Current suicide risk assessments for predicting suicide attempts are time consuming, of low predictive value and have inadequate reliability. This paper aims to develop a predictive model for suicide attempts among patients with depression using machine learning algorithms as well as presents a comparative study on single predictive models with ensemble predictive models for differentiating depressed patients with suicide attempts from non-suicide attempters. We applied and trained eight different machine learning algorithms using a dataset that consists of 75 patients diagnosed with a depressive disorder. A recursive feature elimination was used to reduce the features via three-fold cross validation. An ensemble predictive models outperformed the single predictive models. Voting and bagging revealed the highest accuracy of 92% compared to other machine learning algorithms. Our findings indicate that history of suicide attempt, religion, race, suicide ideation and severity of clinical depression are useful factors for prediction of suicide attempts.

No abstract

Introduction: Anxiety and depression occur at a high rate in cancer patients. However, debate remains regarding the effect of anxiety and depression on cancer survival. Objective: This study aimed to determine the effect of anxiety and depressive symptoms on the survival of cancer patients. Methods: The subjects consisted of 112 cancer patients who attended the Oncology and Radiotherapy outpatient clinic Hospital Kuala Lumpur, Malaysia, in 1999. Anxiety and depressive symptoms were measured using the Hospital Anxiety and Depression Scale (HADS) questionnaire at inception. Information on patients’ mortality status for extended 13 years follow-up (in 2011) was obtained from the National Registration Department death records. Overall survival for each anxiety and depressive symptoms scores in HADS at 13 years was calculated using Cox proportional hazards regression analysis. Results: Cancer patients experienced more anxiety (83%) compared to depressive symptoms (40.2%). The mean (S.D.) HADS scores for depressive symptoms were 9.9 (2.5), and the anxiety symptoms score was 12.6 (2.1). At 13 years, half of the patients (50.9%) had died. No significant effect of anxiety (p=0.399, 95% C.I.= 6.2-8.4) or depressive symptoms at inception (p=0.749, 95% C.I.= 5.9-8.4) towards cancer patients’ survival was found at 13 years follow-up. Conclusion: The occurrence of anxiety symptoms among cancer patients in this study was 2-folds higher than depressive symptoms. However, no significant increased risk of death was found in cancer patients with anxiety or depressive symptoms at 13 years follow-up. It may imply that as time extended, survival in cancer patients may be related to various interacting elements, and intervening health factors are of importance.

No abstract

Criminalization of suicide attempts is an archaic barrier to suicide prevention. Globally, clinical profiles of prosecuted suicide attempters are an under-researched area. This retrospective study aims to describe the clinical profiles of individuals who were charged for attempted suicide and subsequently sent for criminal responsibility and fitness to plead evaluation in a forensic psychiatric unit in Malaysia from January 1, 2008, to December 31, 2019. We identified 22 cases who were mostly adult males (90.9%). Seventy-three percent have a psychiatric disorder. Mood disorders were more prevalent (32%) followed by psychotic disorders and substance use disorders. For most of these individuals, this was the first contact with any form of mental health services and 41% defaulted their treatment before arrest. This sample illustrates a vulnerable group who has been disengaged with mental healthcare. Future research is warranted to further investigate mechanisms that are effective in addressing unmet needs of persons in suicidal crisis as opposed to utilizing the criminal justice pathway.