Suicidal attempters and non-attempters with bipolar disorder in Iran

Machine learning applied to the prediction of relapse, hospitalization, and suicide in bipolar disorder using neuroimaging and clinical data: A systematic review

BACKGROUND

Bipolar disorder (BD) is associated with increased morbidity/mortality. Adverse outcome prediction might help with the management of patients with BD.

METHODS

We systematically reviewed the performance of machine learning (ML) studies in predicting adverse outcomes (relapse or recurrence, hospital admission, and suicide-related events) in patients with BD. Demographic, clinical, and neuroimaging-related poor outcome predictors were also reviewed. Three databases (PubMed, Scopus, and Web of Science) were explored from inception to July 2023.

RESULTS

Eighteen studies, accounting for >30,000 patients, were included. Support vector machine, decision trees, random forest, and logistic regression were the most frequently used ML algorithms. ML models' area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity ranged from 0.71 to 0.98, 72.7-92.8 %, and 59.0-95.2 % for relapse/recurrence prediction (4 studies (3 on relapses and 1 on recurrences). The corresponding values were 0.78-0.88, 21.4-100 %, and 77.0-99.7 % for hospital admissions (3 studies, 21,266 patients), and 0.71-0.99, 44.4-97.9 %, and 38.9-95.0 % for suicide-related events (10 studies, 5558 patients). Also, one study addressed a combination of the interest outcomes. Adverse outcome predictors included early onset BD, BD type I, comorbid psychiatric or substance use disorder, circadian rhythm disruption, hospitalization characteristics, and neuroimaging parameters, including increased dynamic amplitude of low-frequency fluctuation, decreased frontolimbic functional connectivity and aberrant dynamic functional connectivity in corticostriatal circuitry.

CONCLUSIONS

ML models can predict adverse outcomes of BD with relatively acceptable performance measures. Future studies with larger samples and nested cross-validation validation should be conducted to reach more reliable results.

Confirmatory evaluation of the bipolar depression rating scale (BDRS) in a large sample of female patients with bipolar depression

OBJECTIVE

The Bipolar Depression Rating Scale (BDRS) is a structured rating scale designed to assess depressive and mixed symptoms in bipolar disorder (BD). Previous studies evaluating the scale have been performed on small samples or on patients in a depressive phase, but not on patients in a mixed or manic phase. This study evaluated the Persian version of the BDRS regarding its factor structure, reliability, and validity in a large sample of Iranian women with BD in a depressive or mixed/manic phase.

METHODS

Three-hundred and one female BD inpatients completed the BDRS, the Beck Depression Inventory-II (BDI-II), the Hamilton Depression Rating Scale (HDRS), the Montgomery-Åsberg Depression Rating Scale (MADRS), and the Young Mania Rating Scale (YMRS).

RESULTS

The BDRS demonstrated a three-factor structure with good reliability. The BDRS and its psychological and somatic symptom clusters had stronger correlations with other measures of depressive symptoms than a measure of mania. The BDRS mixed symptom cluster also had a stronger correlation with a measure of mania than other measures of depression, supporting the scales' convergent and discriminant validity.

CONCLUSIONS

The BDRS demonstrated psychometric validity in assessing depressive and mixed symptoms in Iranian women with BD in a depressive or mixed/manic phase.KEY POINTSThe Bipolar Depression Rating Scale (BDRS) was validated in Iranian women with BD.The BDRS showed a three-factor structure, similar to the original validation.The BDRS had good reliability based on Omega and test-retest coefficients.The findings provided evidence for the convergent and discriminant validity of the BDRS.

History of Lifetime suicide attempt in bipolar I disorder: its correlates and effect on illness course

OBJECTIVES

To identify the prevalence and correlates of bipolar I patients with a lifetime history of suicide attempt.

MATERIALS AND METHODS

Bipolar I disorder was diagnosed in 150 patients as per DSM-IV-TR criteria. Their lifetime suicide risk was assessed using the Columbia Suicide Severity Rating Scale. NIMH retrospective Life Chart Methodology was used to chart the illness course. Medication Adherence Rating Scale (MARS) and Pittsburgh Sleep Quality Index (PSQI) were used to assess the recent adherence and subjective sleep quality, respectively. The suicide attempters were compared with non-attempters on individual variables.

RESULTS

Around 23% had a positive lifetime history of suicide attempt. They were predominantly female, had an index (first ever) episode of depression, spent more proportion of time being ill, especially in depressive or mixed episode phase. Comorbid substance use disorder along with suicidal attempts was seen only in males. Suicide attempters displayed poor medication adherence attitudes for medications taken during the past week and reported impaired sleep quality for the previous month.

CONCLUSIONS

A positive history of lifetime suicide attempt was significantly associated with a worse course of bipolar I disorder. Effective treatment of depressive episodes, addressing non-adherence, substance use and sleep problems can reduce the suicide risk in such patients. Retrospective design of the study and recall bias are some of the limitations.

Is sex important? Gender differences in bipolar disorder

Sex is clearly important in unipolar mood disorder with compelling evidence that depression is approximately twice as common in women than in men. In the case of bipolar disorder, however, it is widely perceived that the reported equal rate of illness in men and women reflects no important gender distinctions. In this paper we review the literature on gender differences in bipolar illness and attempt to summarize what is known and what requires further study. Despite the uncertainties that remain some conclusions can be drawn. Most studies, but not all, report an almost equal gender ratio in the prevalence of bipolar disorder but the majority of studies do report an increased risk in women of bipolar II/hypomania, rapid cycling and mixed episodes. Important gender distinctions are also found in patterns of co-morbidity. No consistent gender differences have been found in a number of variables including rates of depressive episodes, age and polarity of onset, symptoms, severity of the illness, response to treatment and suicidal behaviour. Unsurprisingly, however, perhaps the major distinction between men and women with bipolar disorder is the impact that reproductive life events, particularly childbirth, have on women with this diagnosis.