BOARD # 71: Integrating Machine Learning into Middle and High School Curricula using Alzheimer’s Disease Prediction Models

Abstract

This study explores the integration of machine learning (ML) concepts into the curriculum for 6th to 12th-grade students thus, addressing the growing importance of computational skills in the STEM workforce. Teachers play a pivotal role as the principal pedagogical agents in fostering students’ motivation and readiness to engage in postsecondary education in STEM career pathways and eventually, the STEM workforce. Thus, we hypothesize that introducing teachers to innovative machine learning (ML) research methodologies—particularly those applied to real-world problem solving—can significantly enhance STEM learning and research experiences in grades 6 through 12. This project is an outcome of a Research Experience for Teachers (RET) summer program designed to immerse secondary educators in authentic research environments. During the program, participating teachers engaged in a ML project centered on predicting the severity of Alzheimer’s Disease using data collected from smart home sensors—a real-world application of ML in healthcare. The teachers were introduced to foundational computing concepts through Scratch, developed basic ML pipelines with interpretability features using ORANGE, and explored automated machine learning through the Aliro platform. Each tool provided a progressively advanced exposure to ML concepts while maintaining a consistent predictive modeling framework. The RET framework emphasized the iterative nature of research, model performance evaluation, and the importance of balancing model fit with generalizability. Teachers were able to learn ML concepts by repetition and reinforcement using the three different software suites (ORANGE, Aliro, and Google Colab). Subsequently, at their local schools, teachers integrated computational thinking and ML concepts into existing curricula across Mathematics, Algebra, and Statistics courses. Despite encountering challenges—including limited instructional time and technological constraints imposed by district policies—teachers successfully introduced foundational ML principles through both formal instructional modules and informal classroom activities. This study contributes to the expanding body of STEM education research by illustrating practical strategies for empowering secondary educators to integrate machine learning and computational thinking into their instruction. The findings underscore the potential for interdisciplinary learning and the cultivation of critical thinking skills that are essential for preparing the next generation of STEM professionals.

Department(s)

Cooperative Engineering Program

Document Type

Conference Proceeding

DOI

10.18260/1-2--55887

Publication Date

1-1-2025

Journal Title

ASEE Annual Conference and Exposition Conference Proceedings

Link to Full Text

Share

COinS