The Use of Artificial Neural Networks Methodology in the Assessment of “Vulnerability” to Heroin Use among Army Corps Soldiers: A Preliminary Study of 170 Cases inside the Military Hospital of Legal Medicine of Verona

Abstract

This article describes a preliminary study of screening/diagnostic instruments for prediction for large-scale application in the military field at the Neuropsychiatric Department of the Military Hospital of Legal Medicine of Verona and for the prevention of self-destructive behaviors, particularly through the use of drugs. 170 subjects divided into three subsamples were examined. The first subsample was characterized by a strong tendency towards normalcy, the second by a strong tendency towards pathology, and the third by a great variety of expressions of psychological and social problems, which were not necessarily related to drug use. These subjects were administered a questionnaire designed according to Squashing Theory principles (Buscema, 1994a). Answers were processed by an Artificial Neural Network created by Semeion in Rome (Buscema, 1996) and were compared with a standard clinical psychiatric assessment report and with the results of psychodiagnostic tests. Results document ANNs' remarkable ability to recognize subjects with declared, in exordium and "at risk" pathological behaviors. Blind results on learning and trial samples show a very high predictive capacity (over 90%). A comparison with the examined subjects' clinical report and the results of the first follow-up also document very high agreements. The broad variation of answers obtained in the third subsample allows further methodological reflections on the contribution of Artificial Neural Networks and Squashing Theory to the study of deviance, for both sociologists and clinicians, and not only for those in the field of drug addiction.

Theories of addiction

“…This has almost certainly fuelled advances in prevention and treatment. Unfortunately, the environment has also been shifting Cheng et al, 2000 A genetic analysis of smoking behavior in family members of older adult males Clapper et al, 1995 Adolescent problem behaviors as predictors of adult alcohol diagnoses Cunningham et al, 1992 Genetic differences in the rewarding and activating effects of morphine and ethanol el- Guebaly et al, 1993 Attachment among adult children of alcoholics Jansen et al, 1989 Restrained eaters are rapidly habituating sensation seekers Johnson & The relationship between ethnicity, gender and alcohol consumption: a strategy Glassman, 1998 for testing competing models Lewis, 1984 Alcoholism, antisocial personality, narcotic addiction: an integrative approach Shoham et al, 1984 Personality core dynamics and drug preference Silvia, Sorell & Biopsychosocial discriminators of alcoholic and nonalcoholic women Busch-Rossnagel, 1988 Speri et al, 1998 The use of arti cial neural networks methodology in the assessment of "vulnerability" to heroin use among army corps soldiers: a preliminary study of 170 cases inside the Military Hospital of Legal Medicine of Verona True et al, 1997 Genetic and environmental contributions to smoking Breslin et al, 1995 Stress and alcohol: the moderating effect of chronic stress on the acute stressintoxication relationship Davis & Tunks, 1990 Environments and addiction: a proposed taxonomy DeFeudis, 1978 Environmental theory of drug addiction Hajema & Knibbe, 1998 Changes in social roles as predictors of changes in drinking behaviour Grun & McKeigue, 2000 Prevalence of excessive gambling before and after introduction of a national lottery in the United Kingdom: another example of the single distribution theory Keeler et al,1993 Taxation, regulation, and addiction: a demand function for cigarettes based on time-series evidence Liu, Liu, Hammitt The price elasticity of opium in Taiwan, 1914-1942& Chou, 1999Pacula, 1997 Economic modelling of the gateway effect Richman & Dunham, A sociological theory of the diffusion and social setting of opiate addiction 1976 Romelsjo & Lundberg, The changes in the social class distribution of moderate and high alcohol 1996…”

Técnicas de clasificación de data mining: una aplicación al consumo de tabaco en adolescentes

“…The predictive capacity of the eight models was always greater than 91%. Meanwhile, Speri et al (1998) managed to correctly classify 94% of a test group made up of drug addicts and control subjects. Finally, Maurelli and Di Giulio (1998) managed to discriminate between ‗moderate' alcoholics and ‗serious' alcoholics using seven Data Mining techniques, reaching a percentage of correct classifications which oscillated between 73% and 86%.…”

Predicción del consumo de éxtasis a partir de redes neuronales artificiales

“…En este sentido, el Centro de Investigación Semeion de las Ciencias de la Comunicación (Roma, Italia), fundado y dirigido por Massimo Buscema, puede ser considerado como pionero en la aplicación de las RNA en este campo. Los investigadores de dicho centro han construido diferentes modelos de red con el fin de predecir el consumo de droga -sobre todo heroína- (Buscema, 1995;Buscema, Intraligi y Bricolo, 1998;Maurelli y Di Giulio, 1998;Speri, Schilirò, Bezzetto et al, 1998), extraer las características prototípicas del sujeto adicto (Buscema, Intraligi y Bricolo, 1998) y así, determinar el tratamiento más adecuado en función de esas características (Massini y Shabtay, 1998). Aunque los resultados son preliminares, estos trabajos demuestran que los buenos resultados obtenidos hasta el momento en las diferentes áreas de conocimiento se pueden extender al campo de las adicciones.…”