The diagnostic and predictive potential of personality traits and coping styles in major depressive disorder.

BACKGROUND: Major depressive disorder (MDD) is a global public health concern that is notably underdiagnosed and undertreated due to its complexity and subjective diagnostic methods. A holistic diagnostic procedure, which sufficiently considers all possible contributors to MDD symptoms, would improve MDD diagnosis and treatment. This study aims to explore whether personality and coping styles can predict MDD status and differentiate between depressed patients and healthy individuals. METHODS: Seventy healthy controls (N = 54 females) were matched to 70 MDD patients for age, sex, ethnicity, and years of education. MDD severity was measured using the Hamilton Depression Rating Scale, while personality traits and coping styles were measured by the Ten-Item Personality (TIPI) and Brief COPE questionnaires, respectively. Logistic regression analyses were conducted to investigate the diagnostic and predictive potential of personality and coping styles. Receiver operating characteristic (ROC) analyses were also conducted to examine their discriminative ability to distinguish between depressed and healthy individuals. RESULTS: Introversion, lack of organisation skills, and neuroticism were statistically significant in predicting MDD status. Dysfunctional coping strategies, such as denial and self-blame, were also shown to significantly predict MDD status. ROC analyses found both the TIPI questionnaire (AUC = 0.90), and dysfunctional coping (as measured by Brief COPE) (AUC = 0.90) to be excellent predictors of MDD. CONCLUSIONS: Our findings demonstrate the diagnostic and predictive potential of personality and coping styles for MDD in the clinical setting. They also demonstrate the remarkable ability of personality and coping styles to differentiate between depressed patients and healthy controls.

MicroRNA classification and discovery for major depressive disorder diagnosis: Towards a robust and interpretable machine learning approach.

BACKGROUND: Major depressive disorder (MDD) is notably underdiagnosed and undertreated due to its complex nature and subjective diagnostic methods. Biomarker identification would help provide a clearer understanding of MDD aetiology. Although machine learning (ML) has been implemented in previous studies to study the alteration of microRNA (miRNA) levels in MDD cases, clinical translation has not been feasible due to the lack of interpretability (i.e. too many miRNAs for consideration) and stability. METHODS: This study applied logistic regression (LR) model to the blood miRNA expression profile to differentiate patients with MDD (n = 60) from healthy controls (HCs, n = 60). Embedded (L1-regularised logistic regression) feature selector was utilised to extract clinically relevant miRNAs, and optimized for clinical application. RESULTS: Patients with MDD could be differentiated from HCs with the area under the receiver operating characteristic curve (AUC) of 0.81 on testing data when all available miRNAs were considered (which served as a benchmark). Our LR model selected miRNAs up to 5 (known as LR-5 model) emerged as the best model because it achieved a moderate classification ability (AUC = 0.75), relatively high interpretability (feature number = 5) and stability (ϕ̂Z=0.55) compared to the benchmark. The top-ranking miRNAs identified by our model have demonstrated associations with MDD pathways involving cytokine signalling in the immune system, the reelin signalling pathway, programmed cell death and cellular responses to stress. CONCLUSION: The LR-5 model, which is optimised based on ML design factors, may lead to a robust and clinically usable MDD diagnostic tool.

Clinical Utility of Functional Near-Infrared Spectroscopy for Assessment and Prediction of Suicidality: A Systematic Review.

Introduction: Suicide is a pressing psychiatric concern worldwide with no established biomarker. While there is some evidence of the clinical utility of functional near-infrared spectroscopy (fNIRS) in assessing and predicting suicidality, no systematic review of such evidence has been conducted to date. Therefore, this review aimed to systematically review and gather evidence from existing studies that used fNIRS signals to assess suicidality and its associated changes in the brain, and those that examined how such signals correlated with suicide symptomatology. Methods: PubMed, EMBASE, and Cochrane Library databases were used in a systematic literature search for English-language articles published between 2000 and December 19, 2020 that focused on the utility of fNIRS for (i) assessing suicidality and its associated changes in the brain, and (ii) correlating with suicide symptomatology. Studies were included if they utilised fNIRS to evaluate variations in fNIRS-measured cerebral hemodynamic responses in patients with different mental disorders (e.g., major depressive disorder, schizophrenia), as well as in healthy controls, of any age group. Quality of evidence was assessed using the Newcastle-Ottawa quality assessment scale. Results: A total of 7 cross-sectional studies were included in this review, all of which had acceptable quality. Across all studies, fNIRS demonstrated reduced cerebral hemodynamic changes in suicidal individuals when compared to non-suicidal individuals. One study also demonstrated the potential of fNIRS signals in correlating with the severity of suicidality. Conclusions: This review provides a comprehensive, updated review of evidence supporting the clinical utility of fNIRS in the assessment and prediction of suicidality. Further studies involving larger sample sizes, standardised methodology, and longitudinal follow-ups are needed.