HomeCannabis MedicineValidation of a Bayesian learning model to predict the risk for cannabis use disorder

Validation of a Bayesian learning model to predict the risk for cannabis use disorder

July 15, 2023

Addict Behav. 2023 Jul 7;146:107799. doi: 10.1016/j.addbeh.2023.107799. Online ahead of print.

ABSTRACT

BACKGROUND: Cannabis use disorder (CUD) is a growing public health problem. Early identification of adolescents and young adults at risk of developing CUD in the future may help stem this trend. A logistic regression model fitted using a Bayesian learning approach was developed recently to predict the risk of future CUD based on seven risk factors in adolescence and youth. A nationally representative longitudinal dataset, Add Health was used to train the model (henceforth referred as Add Health model).

METHODS: We validated the Add Health model on two cohorts, namely, Michigan Longitudinal Study (MLS) and Christchurch Health and Development Study (CHDS) using longitudinal data from participants until they were approximately 30 years old (to be consistent with the training data from Add Health). If a participant was diagnosed with CUD at any age during this period, they were considered a case. We calculated the area under the curve (AUC) and the ratio of expected and observed number of cases (E/O). We also explored recalibrating the model to account for differences in population prevalence.

RESULTS: The cohort sizes used for validation were 424 (53 cases) for MLS and 637 (105 cases) for CHDS. AUCs for the two cohorts were 0.66 (MLS) and 0.73 (CHDS) and the corresponding E/O ratios (after recalibration) were 0.995 and 0.999.

CONCLUSION: The external validation of the Add Health model on two different cohorts lends confidence to the model’s ability to identify adolescent or young adult cannabis users at high risk of developing CUD in later life.

PMID:37451153 | DOI:10.1016/j.addbeh.2023.107799

Tags:,

Related Posts

About The Author

Patrick Blanchard MD

Meet Dr. Blanchard Dr. Blanchard’s medical practice is an embodiment of Integrative health which brings conventional and complementary approaches together in a coordinated way. Conveniently located in sunny Florida and over the internet with ValiseMD’s secure HIPPA compliant telXmed servers. Since 1994, patients with a wide range of challenging medical problems have achieved optimum health using the best of natural medicine, judiciously combined with high-tech innovations. Breakthroughs are often achieved even after patients have consulted mainstream specialists and holistic practitioners. Dr. Blanchard is founder and CEO of ValiseMD, Inc. He is board certified in Family Medicine since 1994 and awarded Fellow of the American Academy of Family Physicians in 2001. He received the ‘Teacher of the Year’ award from the University of Kansas School of Medicine at completion of his residency in Family Medicine. He completed a fellowship at Wake Forest University in the field of vascular neurosonology. He holds a medical patent in the field of Gastroenterology. He holds an unrestricted license to practice medicine and surgery in Florida. He started his medical career as a Emergency Medical Technician, then as a Paramedic and later a Medical Doctor.