How Wearable Sensing Can Be Used to Monitor Patient Recovery Following ACL Reconstruction; Impact of the Public's Perspective of Wearable Sensor Data
Romness, Jane, School of Engineering and Applied Science, University of Virginia
Baritaud, Catherine, Department of Engineering and Society, University of Virginia
Boukhechba, Mehdi, EN-Eng Sys and Environment, University of Virginia
Technology has provided solutions to medical challenges that have altered the medical field and all of humankind, yet there are infinitely more applications that have yet to be explored. The capstone specifically delves into the potential success wearable sensors can provide to help mitigate the reinjury of Anterior Cruciate Ligaments following reconstruction. Patients that have experienced Anterior Cruciate Ligament reconstructive surgery are currently six times more likely to experience a retear which are the result of poor methods of ligament health assessment. The technical project advances the assessment of Anterior Cruciate Ligament health using wearable sensors to determine indicative knee movements relative to stability. Upon consideration of the advantages wearable sensing provides for ligament health, the science, technology, and technology (STS) research project considers the broader impact wearable sensors could have on the medical field. The analysis breaks down the public’s current perception on wearable sensor technology and the likely effects of this preconceived notion. The tightly coupled technical and STS research strives to positively impact the medical field by the utilization of wearable sensors.
The goal of the technical project is to develop a more efficient method of ligament health evaluation to mitigate the occurrence of an additional injury following surgery. My team advanced the analysis of ligament health by collecting accelerometer and EMG data on 12 patients who had not received a reconstructive surgery and 12 patients who had experienced surgery. Using data collected in the lab with IRB clearance, my team used data analytics and machine learning to discover significant features that could best judge the health of an Anterior Cruciate Ligament.
Our analysis shed light on various activities and features that are optimal for health measurement. The most significant conclusions regarding data classification of knee health were extracted from data collection during walking and single leg hop exercises. From these activities, EMG data demonstrated the greatest differences between a healthy and previously injured leg. While these conclusions are significant to the advancement of health assessment, our group recognizes there are limitations of the study such as small sample size and differing patient characteristics across subjects.
The science, technology, and society (STS) thesis analyzes the public’s current usage and perception of wearable sensor technologies. The research examines how the relationship between the public and the technology will likely affect the adoption of wearable sensors in the medical field. Pinch and Bijker’s Social Construction of Technology theory provides insight regarding the technical, organization and societal impacts wearable sensors will affect in the medical field. Given these suggestions, further research is provided to mitigate the impediment of the technology given the device’s vast potential advantages; these suggestions are supported by case studies of past medical devices.
Research suggests the public currently derives incorrect conclusions from wearable sensors and has associations of mistrust regarding accuracy and privacy. These negative conceptions will delay the widespread use of wearable sensors in the medical field if no further actions are taken. To optimize the advantages wearable sensors can offer the medical field, additional regulations and levels of device accuracy must be reached.
Both the technical project and STS project highlight wearable sensors in the medical field. The technical aspect aims to improve the evaluation of Anterior Cruciate Ligament health, while the STS component aims to analyze societal conceptions that may affect the adoption of the technology in the industry.
BS (Bachelor of Science)
Wearable Sensor, Anterior Cruciate Ligament, Machine Learning
School of Engineering and Applied Science
Bachelor of Science in Engineering Systems and Environment
Technical Advisor: Mehdi Boukhechba
STS Advisor: Catherine Baritaud
Technical Team Members: Kevin Cox, Drew Hamrock, Sydney Lawrence, Sean Lynch, Johnathan Saksvig, James Roberts, Alice Warner
All rights reserved (no additional license for public reuse)