Designing an Affordable Distal Radius Fracture Reduction Simulator for Medical Training; Embedded Inequities: How Historical Mechanisms of Bias in Medical Device Implementation Influence AI in Healthcare

The distal radial fracture (DRF), or fracture of the wrist, is a common injury encountered by medical professionals. A crucial step in treating a DRF is to perform a reduction, where the doctor manually sets the broken bone back into proper anatomical alignment. Currently, the standard method for learning reduction is by practicing on patients under professional supervision. As a result, many incoming residents do not feel adequately prepared to reset fractured wrists. My team's Technical Capstone project is developing a training simulator that accurately replicates manual reduction, providing a new alternative to practice. My Science, Technology, and Society (STS) research explores the socio-technical considerations necessary to effectively implement medical technology in the industry. Social factors such as accessibility and inclusive design for all demographics are essential to creating a useful technology that successfully provides an accurate training experience.
The medical industry currently lacks a sufficient physical simulator for students and residents – medical school graduates undergoing post-graduate training – to practice DRF reduction. Existing training options are limited, often consisting of expensive hand-made simulators without thorough design consideration. Available simulators are not standardized or widely accepted in the industry due to factors such as high cost and lack of anatomical accuracy necessary for effective training. Improved educational simulation technology, designed to accurately replicate the tactile experience of performing a reduction, would significantly benefit the healthcare industry. Our team’s Technical Capstone aims to address these shortcomings with a thorough design process, resulting in an affordable, accurate, and easily producible DRF simulator. However, to ensure the device’s efficacy, it is also important to consider the social factors that impact the effectiveness of medical technologies.
One important social factor is design bias, which can undermine a medical device’s effectiveness. This STS paper examines design bias in previous medical devices, the spirometer and pulse oximeter, to better understand how bias manifests. Using Sheila Jasanoff’s concept of historical analytics and Langdon Winner’s theory of technological politics, this analysis investigates how technology is inherently political and shaped by societal power structures. Understanding the historical influence of social power on technology helps identify and mitigate bias in current designs. This research shows that both implicit and explicit racial biases have historically penetrated device design, harming marginalized groups. Without considering all demographics in the design process, medical technologies cannot achieve the goal of improving diagnosis and treatment for all patients. This issue persists today in the implementation of artificial intelligence (AI) in healthcare, where datasets that fail to represent diverse populations lead to unequal health outcomes. Awareness of such gaps is essential for developing effective and equitable medical technologies.
Our simulator intends not only to fill a technological gap in DRF reduction training, but also to design inclusively, ensuring it serves a diverse patient population. By applying knowledge from the history of technological politics, we prioritize demographic inclusivity alongside technical accuracy. The simulator also features thorough technical decisions with guidance from an orthopedist to ensure an accurate model. With a strong understanding of both the technical limitations of current DRF simulators and the social implications of biased design on medical technologies, we accomplished our goal of creating a simulator that effectively improves medical trainees’ ability to perform DRF reductions.

School of Engineering and Applied Science
Bachelor of Science in Mechanical Engineering
Technical Advisor: Jason Forman
STS Advisor: Sean Murray
Technical Team Members: Brian Garmer, Greer Matthias, John Murphy, Katya Napolitano, Lauren Elliff, Natalie Bretton, Ryan DeLoach