Predictors of suicide attempt in patients with obsessive-compulsive disorder: an exploratory study with machine learning analysis

Abstract Background Patients with obsessive-compulsive disorder (OCD) are at increased risk for suicide attempt (SA) compared to the general population. However, the significant risk factors for SA in this population remains unclear – whether these factors are associated with the disorder itself or related to extrinsic factors, such as comorbidities and sociodemographic variables. This study aimed to identify predictors of SA in OCD patients using a machine learning algorithm. Methods A total of 959 outpatients with OCD were included. An elastic net model was performed to recognize the predictors of SA among OCD patients, using clinical and sociodemographic variables. Results The prevalence of SA in our sample was 10.8%. Relevant predictors of SA founded by the elastic net algorithm were the following: previous suicide planning, previous suicide thoughts, lifetime depressive episode, and intermittent explosive disorder. Our elastic net model had a good performance and found an area under the curve of 0.95. Conclusions This is the first study to evaluate risk factors for SA among OCD patients using machine learning algorithms. Our results demonstrate an accurate risk algorithm can be created using clinical and sociodemographic variables. All aspects of suicidal phenomena need to be carefully investigated by clinicians in every evaluation of OCD patients. Particular attention should be given to comorbidity with depressive symptoms.

Download Full-text

Risk factors prospectively associated with adult obsessive–compulsive symptom dimensions and obsessive–compulsive disorder

Psychological Medicine ◽

10.1017/s0033291711000894 ◽

2011 ◽

Vol 41 (12) ◽

pp. 2495-2506 ◽

Cited By ~ 60

Author(s):

J. R. Grisham ◽

M. A. Fullana ◽

D. Mataix-Cols ◽

T. E. Moffitt ◽

A. Caspi ◽

...

Keyword(s):

Risk Factors ◽

Obsessive Compulsive Disorder ◽

Internalizing Symptoms ◽

Diagnostic Interview ◽

Control Group ◽

Obsessive Compulsive ◽

Specific Symptom ◽

Symptom Dimensions ◽

Compulsive Disorder ◽

Increased Risk

BackgroundVery few longitudinal studies have evaluated prospective neurodevelopmental and psychosocial risk factors for obsessive–compulsive disorder (OCD). Furthermore, despite the heterogeneous nature of OCD, no research has examined risk factors for its primary symptom dimensions, such as contamination/washing.MethodPotential risk factors for symptoms or diagnosis of OCD in adulthood and for specific adult obsessive–compulsive (OC) symptom dimensions were examined in the Dunedin Study birth cohort. The presence of obsessions and compulsions and psychological disorders was assessed using the Diagnostic Interview Schedule (DIS) at ages 26 and 32 years. Individuals with a diagnosis of OCD at either age (n=36) were compared to both a healthy control group (n=613) and an anxious control group (n=310) to determine whether associations between a risk factor and an OCD diagnosis were specific.ResultsChildhood neurodevelopmental, behavioral, personality and environmental risk factors were associated with a diagnosis of OCD and with OC symptoms at ages 26 and 32. Social isolation, retrospectively reported physical abuse and negative emotionality were specific predictors of an adult OCD diagnosis. Of note, most risk factors were associated with OC symptoms in adulthood and several risk factors predicted specific OCD dimensions. Perinatal insults were linked to increased risk for symmetry/ordering and shameful thoughts dimensions, whereas poor childhood motor skills predicted the harm/checking dimension. Difficult temperament, internalizing symptoms and conduct problems in childhood also predicted specific symptom dimensions and lower IQ non-specifically predicted increased risk for most dimensions.ConclusionsThe current findings underscore the need for a dimensional approach in evaluating childhood risk factors for obsessions and compulsions.

Download Full-text

How New Technologies Can Improve Prediction, Assessment, and Intervention in Obsessive-Compulsive Disorder (e-OCD): Review

JMIR Mental Health ◽

10.2196/11643 ◽

2019 ◽

Vol 6 (12) ◽

pp. e11643 ◽

Cited By ~ 3

Author(s):

Florian Ferreri ◽

Alexis Bourla ◽

Charles-Siegfried Peretti ◽

Tomoyuki Segawa ◽

Nemat Jaafari ◽

...

Keyword(s):

Machine Learning ◽

Virtual Reality ◽

Obsessive Compulsive Disorder ◽

New Technologies ◽

Assessment Tools ◽

Clinical Practices ◽

Obsessive Compulsive ◽

Compulsive Disorder ◽

Pubmed Database ◽

The Impact

Background New technologies are set to profoundly change the way we understand and manage psychiatric disorders, including obsessive-compulsive disorder (OCD). Developments in imaging and biomarkers, along with medical informatics, may well allow for better assessments and interventions in the future. Recent advances in the concept of digital phenotype, which involves using computerized measurement tools to capture the characteristics of a given psychiatric disorder, is one paradigmatic example. Objective The impact of new technologies on health professionals’ practice in OCD care remains to be determined. Recent developments could disrupt not just their clinical practices, but also their beliefs, ethics, and representations, even going so far as to question their professional culture. This study aimed to conduct an extensive review of new technologies in OCD. Methods We conducted the review by looking for titles in the PubMed database up to December 2017 that contained the following terms: [Obsessive] AND [Smartphone] OR [phone] OR [Internet] OR [Device] OR [Wearable] OR [Mobile] OR [Machine learning] OR [Artificial] OR [Biofeedback] OR [Neurofeedback] OR [Momentary] OR [Computerized] OR [Heart rate variability] OR [actigraphy] OR [actimetry] OR [digital] OR [virtual reality] OR [Tele] OR [video]. Results We analyzed 364 articles, of which 62 were included. Our review was divided into 3 parts: prediction, assessment (including diagnosis, screening, and monitoring), and intervention. Conclusions The review showed that the place of connected objects, machine learning, and remote monitoring has yet to be defined in OCD. Smartphone assessment apps and the Web Screening Questionnaire demonstrated good sensitivity and adequate specificity for detecting OCD symptoms when compared with a full-length structured clinical interview. The ecological momentary assessment procedure may also represent a worthy addition to the current suite of assessment tools. In the field of intervention, CBT supported by smartphone, internet, or computer may not be more effective than that delivered by a qualified practitioner, but it is easy to use, well accepted by patients, reproducible, and cost-effective. Finally, new technologies are enabling the development of new therapies, including biofeedback and virtual reality, which focus on the learning of coping skills. For them to be used, these tools must be properly explained and tailored to individual physician and patient profiles.

