A prediction modelling and pattern detection approach for the first-episode psychosis associated to cannabis use: (extended peer-reviewed conference abstract)

TY - CHAP

T1 - A prediction modelling and pattern detection approach for the first-episode psychosis associated to cannabis use

T2 - 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016

AU - Alghamdi, Wajdi

AU - Stamate, Daniel

AU - Vang, Katherine

AU - Stahl, Daniel

AU - Colizzi, Marco

AU - Tripoli, Giada

AU - Quattrone, Diego

AU - Ajnakina, Olesya

AU - Murray, Robin M.

AU - Di Forti, Marta

PY - 2017/2/2

Y1 - 2017/2/2

N2 - Over the last two decades, a significant body of research has established a link between cannabis use and psychotic outcomes. In this study, we aim to propose a novel symbiotic machine learning and statistical approach to pattern detection and to developing predictive models for the onset of first-episode psychosis. The data used has been gathered from real cases in cooperation with a medical research institution, and comprises a wide set of variables including demographic, drug-related, as well as several variables specifically related to the cannabis use. Our approach is built upon several machine learning techniques whose predictive models have been optimised in a computationally intensive framework. The ability of these models to predict first-episode psychosis has been extensively tested through large scale Monte Carlo simulations. Our results show that Boosted Classification Trees outperform other models in this context, and have significant predictive ability despite a large number of missing values in the data. Furthermore, we extended our approach by further investigating how different patterns of cannabis use relate to new cases of psychosis, via association analysis and Bayesian techniques.

AB - Over the last two decades, a significant body of research has established a link between cannabis use and psychotic outcomes. In this study, we aim to propose a novel symbiotic machine learning and statistical approach to pattern detection and to developing predictive models for the onset of first-episode psychosis. The data used has been gathered from real cases in cooperation with a medical research institution, and comprises a wide set of variables including demographic, drug-related, as well as several variables specifically related to the cannabis use. Our approach is built upon several machine learning techniques whose predictive models have been optimised in a computationally intensive framework. The ability of these models to predict first-episode psychosis has been extensively tested through large scale Monte Carlo simulations. Our results show that Boosted Classification Trees outperform other models in this context, and have significant predictive ability despite a large number of missing values in the data. Furthermore, we extended our approach by further investigating how different patterns of cannabis use relate to new cases of psychosis, via association analysis and Bayesian techniques.

KW - Association analysis

KW - Bayesian inference

KW - Cannabis use

KW - Classification

KW - Monte Carlo simulation

KW - Precision medicine

KW - Predicting first-episode psychosis

KW - Prediction modelling

UR - http://www.scopus.com/inward/record.url?scp=85015434416&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2016.0148

DO - 10.1109/ICMLA.2016.0148

M3 - Conference paper

AN - SCOPUS:85015434416

SN - 9781509061662

SP - 825

EP - 830

BT - Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 18 December 2016 through 20 December 2016

ER -