Comparison of machine learning techniques for the classification of patients with mental and behavioral disorders due to psychotropic consumption in the city of Barranquilla
Published
:Issue
:Section
:License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
Dimensions Metrics
machinelearning, support vector machine, random forest, artificial neural network, substance psychoactive
Substance use disorder contributes to a substantial global burden of disease, despite ongoing efforts by government entities to mitigate this problem. This problem is one of the most attractive current research areas for developing machine learning models. This research study aimed to develop a Machine Learning model for the classification of patients with mental and behavioral disorders due to the consumption of psychotropic substances located in the acute intoxication class or dependency syndrome in the city of Barranquilla. The method used was to train, validate and compare four Machine Learning techniques with databases of patients in Barranquilla. The results revealed that Random Forest and Logistic Regression had the best accuracy (72%). However, Artificial Neural Network is the best model to predict the proportion of positive cases among the detected positive cases. On the other hand, the best predictor of the proportion of positive cases that are well detected is Random Forest, and the best predictor of the proportion of negative cases that are well detected is the Support Vector Machine. Finally, it is worth mentioning that Artificial Neural Network and Random Forest are the best classifiers that AUC records with 80% each. In general terms, Artificial Neural Network and Random Forest showed signs of being a good classifier to discriminate between patients who would potentially be in a case of acute intoxication or dependency syndrome, obtaining average performance values between 80% and 90%.
B.F. Grant et al., “Prevalence and co-occurrence of substance use disorders and independent mood and anxiety disorders - Results from the national epidemiologic survey on alcohol and related conditions,” Arch. Gen. Psychiatry, vol. 61, no. 8, pp. 807–816, 2004
R.C. Kessler, C.B. Nelson, K.A. McGonagle, M. J. Edlund, R. G. Frank, and P. J. Leaf, “The epidemiology of co-occurring addictive and mental disorders: Implications for prevention and service utilization,” Am. J. Orthopsychiatry, vol. 66, no. 1, pp. 17–31, 1996
D. A. Regier et al., “Comorbidity of Mental Disorders With Alcohol and Other Drug Abuse: Results From the Epidemiologic Catchment Area (ECA) Study,” JAMA, vol. 264, no. 19, pp. 2511–2518, 1990
WHO, “Mental Health Action Plan 2013-2020.,” Ginebra, Suiza, 2013
L.M. Squeglia et al., “Neural Predictors of Initiating Alcohol Use During Adolescence,” Am. J. Psychiatry, vol. 174, no. 2, pp. 172–185, Feb. 2017
T. Katsuki, T.K. Mackey, and R. Cuomo, “Establishing a Link Between Prescription Drug Abuse and Illicit Online Pharmacies: Analysis of Twitter Data,” J. Med. INTERNET Res., vol. 17, no. 12, 2015
B. F. Grant, D. A. Dawson, F. S. Stinson, P. S. Chou, W. Kay, and R. Pickering, “The Alcohol Use Disorder and Associated Disabilities Interview Schedule-IV (AUDADIS-IV): reliability of alcohol consumption, tobacco use, family history of depression and psychiatric diagnostic modules in a general population sample,” Drug Alcohol Depend., vol. 71, no. 1, pp. 7–16, Jul. 2003
R. Ali et al., “The alcohol, smoking and substance involvement screening test (ASSIST): development, reliability and feasibility,” ADDICTION, vol. 97, no. 9, pp. 1183–1194, Sep. 2002
J.E. Schulenberg and J. L. Maggs, “A developmental perspective on alcohol use and heavy drinking during adolescence and the transition to young adulthood,” J. Stud. Alcohol, no. 14, pp. 54–70, Mar. 2002
H. W. Perkins, “Social norms and the prevention of alcohol misuse in collegiate contexts,” J. Stud. Alcohol, no. 14, pp. 164–172, Mar. 2002
M. Dennis et al., “The Cannabis Youth Treatment (CYT) Study: Main findings from two randomized trials,” J. Subst. Abuse Treat., vol. 27, no. 3, pp. 197–213, Oct. 2004
R.W. Hingson, T. Heeren, R.C. Zakocs, A. Kopstein, and H. Wechsler, “Magnitude of alcohol-related mortality and morbidity among US college students ages 18-24,” J. Stud. Alcohol, vol. 63, no. 2, pp. 136–144, Mar. 2002
