Predicting alcohol use disorder through machine learning
How to come to valid risk stratification of alcohol use disorder?
- Marc Molendijk
Alcohol use disorder is a common disorder that comes with personal and societal costs that are too large to ignore. The scientific literature reports on a host of variables that are associated with risk on alcohol use disorder. The studies that report on this all tend to isolate the effects that single predictor variables (e.g., socio-economic status) may have on the presence or incidence of alcohol use disorder. Given that alcohol use disorder likely results from complex processes in which multiple variables react and respond to each other, the current simplistic approach is ill equipped to capture the phenomenon of risk for alcohol use disorder. Another set of statistical analyses is needed to answer this question.
We aim to solve the public health conundrum of risk-stratification for alcohol use disorder by means of the method of machine learning. Machine learning searches the best solution for a given problem in a data-set and it bypasses the need to selectively study single options. That is, machine learning is not restricted by background theory or human biases. The product of machine learning is a set of rules or contingencies that serve to implement, individual, risk stratification of alcohol use disorder. Now we have the expertise to apply this method on the rich and well defined data from the Netherlands Study of Depression and Anxiety.
Marc Molendijk 1, 2, Thomas Bäck 3, Willem van der Does 1, 2, Bernet Elzinga 1, 2, Aske Plaat 3, Fons Verbeek 3, Dennis Mook-Kanamori 4, Brenda Penninx 5
- Institute of Psychology, Clinical Psychology Unit, Leiden University, Leiden, The Netherlands
- Leiden Institute for Brain and Cognition (LIBC), Leiden University Medical Center, Leiden, The Netherlands
- Leiden Institute of Advanced Computer Science (LIACS), Faculty of Science, Leiden University, The Netherlands
- Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, The Netherlands
- Department of Psychiatry, EMGO Institute for Health and Care Research and Neuroscience Campus Amsterdam, VU University Medical Center/GGZ inGeest, Amsterdam, The Netherlands