Related Experiment Video
Updated: Jun 15, 2026
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Optimizing DSM-IV-TR classification accuracy: a brief biosocial screen for detecting current gambling disorders among
Line Gebauer1, Richard LaBrie, Howard J Shaffer
1Centre of Functionally Integrative Neuroscience, University of Aarhus, Denmark.
Objective:
To develop a pathological gambling (PG) screen for efficient application to the household population and for clinicians to use with treatment seekers.
Method:
We applied a series of multivariate discriminant functions to past-12-month Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition, Text Revision (DSM-IV-TR)-based, gambling-related problems; the National Epidemiologic Survey on Alcohol and Related Conditions (NESARC) measured and collected this data. The NESARC conducted computer-assisted personal interviews with 43 093 households and identified the largest sample of pathological gamblers drawn from the general household population.
Results:
We created a 3-item, brief biosocial gambling screen (BBGS) with high sensitivity (Sensitivity = 0.96; 76 of 79 pathological gamblers correctly identified) and high specificity (Specificity = 0.99; 10 892 of 11 027 nonpathological gamblers correctly identified).
Conclusions:
Major US studies reveal extensive comorbidity of PG with other mental illnesses. The BBGS features psychometric advantages for health care providers that should encourage clinicians and epidemiologists to consider current PG along with other problems. The BBGS is practical for clinical application because it uses only 3 items and they are easy to ask, answer, and include in all modes of interviewing, including self-administered surveys. The BBGS has a strong theoretical foundation because it includes 1 item from each of the addiction syndrome 3 domains: neuroadaptation (for example, withdrawal); psychosocial characteristics (for example, lying); and adverse social consequences of gambling (for example, obtaining money from others).