J.R. Greenmyer, M.G. Klug, C. Kambeitz, S. Popova, and L. Burd, “A Multicountry Updated Assessment of the Economic Impact of Fetal Alcohol Spectrum Disorder: Costs for Children and Adults,” J. Addict. Med., vol. 12, no. 6, pp. 466–473, 2018
C. Potier, V. Laprevote, F. Dubois-Arber, O. Cottencin, and B. Rolland, “Supervised injection services: What has been demonstrated? A systematic literature review,” Drug Alcohol Depend., vol. 145, pp. 48–68, 2014
L. Lu, Y. Fang, and X. Wang, “Drug abuse in China: Past, present and future,” Cell. Mol. Neurobiol., vol. 28, no. 4, pp. 479–490, Jun. 2008
R.B. Felson and J. Staff, “Committing Economic Crime for Drug Money,” CRIME Delinq., vol. 63, no. 4, pp. 375–390, 2017
S. Metternich, S. Zoerntlein, T. Schoenberger, and C. Huhn, “Ion mobility spectrometry as a fast screening tool for synthetic cannabinoids to uncover drug trafficking in jail via herbal mixtures, paper, food, and cosmetics,” DRUG Test. Anal., vol. 11, no. 6, pp. 833–846, Jun. 2019
D.S. Dolliver, S. P. Ericson, and K. L. Love, “A Geographic Analysis of Drug Trafficking Patterns on the TOR Network,” Geogr. Rev., vol. 108, no. 1, pp. 45–68, 2018
E.-U. Nelson and I. Obot, “Beyond prohibition: responses to illicit drugs in West Africa in an evolving policy context,” DRUGS AND ALCOHOL TODAY, 2020
S. Gharaei-Manesh, A. Fathzadeh, and R. Taghizadeh-Mehrjardi, “Comparison of artificial neural network and decision tree models in estimating spatial distribution of snow depth in a semi-arid region of Iran,” Cold Reg. Sci. Technol., vol. 122, pp. 26–35, Feb. 2016
Y.S. Kim, “Comparison of the decision tree, artificial neural network, and linear regression methods based on the number and types of independent variables and sample size,” Expert Syst. Appl., vol. 34, no. 2, pp. 1227–1234, Feb. 2008
E. Reza, R. Arash, and M. Behrouz, “Comparison of Classification Methods Based on the Type of Attributes and Sample Size,” J. Converg. Inf. Technol., vol. 4, no. 3, pp. 94–102, Sep. 2009
D.A. Salazar, J.I. Velez, and J.C. Salazar, “Comparison between SVM and Logistic Regression: Which One is Better to Discriminate?,” Rev. Colomb. Estadística, vol. 35, no. 2, pp. 223–237, 2012
J. M. Moguerza and A. Muñoz, “Support Vector Machines with Applications,” Stat. Sci., vol. 21, no. 3, pp. 322–336, 2006
Wasserman, “All of Statistics : A Concise Course in Statistical Inference Brief Contents,” Simulation, vol. C, p. 461, 2004
L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, Oct. 2001
AFCEA International Press, Darpa Neural Network Study. 1988
S. Haykin, Neural networks: A comprehensive foundation. Pearson, 1994
J. Manuel Gutiérrez, “Introducción a las Redes Neuronales,” España, 2016
Substance use disorder contributes to a substantial global burden of disease, despite ongoing efforts by government entities to mitigate this problem. This problem is one of the most attractive current research areas for developing machine learning models. This research study aimed to develop a Machine Learning model for the classification of patients with mental and behavioral disorders due to the consumption of psychotropic substances located in the acute intoxication class or dependency syndrome in the city of Barranquilla. The method used was to train, validate and compare four Machine Learning techniques with databases of patients in Barranquilla. The results revealed that Random Forest and Logistic Regression had the best accuracy (72%). However, Artificial Neural Network is the best model to predict the proportion of positive cases among the detected positive cases. On the other hand, the best predictor of the proportion of positive cases that are well detected is Random Forest, and the best predictor of the proportion of negative cases that are well detected is the Support Vector Machine. Finally, it is worth mentioning that Artificial Neural Network and Random Forest are the best classifiers that AUC records with 80% each. In general terms, Artificial Neural Network and Random Forest showed signs of being a good classifier to discriminate between patients who would potentially be in a case of acute intoxication or dependency syndrome, obtaining average performance values between 80% and 90%.
