Dataset Information

Problematic internet use (PIU): Associations with the impulsive-compulsive spectrum. An application of machine learning in psychiatry.

ABSTRACT: Problematic internet use is common, functionally impairing, and in need of further study. Its relationship with obsessive-compulsive and impulsive disorders is unclear. Our objective was to evaluate whether problematic internet use can be predicted from recognised forms of impulsive and compulsive traits and symptomatology. We recruited volunteers aged 18 and older using media advertisements at two sites (Chicago USA, and Stellenbosch, South Africa) to complete an extensive online survey. State-of-the-art out-of-sample evaluation of machine learning predictive models was used, which included Logistic Regression, Random Forests and Naïve Bayes. Problematic internet use was identified using the Internet Addiction Test (IAT). 2006 complete cases were analysed, of whom 181 (9.0%) had moderate/severe problematic internet use. Using Logistic Regression and Naïve Bayes we produced a classification prediction with a receiver operating characteristic area under the curve (ROC-AUC) of 0.83 (SD 0.03) whereas using a Random Forests algorithm the prediction ROC-AUC was 0.84 (SD 0.03) [all three models superior to baseline models p < 0.0001]. The models showed robust transfer between the study sites in all validation sets [p < 0.0001]. Prediction of problematic internet use was possible using specific measures of impulsivity and compulsivity in a population of volunteers. Moreover, this study offers proof-of-concept in support of using machine learning in psychiatry to demonstrate replicability of results across geographically and culturally distinct settings.

SUBMITTER: Ioannidis K

PROVIDER: S-EPMC5119576 | biostudies-literature | 2016 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Problematic internet use (PIU): Associations with the impulsive-compulsive spectrum. An application of machine learning in psychiatry.

Ioannidis Konstantinos K Chamberlain Samuel R SR Treder Matthias S MS Kiraly Franz F Leppink Eric W EW Redden Sarah A SA Stein Dan J DJ Lochner Christine C Grant Jon E JE

Journal of psychiatric research 20160815

Problematic internet use is common, functionally impairing, and in need of further study. Its relationship with obsessive-compulsive and impulsive disorders is unclear. Our objective was to evaluate whether problematic internet use can be predicted from recognised forms of impulsive and compulsive traits and symptomatology. We recruited volunteers aged 18 and older using media advertisements at two sites (Chicago USA, and Stellenbosch, South Africa) to complete an extensive online survey. State- ...[more]

PMID: 27580487

Similar Datasets

Project description:BACKGROUND:Problematic use of the Internet has been highlighted as needing further study by international bodies, including the European Union and American Psychiatric Association. Knowledge regarding the optimal classification of problematic use of the Internet, subtypes, and associations with clinical disorders has been hindered by reliance on measurement instruments characterized by limited psychometric properties and external validation. METHODS:Non-treatment seeking individuals were recruited from the community of Stellenbosch, South Africa (N?=?1661), and Chicago, United States of America (N?=?827). Participants completed an online version of the Internet Addiction Test, a widely used measure of problematic use of the Internet consisting of 20-items, measured on a 5-point Likert-scale. The online questions also included demographic measures, time spent engaging in different online activities, and clinical scales. The psychometric properties of the Internet Addiction Test, and potential problematic use of the Internet subtypes, were characterized using factor analysis and latent class analysis. RESULTS:Internet Addiction Test data were optimally conceptualized as unidimensional. Latent class analysis identified two groups: those essentially free from Internet use problems, and those with problematic use of the Internet situated along a unidimensional spectrum. Internet Addiction Test scores clearly differentiated these groups, but with different optimal cut-offs at each site. In the larger Stellenbosch dataset, there was evidence for two subtypes of problematic use of the Internet that differed in severity: a lower severity "impulsive" subtype (linked with attention-deficit hyperactivity disorder), and a higher severity "compulsive" subtype (linked with obsessive-compulsive personality traits). CONCLUSIONS:Problematic use of the Internet as measured by the Internet Addiction Test reflects a quasi-trait - a unipolar dimension in which most variance is restricted to a subset of people with problems regulating Internet use. There was no evidence for subtypes based on the type of online activities engaged in, which increased similarly with overall severity of Internet use problems. Measures of comorbid psychiatric symptoms, along with impulsivity, and compulsivity, appear valuable for differentiating clinical subtypes and could be included in the development of new instruments for assessing the presence and severity of Internet use problems.

Project description:ObjectiveYoung adulthood is a crucial neurodevelopmental period during which impulsive and compulsive problem behaviours commonly emerge. While traditionally considered diametrically opposed, impulsive and compulsive symptoms tend to co-occur. The objectives of this study were as follows: (a) to identify the optimal trans-diagnostic structural framework for measuring impulsive and compulsive problem behaviours, and (b) to use this optimal framework to identify common/distinct antecedents of these latent phenotypes.MethodIn total, 654 young adults were recruited as part of the Neuroscience in Psychiatry Network, a population-based cohort in the United Kingdom. The optimal trans-diagnostic structural model capturing 33 types of impulsive and compulsive problem behaviours was identified. Baseline predictors of subsequent impulsive and compulsive trans-diagnostic phenotypes were characterised, along with cross-sectional associations, using partial least squares.ResultsCurrent problem behaviours were optimally explained by a bi-factor model, which yielded dissociable measures of impulsivity and compulsivity, as well as a general disinhibition factor. Impulsive problem behaviours were significantly explained by prior antisocial and impulsive personality traits, male gender, general distress, perceived dysfunctional parenting and teasing/arguments within friendships. Compulsive problem behaviours were significantly explained by prior compulsive traits and female gender.ConclusionThis study demonstrates that trans-diagnostic phenotypes of 33 impulsive and compulsive problem behaviours are identifiable in young adults, utilising a bi-factor model based on responses to a single questionnaire. Furthermore, these phenotypes have different antecedents. The findings yield a new framework for fractionating impulsivity and compulsivity, and suggest different early intervention targets to avert emergence of problem behaviours. This framework may be useful for future biological and clinical dissection of impulsivity and compulsivity.

Dataset Information

Problematic internet use (PIU): Associations with the impulsive-compulsive spectrum. An application of machine learning in psychiatry.

Publications

Problematic internet use (PIU): Associations with the impulsive-compulsive spectrum. An application of machine learning in psychiatry.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets