Improving risk prediction for target subpopulations: Predicting suicidal behaviors among multiple sclerosis patients

Factors Contributing to the Development of Neuropsychiatric Manifestations in Persons With Multiple Sclerosis: A Systematic Review

Multiple sclerosis (MS) is the most common chronic demyelinating disease affecting the central nervous system (CNS) and is distinguished by neuroinflammation and neurodegeneration. It has four categories based on clinical course, with relapsing-remitting being the most common type. MS predominantly manifests with motor and sensory dysfunctions. However, neuropsychiatric manifestations such as depression, anxiety, schizophrenia, and bipolar disorder are not uncommon. Various factors may contribute to the development of these manifestations; therefore, this study aimed to unravel them. This systematic review implemented the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. Five databases (PubMed, PubMed Central (PMC), ScienceDirect, Cochrane Library, and Google Scholar) were used to acquire articles published in the past five years. After screening and quality appraisal were completed, eight articles were deemed eligible for inclusion in this study. The study designs included cohort, cross-sectional, randomized-controlled trial (RCT), case report, case-control, and narrative review. The development of neuropsychiatric manifestations in persons with MS is influenced by various factors. These were categorized into morphological changes of the brain, immunological mechanisms, socioeconomic factors, and individual factors for discussion. Each factor was found to intermingle with the others, requiring further research to understand the features that each factor contributes. This is crucial for improving the quality of life (QOL) and prognosis for persons living with MS.

Prevalence and correlates of suicide risk among non-psychiatric inpatients in a general hospital in China

OBJECTIVE

This study aims to investigate the suicide risk and mental health status of non-psychiatric inpatients in general hospital and explore the risk factors of suicide.

METHODS

A prospective study was conducted at a tertiary general hospital in Guangzhou, Guangdong Province, China. On-line assessment of mental health status and suicide was completed at admission and discharge. We assessed depression, anxiety, insomnia and suicide of inpatients and binary logistics regression was used to examine the risk factors of suicide.

RESULTS

From April 1, 2021 and January 31, 2022, 3685 inpatients were included. The detection rates of depression, anxiety and insomnia were 14.6 %, 9.0 % and 17.8 %, respectively. There were 2.7 % of inpatients at suicide risk. Binary logistics regression demonstrated that the inpatients with anxiety were at higher risk of suicide.

LIMITATIONS

(1) Single-center study limits the generalization of conclusion, (2) low response rate at discharge.

CONCLUSIONS

The comorbidity of physical illnesses and mental health problems, including depression, anxiety, insomnia, and suicide among non-psychiatric patients in general hospital was common. An assessment of anxiety may help identify individuals at high suicide risk. Medical staff in general hospitals should be trained to improve their ability to identify mental disorders and high-risk individuals for suicide, provide timely interventions and effectively reduce the suicide risk of patients.

Evidence for the biopsychosocial model of suicide: a review of whole person modeling studies using machine learning

Background

Traditional approaches to modeling suicide-related thoughts and behaviors focus on few data types from often-siloed disciplines. While psychosocial aspects of risk for these phenotypes are frequently studied, there is a lack of research assessing their impact in the context of biological factors, which are important in determining an individual's fulsome risk profile. To directly test this biopsychosocial model of suicide and identify the relative importance of predictive measures when considered together, a transdisciplinary, multivariate approach is needed. Here, we systematically review the emerging literature on large-scale studies using machine learning to integrate measures of psychological, social, and biological factors simultaneously in the study of suicide.

Methods

We conducted a systematic review of studies that used machine learning to model suicide-related outcomes in human populations including at least one predictor from each of biological, psychological, and sociological data domains. Electronic databases MEDLINE, EMBASE, PsychINFO, PubMed, and Web of Science were searched for reports published between August 2013 and August 30, 2023. We evaluated populations studied, features emerging most consistently as risk or resilience factors, methods used, and strength of evidence for or against the biopsychosocial model of suicide.

Results

Out of 518 full-text articles screened, we identified a total of 20 studies meeting our inclusion criteria, including eight studies conducted in general population samples and 12 in clinical populations. Common important features identified included depressive and anxious symptoms, comorbid psychiatric disorders, social behaviors, lifestyle factors such as exercise, alcohol intake, smoking exposure, and marital and vocational status, and biological factors such as hypothalamic-pituitary-thyroid axis activity markers, sleep-related measures, and selected genetic markers. A minority of studies conducted iterative modeling testing each data type for contribution to model performance, instead of reporting basic measures of relative feature importance.

Conclusion

Studies combining biopsychosocial measures to predict suicide-related phenotypes are beginning to proliferate. This literature provides some early empirical evidence for the biopsychosocial model of suicide, though it is marred by harmonization challenges. For future studies, more specific definitions of suicide-related outcomes, inclusion of a greater breadth of biological data, and more diversity in study populations will be needed.