B.F. Grant et al., “Prevalence and co-occurrence of substance use disorders and independent mood and anxiety disorders - Results from the national epidemiologic survey on alcohol and related conditions,” Arch. Gen. Psychiatry, vol. 61, no. 8, pp. 807–816, 2004
R.C. Kessler, C.B. Nelson, K.A. McGonagle, M. J. Edlund, R. G. Frank, and P. J. Leaf, “The epidemiology of co-occurring addictive and mental disorders: Implications for prevention and service utilization,” Am. J. Orthopsychiatry, vol. 66, no. 1, pp. 17–31, 1996
D. A. Regier et al., “Comorbidity of Mental Disorders With Alcohol and Other Drug Abuse: Results From the Epidemiologic Catchment Area (ECA) Study,” JAMA, vol. 264, no. 19, pp. 2511–2518, 1990
WHO, “Mental Health Action Plan 2013-2020.,” Ginebra, Suiza, 2013
L.M. Squeglia et al., “Neural Predictors of Initiating Alcohol Use During Adolescence,” Am. J. Psychiatry, vol. 174, no. 2, pp. 172–185, Feb. 2017
T. Katsuki, T.K. Mackey, and R. Cuomo, “Establishing a Link Between Prescription Drug Abuse and Illicit Online Pharmacies: Analysis of Twitter Data,” J. Med. INTERNET Res., vol. 17, no. 12, 2015
B. F. Grant, D. A. Dawson, F. S. Stinson, P. S. Chou, W. Kay, and R. Pickering, “The Alcohol Use Disorder and Associated Disabilities Interview Schedule-IV (AUDADIS-IV): reliability of alcohol consumption, tobacco use, family history of depression and psychiatric diagnostic modules in a general population sample,” Drug Alcohol Depend., vol. 71, no. 1, pp. 7–16, Jul. 2003
R. Ali et al., “The alcohol, smoking and substance involvement screening test (ASSIST): development, reliability and feasibility,” ADDICTION, vol. 97, no. 9, pp. 1183–1194, Sep. 2002
J.E. Schulenberg and J. L. Maggs, “A developmental perspective on alcohol use and heavy drinking during adolescence and the transition to young adulthood,” J. Stud. Alcohol, no. 14, pp. 54–70, Mar. 2002
H. W. Perkins, “Social norms and the prevention of alcohol misuse in collegiate contexts,” J. Stud. Alcohol, no. 14, pp. 164–172, Mar. 2002
M. Dennis et al., “The Cannabis Youth Treatment (CYT) Study: Main findings from two randomized trials,” J. Subst. Abuse Treat., vol. 27, no. 3, pp. 197–213, Oct. 2004
R.W. Hingson, T. Heeren, R.C. Zakocs, A. Kopstein, and H. Wechsler, “Magnitude of alcohol-related mortality and morbidity among US college students ages 18-24,” J. Stud. Alcohol, vol. 63, no. 2, pp. 136–144, Mar. 2002
J.R. Greenmyer, M.G. Klug, C. Kambeitz, S. Popova, and L. Burd, “A Multicountry Updated Assessment of the Economic Impact of Fetal Alcohol Spectrum Disorder: Costs for Children and Adults,” J. Addict. Med., vol. 12, no. 6, pp. 466–473, 2018
C. Potier, V. Laprevote, F. Dubois-Arber, O. Cottencin, and B. Rolland, “Supervised injection services: What has been demonstrated? A systematic literature review,” Drug Alcohol Depend., vol. 145, pp. 48–68, 2014
L. Lu, Y. Fang, and X. Wang, “Drug abuse in China: Past, present and future,” Cell. Mol. Neurobiol., vol. 28, no. 4, pp. 479–490, Jun. 2008
R.B. Felson and J. Staff, “Committing Economic Crime for Drug Money,” CRIME Delinq., vol. 63, no. 4, pp. 375–390, 2017
S. Metternich, S. Zoerntlein, T. Schoenberger, and C. Huhn, “Ion mobility spectrometry as a fast screening tool for synthetic cannabinoids to uncover drug trafficking in jail via herbal mixtures, paper, food, and cosmetics,” DRUG Test. Anal., vol. 11, no. 6, pp. 833–846, Jun. 2019
D.S. Dolliver, S. P. Ericson, and K. L. Love, “A Geographic Analysis of Drug Trafficking Patterns on the TOR Network,” Geogr. Rev., vol. 108, no. 1, pp. 45–68, 2018
E.-U. Nelson and I. Obot, “Beyond prohibition: responses to illicit drugs in West Africa in an evolving policy context,” DRUGS AND ALCOHOL TODAY, 2020
S. Gharaei-Manesh, A. Fathzadeh, and R. Taghizadeh-Mehrjardi, “Comparison of artificial neural network and decision tree models in estimating spatial distribution of snow depth in a semi-arid region of Iran,” Cold Reg. Sci. Technol., vol. 122, pp. 26–35, Feb. 2016
Y.S. Kim, “Comparison of the decision tree, artificial neural network, and linear regression methods based on the number and types of independent variables and sample size,” Expert Syst. Appl., vol. 34, no. 2, pp. 1227–1234, Feb. 2008
E. Reza, R. Arash, and M. Behrouz, “Comparison of Classification Methods Based on the Type of Attributes and Sample Size,” J. Converg. Inf. Technol., vol. 4, no. 3, pp. 94–102, Sep. 2009
D.A. Salazar, J.I. Velez, and J.C. Salazar, “Comparison between SVM and Logistic Regression: Which One is Better to Discriminate?,” Rev. Colomb. Estadística, vol. 35, no. 2, pp. 223–237, 2012
J. M. Moguerza and A. Muñoz, “Support Vector Machines with Applications,” Stat. Sci., vol. 21, no. 3, pp. 322–336, 2006
Wasserman, “All of Statistics : A Concise Course in Statistical Inference Brief Contents,” Simulation, vol. C, p. 461, 2004
L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, Oct. 2001
AFCEA International Press, Darpa Neural Network Study. 1988
S. Haykin, Neural networks: A comprehensive foundation. Pearson, 1994
J. Manuel Gutiérrez, “Introducción a las Redes Neuronales,” España, 2016