Author Archives: Shawn McCollum

Population Bias In ML Based Medical Research

Unequal outcomes in medical research has been an ongoing issue, but a new study indicates that machine learning may not be an automatic solution to this problem. (Conev, et al. 2024)

A team of researchers from Rice University in Houston, Texas have recently published a study examining how the utilization of a biased dataset within a machine learning model can result in a disparity of immunotherapy treatments across different income classifications and geographic populations.

In an analysis of available datasets the team found that these datasets were “biased toward the countries with higher income levels.” Several solutions are suggested, including a conscious effort to expand data collection to under-represented geographic populations as well as creating models that train on the characteristics of each individual patient.

Conev, A., Fasoulis, R., Hall-Swan, S., Ferreira, R., Kavraki, L. (2024) ‘HLAEquity: Examining biases in pan-allele peptide-HLA binding predictors’, iScience, 27(1), https://www.sciencedirect.com/science/article/pii/S2589004223026901

DataFest@Miami ’24 Registration Opens

DataFest returns to Miami University from April 5th – April 7th for a data-packed 48 hours.

DataFest returns to Miami University from April 5th – April 7th for a data-packed 48 hours

DataFest, now in its eighth year at Miami, brings together teams of 3 – 5 analysis-minded undergraduates as they compete to extract a narrative from real-world datasets. These datasets are provided in cooperation with the American Statistical Assocation as part of the broader, international, event.

This year’s DataFest will find teams working in the new McVey Data Science Building, taking advantage of its numerous open-concept study spaces as they condense their insights into a short presentation. Along the way, students will have the opportunity to bounce ideas off a group of “roving consultants” – subject matter experts who volunteer their time so that students can leverage the benefit of real-world experience.

All of this leads to Sunday afternoon, when teams will showcase their understanding of the data by presenting to a group of expert judges. After deliberation, three teams will be chosen as winners across a variety of categories.

New this year, the Center for Analytics and Data Science will be hosting an information session on February 26th. Intended for students who have never participated in DataFest, we welcome any undergraduate student with questions about how this year’s competition might be different than years past.

Social Network Analysis in R

The Center for Analytics and Data Science Faculty Fellow Bootcamp Series is kicking off for Spring Semester.

Join Kevin Reuning, Center for Analytics and Data Science Faculty Fellow and assistant professor in Political Science, as he leads an activity-driven exploration of the (sometimes hidden) connections that link us as a society.

Over three consecutive Wednesday evenings in McVey 168, Reuning will help the audience take their knowledge of R and data analysis as it pertains to more traditional data sets and apply it to the interconnected web that is the foundation of a social networking modelling.

March 6th: Introduction to network terminology and data
March 13th: Visualizing networks
March 20th: Calculating basic network statistics

This entry in the CADS Faculty Fellow Boot Camp Series presumes at least some level of R proficiency and working knowledge of basic data analysis principles. Due to the interactive nature of the exploration, please bring your laptop.

The Center for Analytics and Data Science is proud to be able to bring unique views into the arena of data science through its Faculty Fellow program. Thanks to the wide variety of talent offered by these gifted academics, CADS is able to provide examples of data science principles as they apply to the research of an array of disciplines. We thank all of our Faculty Fellows for their hard work and willingness to share.

If you have a topic that you would like to see covered as part of the Faculty Fellows Bootcamp Series, or any other question please contact the Center for Analytics and Data Science at cads@miamioh.edu