Machine Learning Prediction of Comorbid Substance Use Disorders among People with Bipolar Disorder

Cognitive Dysfunction in the Addictions (CDiA): A Neuron to Neighbourhood Collaborative Research Program on Executive Dysfunction and Functional Outcomes in Outpatients Seeking Treatment for Addiction

Background

Substance use disorders (SUDs) are pressing global public health problems. Executive functions (EFs) are prominently featured in mechanistic models of addiction. However, there remain significant gaps in our understanding of EFs in SUDs, including the dimensional relationships of EFs to underlying neural circuits, molecular biomarkers, disorder heterogeneity, and functional ability. To improve health outcomes for people with SUDs, interdisciplinary clinical, preclinical and health services research is needed to inform policies and interventions aligned with biopsychosocial models of addiction. Here, we introduce Cognitive Dysfunction in the Addictions (CDiA), an integrative team-science and translational research program, which aims to fill these knowledge gaps and facilitate research discoveries to enhance treatments for people living with SUDs.

Methods

The CDiA Program comprises seven complementary interdisciplinary projects that aim to progress understanding of EF in SUDs and investigate new biological treatment approaches. The projects draw on a diverse sample of adults aged 18-60 (target N=400) seeking treatment for addiction, who are followed prospectively over one year to identify EF domains crucial to recovery. Projects 1-3 investigate SUD symptoms, brain circuits, and blood biomarkers and their associations with both EF domains (inhibition, working memory, and set-shifting) and functional outcomes (disability, quality of life). Projects 4 and 5 evaluate interventions for addiction and their impacts on EF: a clinical trial of repetitive transcranial magnetic stimulation and a preclinical study of potential new pharmacological treatments in rodents. Project 6 links EF to healthcare utilization and is supplemented with a qualitative investigation of EF-related barriers to treatment engagement for those with substance use concerns. Project 7 uses innovative whole-person modeling to integrate the multi-modal data generated across projects, applying clustering and deep learning methods to identify patient subtypes and drive future cross-disciplinary initiatives.

Discussion

The CDiA program has promise to bring scientific domains together to uncover the diverse ways in which EFs are linked to SUD severity and functional recovery. These findings, supported by emerging clinical, preclinical, health service, and whole-person modeling investigations, will facilitate future discoveries about cognitive dysfunction in addiction and could enhance the future clinical care of individuals seeking treatment for SUDs.

Meta-analysis of the effects of adjuvant drugs in co-occurring bipolar and substance use disorder

BACKGROUND

Individuals with bipolar disorder (BD) often have co-occurring substance use disorders (SUDs), which substantially impoverish the course of illness. Despite the importance of this dual diagnosis, the evidence of the efficacy and safety of adjuvant treatments is mostly unknown.

OBJECTIVE

To perform a meta-analysis to evaluate the efficacy and safety of adjuvant drugs in patients with co-occurring BD and SUD.

METHODS

We searched PubMed, Scopus, and Web of Knowledge until 30th April 2022 for randomized clinical trials (RCT) evaluating the efficacy and safety of adjuvant drugs compared to placebo in patients with a dual diagnosis of BD and SUD. We meta-analyzed the effect of adjuvant drugs on general outcomes (illness severity, mania, depression, anxiety, abstinence, substance craving, substance use, gamma-GT, adherence, and adverse events) and used the results to objectively assess the quality of the evidence according to the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) approach. For completeness, we also report the specific effects of specific adjuvant drugs in patients with specific substance disorders.

RESULTS

We included 15 RCT studies (9 alcohol, 3 cocaine, 2 nicotine, and 1 cannabis) comprising 628 patients allocated to treatment and 622 to placebo. There was low-quality evidence that adjuvant drugs may reduce illness severity (g=-0.25, 95% CI: -0.44, -0.06), and very-low quality evidence that they may decrease substance use (g=-0.23, 95% CI: -0.44, -0.02) and increase substance abstinence (g=0.21, 95% CI: 0.04, 0.38).

DISCUSSION

There is low-quality evidence that adjuvant drugs may help reduce illness severity, probably via facilitating abstinence and lower substance use. However, the evidence is weak; thus, these results should be considered cautiously until better evidence exists.

