Strain Gauge-Based Torque Sensor for Orthopedic Surgery Applications; Implementation of Artificial Intelligence in Medicine

The technical project introduces an innovative solution to address the critical issue of bone quality assessment during surgical fixation. Currently, surgeons face challenges in acquiring localized, real-time bone density data, relying instead on rough imaging estimates. This limitation affects the success of surgical outcomes, highlighting the need for more precise and immediate feedback. The project focuses on the development of a torque-based bone strength drill capable of providing real-time, site-specific bone density measurements during surgery. By integrating strain gauges configured in a Wheatstone bridge circuit, the system detects subtle resistance changes that correlate torque with bone density. The design prioritizes key factors such as data readability, sterilization, accuracy, ease of use, and compatibility with existing surgical equipment. Extensive testing was conducted using both wood and bone samples to establish relationships between torque, strain, and axial force. Initial and final Instron tests demonstrated a strong correlation, confirming the reliability of the device in replicating real-world scenarios. Results were further validated through testing the custom device we manufactured on wood and bone samples. Future work will include enhancing compatibility with existing surgical drills, ensuring interchangeability of drill bits, and refining sterilization methods. Additionally, axial force considerations will be integrated to improve accuracy and robustness in varied surgical contexts. This device represents a groundbreaking advancement, aiming to bridge the gap between technological innovation and practical application in orthopedic surgery. By delivering precise, localized bone data in real time, it has the potential to significantly improve surgical outcomes and patient care, while minimizing risks associated with current methods. The technical paper will cover the design process, testing phases, and key technical achievements, as well as propose directions for further development.

Artificial Intelligence (AI) is transforming healthcare, presenting both promising advancements and unique challenges. This paper examines the integration of AI in medicine, focusing on its impact on clinical decision-making, ethical implications, and the interplay between tacit knowledge and AI-driven systems. Tacit knowledge, developed through experiential learning and intuitive judgment, remains a cornerstone of medical expertise, enabling doctors to navigate complex and ambiguous cases. While AI excels in processing vast datasets to offer diagnostics, predictive analytics, and robotic-assisted surgeries, its reliance on explicit knowledge limits its ability to replicate the nuanced decision-making inherent in human expertise. The paper delves into Actor-Network Theory, exploring how AI operates within healthcare networks and reshapes relationships among patients, doctors, institutions, and developers. Key findings highlight the evolving dynamics between AI and human actors, the black-box problem in AI decision-making, and the ethical challenges stemming from biased datasets and disparities in healthcare outcomes. Additionally, regulatory frameworks and policies from the U.S. and Europe are analyzed, emphasizing the need for transparency, accountability, and fairness in AI deployment. While AI provides unprecedented efficiency, this paper argues that human oversight is essential to mitigate risks, address biases, and preserve the empathetic aspects of medical practice. Stakeholders are urged to develop transparent AI models and robust regulatory measures to ensure equitable patient outcomes. The conclusion emphasizes AI as a collaborative tool that complements rather than replaces human expertise, advocating for thoughtful integration that preserves the core values of medicine while maximizing technological benefits. Future research priorities include encoding tacit knowledge into AI systems and examining the societal implications of AI in healthcare. By balancing innovation with ethical considerations, AI can redefine the role of medical professionals and enhance patient care without compromising its human-centric foundation.

The two projects—the integration of AI in medicine and the torque-based bone strength drill—share a common vision: improving healthcare outcomes through technological innovation. Both initiatives address gaps in medical practice, aiming to bridge the divide between existing methodologies and enhanced precision tools. The AI-in-medicine project emphasizes utilizing AI for clinical decision-making, data analysis, and predictive capabilities, which are vital for refining diagnostic and therapeutic approaches. Similarly, the bone strength drill project targets real-time, localized data acquisition to aid surgeons in optimizing fixation success during orthopedic procedures. At their core, both focus on the importance of accurate, data-driven decision-making to enhance patient care. Another connection lies in their ethical considerations and challenges. The AI project explores biases in datasets, regulatory concerns, and the human-centric approach to preserving empathy in medicine. The drill project complements this focus by considering factors such as sterilization, compatibility, and ergonomic design to ensure practical application without compromising safety. Both demonstrate how technology must balance functionality and ethical responsibility. Finally, both projects advocate for human oversight and collaboration. AI systems are positioned as tools to complement human expertise rather than replace it, much like the torque drill provides surgeons with supplemental data rather than automated decision-making. Together, these efforts illustrate the dynamic interplay between technological innovation and medical expertise, offering pathways to redefine healthcare practices and enhance outcomes in complementary ways.

School of Engineering and Applied Science

Bachelor of Science in Mechanical Engineering

Technical Advisor: Michael Momot; Jason Foreman; Joseph Park

STS Advisor: Joshua Earle

Technical Team Members: Grant Garland, Jackson Green, Joseph Liberatore, Matthew McEwen,
Michael Riley, Logan Wasserman