Can Artificial Neural Networks Predict Psychiatric Conditions Associated with Cannabis Use?
This data-driven computational psychiatry research proposes a novel machine learning approach to developing predictive models for the onset of first-episode psychosis, based on artificial neural networks. The performance capabilities of the predictive models are enhanced and evaluated by a methodology consisting of novel model optimisation and testing, which integrates a phase of model tuning, a phase of model post-processing with ROC optimisation based on maximum accuracy, Youden and top-left methods, and a model evaluation with the k-fold cross-testing methodology. We further extended our framework by investigating the cannabis use attributes’ predictive power, and demonstrating statistically that their presence in the dataset enhances the prediction performance of the neural network models. Finally, the model stability is explored via simulations with 1000 repetitions of the model building and evaluation experiments. The results show that our best Neural Network model’s average accuracy of predicting first-episode psychosis, which is evaluated with Monte Carlo, is above 80%.
KeywordsMachine learning Neural networks Prediction modelling ROC optimisation Monte carlo Computational psychiatry Cannabis Psychosis
- 1.United Nations Office on Drugs and Crime, World Drug Report, United Nations publication, Sales No. E.16.XI.7 (2016)Google Scholar
- 2.Radhakrishnan, R., Wilkinson, S., Dsouza, D.: Gone to pot: a review of the association between cannabis and psychosis. Front. Psychiatry 5 (2014)Google Scholar
- 4.Alghamdi, W., Stamate, D., et al.: A prediction modelling and pattern detection approach for the first-episode psychosis associated to cannabis use. In: 15th IEEE International Conference on Machine Learning and Applications, pp. 825–830 (2016)Google Scholar
- 5.Zhou, H., Tang, J., Zheng, H.: Machine learning for medical applications. Sci. World J., 20, 1 (2015)Google Scholar
- 8.Katrinecz, A., Stamate, D., et al.: Predicting psychosis using the experience sampling method with mobile apps. In: 16th IEEE International Conference on Machine Learning and Applications (2017)Google Scholar
- 9.Belgrave, D., Cassidy, R., Stamate, D., et al.: Predictive modelling strategies to understand heterogeneous manifestations of asthma in early life. In: 16th IEEE International Conference on Machine Learning and Applications (2017)Google Scholar
- 12.Yan, Y., Qin, X., et al.: A restricted Boltzmann machine based two-lead electrocardiography classification. In: Proceedings of 12th International Conference on Wearable Implantable Body Sensor Networks (2015)Google Scholar
- 13.Liaw, A., Wiener, M.: Classification and regression by random forest. R News 2(3), 18–22 (2002)Google Scholar
- 14.Qazi, N., Raza, K.: Effect of feature selection, SMOTE and under sampling on class imbalance classification. In: 2012 UKSim 14th International Conference on Computer Modelling and Simulation, pp. 145–150 (2012)Google Scholar
- 18.Cran.r-project.org.: The Comprehensive R Archive Network (2018). https://cran.r-project.org/. Accessed 2 Jan 2018