Bias in Machine Learning Applications

Understanding bias, auditing and quality control are key challenges for developing machine learning methods in healthcare. Models that have been trained on biased data, have the potential to automate decisions that are unfair and inequitable. This talk discusses strategies and methods for domain and outcome bias exploration to evaluate performance equitably across subgroups and whether the training data are representative of novel data expected in the model application. Three themes of exploration addressed are, subgroup performance equitability, application and training data similarity, training data grouping variable congruence.­­ Models developed on two publicly available datasets and a novel data set from MUSC describing mammogram screening uptake are used as examples exploring and detecting bias
Agenda:

• Join us at 5:30 for snacks, drinks, conversation and socializing.
• 6:00 - Main talk(s)
• 7:00 - 7:30 - Wrap up and hang out some more
• 7:30 - ? - After Party*

======================================

"Call for Papers"! .. if you have some knowledge to share with the community, please talk to Dave at the next meetup. We'd love to have 1 or 2 talks per meetup lined up for the coming months.

*After Party? .. The meetup is right next to Revelry Brewing. If folks are interested, we can clean up at the CLC and keep the conversation going over a nice local brew.