Monday, March 14, 2022

7:30 am - 9:00 am

Baker Ballroom

Professional Development - Mentor/Mentee Collaborations

Presenter:   Matthew Lee Smith, PhD, MPH, CHES, FGSA, FAAHB

Texas A&M University

Title:  Keys to Quality Mentorship and Productive Collaborations: Lessons Learned from AAHB Scholars

This interactive session will provide attendees with tips and strategies essential to form strong and productive mentor/mentee relationships and collaborations.  

The session will begin with brief presentations from the AAHB Research Scholars Mentorship Program (RSMP) cohorts to highlight their efforts over the past year. Then, a panel discussion will be facilitated to enable mentor/mentee pairs to share lessons learned and address questions from the audience. Past RSMP cohorts and those interested in being part of the 2022 RSMP are encouraged to attend. 

Learning Objectives:

• Attendees will increase their familiarity with the scope and potential benefits of participation in the AAHB Research Scholars Mentoring Program.
• Attendees will be able to describe several specific ways in which mentoring can promote the development and scholarship of early career professionals.
• Attendees will be able to identify at least three strategies for making the most out of a mentoring relationship.

Sponsored by AAHB Fellows

Tuesday, March 15, 2022

7:30 am - 9:00 am 

Baker Ballroom 

Professional Development - Meta-Analysis with STATA

Zoom Presenter:  Gabriela Ortiz, Applied Econometrician Stata Representative and 

Houssein Assaad, PhD - Principal Statistician and Software Developer at StataCorp and the primary developer of Stata's meta-analysis suite.

Title:  Performing meta-analysis in Stata

Moderator:  Matthew E. Rossheim, PhD, MPH, CPH

University of Texas Health Science Center at Fort Worth

Department of Health Behavior and Health Systems

School of Public Health

This professional development session is designed for graduate students and researchers.

Learning Objectives:

1. Learn the tools in Stata 17 for performing meta-analysis.
2. Learn how to compute effect sizes and summarize meta-analytic results in tables and in forest plots. Also, learn to perform cumulative meta-analysis and explore how the overall effect size is influenced by individual studies.
3. Learn ways to assess heterogeneity, such as generating Galbraith plots and L'Abbé plots. Additionally, learn how subgroup analysis and meta-regression can be used to determine whether moderators explain the observed heterogeneity. Also, learn to perform multivariate meta-regression for studies reporting multiple effect sizes.
4. Learn how to explore and address small-study effects.  Learn to create funnel plots, perform tests for small-study effects, and perform trim-and-fill analysis of publication bias.

Sponsored by Stata

Tuesday, March 15, 2022

1:00 pm - 2:30 pm 

Baker Ballroom 

Presenter:  Ruopeng An, PhD

Brown School, Washington University in St. Louis

Title: Incorporating Artificial Intelligence in Public Health Teaching and Research

A Brief Summary:  Artificial intelligence (AI), characterized by machine learning (ML), has been increasingly recognized as an indispensable tool in health sciences, with relevant applications expanding from disease outbreak prediction to medical imaging and from patient communication to behavioral modification. However, gaps in adopting and utilizing those modern data analytic techniques prevail in public health. This workshop aims to provide an overview of the basic concepts and applications of AI and ML in the fields of public health, medicine, and beyond. After attending the workshop, participants will be able to (1) understand the ML programming paradigm, (2) learn various contemporary applications of ML, (3) differentiate various types of ML systems, (4) explain the main challenges of ML and potential remedies, and (5) familiarize with a rich set of resources (e.g., textbooks, online courses, computational platforms, software packages, datasets) that can facilitate learning AI and ML.

Learning objectives:

Workshop participants will:

(1) learn a brief history, key definitions and essential concepts, popular applications, algorithm biases, and misperceptions about artificial intelligence (i.e., machine learning and deep learning or neural network models);

(2) learn to implement an end-to-end machine learning project using Python and Scikit-Learn in Google Colab; and

(3) familiarize with a rich set of resources (e.g., textbooks, online courses, computational platforms, software packages, and datasets) that can facilitate learning artificial intelligence.

Sponsored by AAHB Fellows