in this study using multimodality data, including demographic, depressive symptoms, and brain structural imaging data. This model will be very helpful in the early intervention of MDD patients with suicidal attempts.

Methods

Two feature selection methods, support vector machine-recursive feature elimination (SVM-RFE) and random forest (RF) algorithms, were merged for feature selection in 208 MDD patients. SVM was then used as a classification model to distinguish MDD patients with suicidal attempts or not.

Results

The multimodal predictive model was found to correctly distinguish MDD patients with and without suicidal attempts using integrated features derived from SVM-RFE and RF, with a balanced accuracy of 77.78%, sensitivity of 83.33%, specificity of 70.37%, positive predictive value of 78.95%, and negative predictive value of 76.00%. The strategy of merging the features from two selection methods outperformed traditional methods in the prediction of suicidal attempts in MDD patients, with hippocampal volume, cerebellar vermis volume, and supracalcarine volume being the top three features in the prediction model.

Conclusions

This study not only developed a new multimodal prediction model but also found three important brain structural phenotypes for the prediction of suicidal attempters in MDD patients. This prediction model is a powerful tool for early intervention in MDD patients, which offers neuroimaging biomarker targets for treatment in MDD patients with suicidal attempts.

Classification of suicidality by training supervised machine learning models with brain MRI findings: A systematic review

BACKGROUND

Suicide is a global public health issue causing around 700,000 deaths worldwide each year. Therefore, identifying suicidal thoughts and behaviors in patients can help lower the suicide-related mortality rate. This review aimed to investigate the feasibility of suicidality identification by applying supervised Machine Learning (ML) methods to Magnetic Resonance Imaging (MRI) data.

METHODS

We conducted a systematic search on PubMed, Scopus, and Web of Science to identify studies examining suicidality by applying ML methods to MRI features. Also, the Prediction Model Risk of Bias Assessment Tool (PROBAST) was employed for the quality assessment.

RESULTS

23 studies met the inclusion criteria. Of these, 20 developed prediction models without external validation and 3 developed prediction models with external validation. The performance of ML models varied among the reviewed studies, with the highest reported values of accuracies and Area Under the Curve (AUC) ranging from 51.7 % to 100 % and 0.52 to 1, respectively. Over half of the studies that reported accuracy (12/21) or AUC (13/16) achieved values of ≥0.8. Our comparative analysis indicated that deep learning exhibited the highest predictive performance compared to other ML models. The most commonly identified discriminative imaging features were resting-state functional connectivity and grey matter volume within prefrontal-limbic structures.

LIMITATIONS

Small sample sizes, lack of external validation, heterogeneous study designs, and ML model development.

CONCLUSIONS

Most of the studies developed ML models capable of ML-based suicide identification, although ML models' predictive performance varied across the reviewed studies. Thus, further well-designed is necessary to uncover the true potential of different ML models in this field.

Establishment of a risk prediction model for suicide attempts in first-episode and drug naïve patients with major depressive disorder

BACKGROUND

Suicide is common in patients with major depressive disorder (MDD) and has serious consequences for individuals and families. This study aims to establish a risk prediction model for suicide attempts in MDD patients to make the detection of suicide risk more accurate and effective.

METHODS

A cross-sectional survey, clinical examination, and biochemical indicator tests were performed on 1718 first-episode and drug naïve patients with major depressive disorder. We used Machine Learning to establish a risk prediction model for suicide attempts in FEDN patients with MDD.

RESULTS

Five predictors were identified by LASSO regression analysis from a total of 20 variables studied, namely psychotic symptoms, anxiety symptoms, thyroid peroxidase antibodies (ATPO), total cholesterol (TC), and high-density lipoprotein-cholesterol (HDL-C). The model constructed using the five predictors displayed moderate predictive ability, with an area under the ROC of 0.771 in the training set and 0.720 in the validation set. The DCA curve showed that the nomogram could be applied clinically if the risk threshold was between 22 % and 60 %. The risk threshold was found to be between 20 % and 60 % in external validation.

CONCLUSION

Introducing psychotic symptoms, anxiety symptoms, ATPO, TC, and HDL-C to the risk nomogram increased its usefulness for predicting suicide risk in patients with MDD. It may be useful in clinical decision-making or in discussions with patients, especially in crisis interventions.