Download Full-text

Anxiety and Shame as Risk Factors for Depression, Suicidality, and Functional Impairment in Body Dysmorphic Disorder and Obsessive Compulsive Disorder

The Journal of Nervous and Mental Disease ◽

10.1097/nmd.0000000000000498 ◽

2016 ◽

Vol 204 (11) ◽

pp. 832-839 ◽

Cited By ~ 24

Author(s):

Hilary Weingarden ◽

Keith D. Renshaw ◽

Sabine Wilhelm ◽

June P. Tangney ◽

Jennifer DiMauro

Keyword(s):

Risk Factors ◽

Obsessive Compulsive Disorder ◽

Functional Impairment ◽

Body Dysmorphic Disorder ◽

Obsessive Compulsive ◽

Compulsive Disorder

Download Full-text

The analytical epidemiology of obsessive–compulsive disorder: Risk factors and correlates

Progress in Neuro-Psychopharmacology and Biological Psychiatry ◽

10.1016/j.pnpbp.2007.06.024 ◽

2008 ◽

Vol 32 (1) ◽

pp. 1-15 ◽

Cited By ~ 59

Author(s):

Leonardo F. Fontenelle ◽

Gregor Hasler

Keyword(s):

Risk Factors ◽

Obsessive Compulsive Disorder ◽

Obsessive Compulsive ◽

Compulsive Disorder ◽

Disorder Risk

Download Full-text

When you meet: assessing obsessive-compulsive disorder

Cognitive Behaviour Therapy for Obsessive-compulsive Disorder ◽

10.1093/med-psych/9780198703266.003.0002 ◽

2017 ◽

pp. 51-66

Author(s):

Victoria Bream ◽

Fiona Challacombe ◽

Asmita Palmer ◽

Paul Salkovskis

Keyword(s):

Risk Factors ◽

Risk Assessment ◽

Obsessive Compulsive Disorder ◽

Health Anxiety ◽

Assessment Tools ◽

Generalized Anxiety ◽

Presenting Problems ◽

Obsessive Compulsive ◽

Compulsive Disorder ◽

Experienced Clinician

This chapter provides a practical guide to assessing obsessive-compulsive disorder (OCD) that is both informative to the inexperienced clinician and addresses questions raised by the experienced clinician. It will summarize the diagnostic criteria for OCD, including advice on making a differential diagnosis when presented with symptoms that are associated with other disorders; for example, differentiating OCD from psychosis, generalized anxiety disorder, or health anxiety. It will guide the reader through the process of conducting a thorough assessment of the patient’s presenting problems, including OCD and any comorbid problems. The chapter will offer guidance on how to engage the person with OCD and promote trust. There is clear guidance on risk assessment, differentiating between primary risk factors (which clinicians are typically very good at assessing), and secondary risk factors (which may easily be overlooked). Advice on structuring an assessment and on appropriate assessment tools is provided.

Download Full-text

T102C and –1438 G/A polymorphisms of the 5-HT2A receptor gene in Turkish patients with obsessive–compulsive disorder

European Psychiatry ◽

10.1016/s0924-9338(03)00066-x ◽

2003 ◽

Vol 18 (5) ◽

pp. 249-254 ◽

Cited By ~ 32

Author(s):

Şenel Tot ◽

M. Emin Erdal ◽

Kemal Yazıcı ◽

Aylin Ertekin Yazıcı ◽

Özmen Metin

Keyword(s):

Obsessive Compulsive Disorder ◽

Receptor Gene ◽

Clinical Severity ◽

Genotype Distribution ◽

Healthy Controls ◽

Obsessive Compulsive ◽

Compulsive Disorder ◽

Increased Risk ◽

T102c Polymorphism ◽

Turkish Patients

AbstractObjectiveThis study aimed to investigate the possible association between T102C and –1438 G/A polymorphism in the 5-HT2A receptor gene and susceptibility to and clinical features of obsessive–compulsive disorder (OCD).MethodFifty-eight patients with OCD and 83 healthy controls were included in the study. All patients were interviewed and rated by Yale-Brown Obsessive–Compulsive Scale. T102C and –1438 G/A polymorphisms of 5-HT2A receptor gene were determined by PCR technique in DNAs of peripheral leucocytes.ResultsOCD patients and healthy controls did not show significant differences in genotype distribution for both polymorphisms investigated. We found that frequencies of the TT genotype for T102C polymorphism and the AA genotype for –1438 G/A polymorphism were significantly higher in patients with severe OCD compared to those with moderate or moderate–severe OCD.ConclusionThe –1438 G/A and T102C polymorphisms of the 5-HT2A receptor gene are not associated with an increased risk of OCD. Our data suggest that the TT genotype of T102C and the AA genotype of –1438 G/A polymorphism might be a factor in clinical severity of OCD.

Download Full-text