Antonio Cerasa1, Danilo Lofaro2, Paolo Cavedini3, Iolanda Martino4, Antonella Bruni5, Alessia Sarica4, Domenico Mauro6, Giuseppe Merante7, Ilaria Rossomanno4, Maria Rizzuto4, Antonio Palmacci8, Benedetta Aquino9, Pasquale De Fazio5, Giampaolo R Perna10, Elena Vanni3, Giuseppe Olivadese4, Domenico Conforti11, Gennarina Arabia12, Aldo Quattrone13. 1. Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), 88100 Catanzaro, Italy; S. Anna Institute and Research in Advanced Neurorehabilitation (RAN), 88900 Crotone, Italy. Electronic address: antonio.cerasa76@gmail.com. 2. de-Health Lab, Department of Mechanical, Energy, Management Engineering, University of Calabria, 87036 Rende (CS), Italy; Kidney and Transplantation Research Center, Annunziata Hospital, 87100 Cosenza, Italy. 3. Department of Clinical Neurosciences, Hermanas Hospitalarias, Villa San Benedetto Menni Hospital, FoRiPsi, 22032, Albese con Cassano, Como, Italy. 4. Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), 88100 Catanzaro, Italy. 5. Psychiatric Unit, Department of Health Science, "Magna Graecia" University, 88100, Catanzaro, Italy. 6. Centro Clinico "San Vitaliano" - Malattie Neuromuscolari, Centro di Riabilitazione, 88100 Catanzaro, Italy. 7. Ascoc, Scuola di Psicoterapia cognitivo-comportamentale. 87040, Castrolibero (CS), Italy. 8. Innovation Lab, Infobyte@, 80124 Naples, Italy. 9. Kidney and Transplantation Research Center, Annunziata Hospital, 87100 Cosenza, Italy. 10. Department of Clinical Neurosciences, Hermanas Hospitalarias, Villa San Benedetto Menni Hospital, FoRiPsi, 22032, Albese con Cassano, Como, Italy; Department of Psychiatry and Neuropsychology, Faculty of Health, Medicine and Life Sciences, Maastricht University, 6200, Maastricht, The Netherlands; Department of Psychiatry and Behavioral Sciences, Leonard Miller School of Medicine, Miami University, 33136 -1015, Miami, USA. 11. de-Health Lab, Department of Mechanical, Energy, Management Engineering, University of Calabria, 87036 Rende (CS), Italy. 12. Institute of Neurology, Department of Medicine, "Magna Graecia" University, 88100 Catanzaro, Italy. 13. Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), 88100 Catanzaro, Italy; Institute of Neurology, Department of Medicine, "Magna Graecia" University, 88100 Catanzaro, Italy.
Abstract
BACKGROUND: The application of artificial intelligence to extract predictors of Gambling disorder (GD) is a new field of study. A plethora of studies have suggested that maladaptive personality dispositions may serve as risk factors for GD. NEW METHOD: Here, we used Classification and Regression Trees algorithm to identify multivariate predictive patterns of personality profiles that could identify GD patients from healthy controls at an individual level. Forty psychiatric patients, recruited from specialized gambling clinics, without any additional comorbidity and 160 matched healthy controls completed the Five-Factor model of personality as measured by the NEO-PI-R, which were used to build the classification model. RESULTS: Classification algorithm was able to discriminate individuals with GD from controls with an AUC of 77.3% (95% CI 0.65-0.88, p<0.0001). A multidimensional construct of traits including sub-facets of openness, neuroticism and conscientiousness was employed by algorithm for classification detection. COMPARISON WITH EXISTING METHOD(S): To the best of our knowledge, this is the first study that combines behavioral data with machine learning approach useful to extract multidimensional features characterizing GD realm. CONCLUSION: Our study provides a proof-of-concept demonstrating the potential of the proposed approach for GD diagnosis. The multivariate combination of personality facets characterizing individuals with GD can potentially be used to assess subjects' vulnerability in clinical setting.
BACKGROUND: The application of artificial intelligence to extract predictors of Gambling disorder (GD) is a new field of study. A plethora of studies have suggested that maladaptive personality dispositions may serve as risk factors for GD. NEW METHOD: Here, we used Classification and Regression Trees algorithm to identify multivariate predictive patterns of personality profiles that could identify GDpatients from healthy controls at an individual level. Forty psychiatricpatients, recruited from specialized gambling clinics, without any additional comorbidity and 160 matched healthy controls completed the Five-Factor model of personality as measured by the NEO-PI-R, which were used to build the classification model. RESULTS: Classification algorithm was able to discriminate individuals with GD from controls with an AUC of 77.3% (95% CI 0.65-0.88, p<0.0001). A multidimensional construct of traits including sub-facets of openness, neuroticism and conscientiousness was employed by algorithm for classification detection. COMPARISON WITH EXISTING METHOD(S): To the best of our knowledge, this is the first study that combines behavioral data with machine learning approach useful to extract multidimensional features characterizing GD realm. CONCLUSION: Our study provides a proof-of-concept demonstrating the potential of the proposed approach for GD diagnosis. The multivariate combination of personality facets characterizing individuals with GD can potentially be used to assess subjects' vulnerability in clinical setting.