Presentation
Studying teenage suicidal behavior faces many challenges. This presentation will discuss how interdisciplinary research bridging data science with health psychology can help overcome these challenges. In addition, several data science algorithms and toolkits developed by a research team at the psychology department are presented, underscoring the necessity of a mindful integration and interpretation of machine learning techniques into health research. Therefore, this presentation addresses scientific challenges and innovations at two fronts, data science and health psychology.
From a data science perspective, several data science tools (R packages) will be presented including the mlim R package for missing data imputation, the autoEnsemble R package for risk estimation of rare events, the Shapley R package for generalizable identification of important indicators, and the fair R package for model fairness assessment. These tools were designed to address challenges in our research and provided solutions to these problems that will be presented. In terms of health psychology research, findings from several scientific publication will be presented, demonstrating how these data science tools have enabled accurate suicide attempt risk estimation, identification of high-risk teenagers, clarifying their inconsistent self-reported data, differentiating suicide attempts from self-harm behavior, which are highly comorbid conditions, and developing a comprehensive theoretical model for teenage suicidal behavior.
Speaker
Haghish is an applied statistician and health psychologist. His research concerns adolescent mental health, particularly suicidal thoughts and behavior. He is also interested in improving machine learning algorithms and their applications for health and mental health research.
Program
11:30 – Doors open and lunch is served
12:00 – "Machine Learning for Mental Health Research" by Haghish Ebad Fardzadeh (Postdoctoral Fellow, Department of Psychology)
This event is open for all students, PhD candidates, postdocs, and everyone else who is interested in the topic. No registration needed.
About the seminar series
Once a month, dScience will invite you to join us for lunch and professional talks at the Science Library. In addition to these, we will serve lunch in our lounge in Kristine Bonnevies house every Thursday. Due to limited space (40 people), this will be first come, first served. See how to find us here.
Our lounge can also be booked by PhDs and Postdocs on a regular basis, whether it is for a meeting or just to hang out – we have fresh coffee all day long!