Research landscape analysis on dual diagnosis of substance use and mental health disorders: key contributors, research hotspots, and emerging research topics

BACKGROUND

Substance use disorders (SUDs) and mental health disorders (MHDs) are significant public health challenges with far-reaching consequences on individuals and society. Dual diagnosis, the coexistence of SUDs and MHDs, poses unique complexities and impacts treatment outcomes. A research landscape analysis was conducted to explore the growth, active countries, and active journals in this field, identify research hotspots, and emerging research topics.

METHOD

A systematic research landscape analysis was conducted using Scopus to retrieve articles on dual diagnosis of SUDs and MHDs. Inclusion and exclusion criteria were applied to focus on research articles published in English up to December 2022. Data were processed and mapped using VOSviewer to visualize research trends.

RESULTS

A total of 935 research articles were found. The number of research articles on has been increasing steadily since the mid-1990s, with a peak of publications between 2003 and 2012, followed by a fluctuating steady state from 2013 to 2022. The United States contributed the most articles (62.5%), followed by Canada (9.4%). The Journal of Dual Diagnosis, Journal of Substance Abuse Treatment, and Mental Health and Substance Use Dual Diagnosis were the top active journals in the field. Key research hotspots include the comorbidity of SUDs and MHDs, treatment interventions, quality of life and functioning, epidemiology, and the implications of comorbidity. Emerging research topics include neurobiological and psychosocial aspects, environmental and sociocultural factors, innovative interventions, special populations, and public health implications.

CONCLUSIONS

The research landscape analysis provides valuable insights into dual diagnosis research trends, active countries, journals, and emerging topics. Integrated approaches, evidence-based interventions, and targeted policies are crucial for addressing the complex interplay between substance use and mental health disorders and improving patient outcomes.

Managing the Dual Diagnosis Dilemma of Bipolar Disorder and Substance Abuse in Clinical Settings

OBJECTIVE

Drug addiction is a chronic mental disorder that significantly impacts all aspects of an individual's life, and substance use disorder in patients with bipolar disorder. The objective of this study is to assess the frequency of substance abuse among patients with bipolar spectrum disorder.

METHOD

This cross-sectional study evaluated the frequency of bipolar spectrum disorder in patients taking methadone through various screening measures, including Mini Mental State Examination (MMSE), DSM IV criteria, Mood Disorders Questionnaire (MDQ), Goodwin and Ghaemi's criteria, and Akiskal classification for bipolar disorders.

RESULTS

Out of the total 197 participants in the study, 77 were identified as individuals engaging in poly-substance abuse. The investigation assessed the frequency of bipolar spectrum disorder based on various diagnostic criteria: 24% according to DSM-IV criteria, 29.9% using MDQ, 29.9% based on Ghaemi and Goodwin's criteria, and the highest rate at 48.2% when applying Akiskal's classification.

CONCLUSIONS

This study highlights the high frequency of bipolar disorder among individuals with substance use disorder, especially those with concomitant depression. Therefore, it is crucial to pay special attention to individuals with substance use disorder with co-existing bipolar disorder.

Correlation between emotion dysregulation and mood symptoms of bipolar disorder: A systematic review and meta-analysis

BACKGROUND

Emotion dysregulation (ED) is a transdiagnostic construct characterized by difficulties regulating intense emotions. People with bipolar disorder (BD) are more likely to show ED and use maladaptive emotion regulation strategies than adaptive ones. However, little is known about whether ED in BD is a trait or it is rather an epiphenomenon of mood symptoms.

METHODS

We conducted a systematic review and meta-analysis of the evidence across major literature databases reporting correlations between measures of emotion regulation (overall ED and different emotion regulation strategies) and measures of depressive and (hypo)manic symptoms in BD from inception until April 12th, 2022.

RESULTS

Fourteen studies involving 1371 individuals with BD were included in the qualitative synthesis, of which 11 reported quantitative information and were included in the meta-analysis. ED and maladaptive strategies were significantly higher during periods with more severe mood symptoms, especially depressive ones, while adaptive strategies were lower.

CONCLUSION

ED significantly correlates with BD symptomatology, and it mainly occurs during mood alterations. ED may be a target for specific psychotherapeutic and pharmacological treatments, according to precision psychiatry. However, further studies are needed, including patients with mood episodes and longitudinal design, to provide more robust evidence and explore the causal direction of the associations.

Does Screening for Bipolar Disorders Identify a "Dysregulation of Mood, Energy, and Social Rhythms Syndrome" (DYMERS)? A Heuristic Working Hypothesis

The aim of this paper is to verify if people with a positive score on the Mood Disorder Questionnaire (MDQ) without comorbidity of mood disorders showed a worse level of Health-related Quality of life (HRQol) compared to a control-matched sample of MDQ negatives, identifying a specific syndrome. This is a case-control study based on a database from a community survey. Cases: MDQ-positive without mood disorders; Controls: MDQ negatives matched by sex, age, and psychiatric diagnosis according to the Diagnostic and Statistical Manual of Mental Disorders IV (DSM-IV) criteria. Tools: MDQ, the Advanced Neuropsychiatric Tools and Assessment Schedule (ANTAS) semi-structured interview for psychiatric diagnosis, and the Health Survey Short Form (SF-12) for measuring HRQol. People scoring positive on the MDQ without a diagnosis of mood disorders showed significantly lower scores on the SF-12 compared to people of the same age and of the same sex with an equal diagnosis of psychiatric disorders not related to mood disorders (35.21 ± 6.30 vs. 41.48 ± 3.39, p < 0.0001). In the debate whether a positive score on the MDQ selects an area of "malaise" due to the presence of disorders differing from Bipolar Disorders, or if a positive score on the MDQ may be considered a "subthreshold" form of bipolar disorder in people who may later develop bipolar disorder, a third hypothesis can be advanced, i.e., that a positive score on the MDQ identifies a specific "Dysregulation of Mood, Energy, and Social Rhythms Syndrome" (DYMERS), characterized by a considerable amount of suffering and not attributable to other disorders, and which might represent a trigger for the previously mentioned disorders with which a positive score on the MDQ is associated, probably including, in severe conditions, bipolar disorder.

Recent Advances in Dual Disorders (Addiction and Other Mental Disorders)

In clinical mental health practice, the presence of Dual Disorders (DDs), defined as the comorbidity of at least one Substance Use Disorder (SUD) and another mental disorder in the same person [...].

Prediction of disease comorbidity using explainable artificial intelligence and machine learning techniques: A systematic review

OBJECTIVE

Disease comorbidity is a major challenge in healthcare affecting the patient's quality of life and costs. AI-based prediction of comorbidities can overcome this issue by improving precision medicine and providing holistic care. The objective of this systematic literature review was to identify and summarise existing machine learning (ML) methods for comorbidity prediction and evaluate the interpretability and explainability of the models.

MATERIALS AND METHODS

The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework was used to identify articles in three databases: Ovid Medline, Web of Science and PubMed. The literature search covered a broad range of terms for the prediction of disease comorbidity and ML, including traditional predictive modelling.

RESULTS

Of 829 unique articles, 58 full-text papers were assessed for eligibility. A final set of 22 articles with 61 ML models was included in this review. Of the identified ML models, 33 models achieved relatively high accuracy (80-95%) and AUC (0.80-0.89). Overall, 72% of studies had high or unclear concerns regarding the risk of bias.

DISCUSSION

This systematic review is the first to examine the use of ML and explainable artificial intelligence (XAI) methods for comorbidity prediction. The chosen studies focused on a limited scope of comorbidities ranging from 1 to 34 (mean = 6), and no novel comorbidities were found due to limited phenotypic and genetic data. The lack of standard evaluation for XAI hinders fair comparisons.

CONCLUSION

A broad range of ML methods has been used to predict the comorbidities of various disorders. With further development of explainable ML capacity in the field of comorbidity prediction, there is a significant possibility of identifying unmet health needs by highlighting comorbidities in patient groups that were not previously recognised to be at risk for particular comorbidities.