Abstract
Technical Project
Surgery is a cornerstone of modern healthcare, with the operating room (OR) as one of the most resource-intensive units within a hospital. Since surgeries account for a substantial portion of hospital revenue, accurate prediction of surgery durations and efficient OR scheduling are critical to minimizing delays for patients as well as reducing overtime for staff and OR idle time. However, OR scheduling is complex due to variability including patient history, unforeseen complications, and emergency cases that can disrupt planned schedules. This complexity is compounded by the current OR scheduling approach, which remains a highly manual process driven largely by human decision-making and crude statistical averages. The goal of this project is to develop a model that improves elective surgery duration predictions by identifying patterns from historical data from the UVA Department of Surgery. Given the large number of unique surgeries, we clustered the data to gain greater insights into underlying patterns. Using this processed data, we developed XGBoost and Random Forest models that identify the most influential variables affecting surgery duration and improve time estimates for future procedures. Preliminary models show a 39.7-minute improvement in Root Mean Squared Error (RMSE) for time prediction, a 59% decrease from the current prediction method.
STS Project
The drive from Los Angles to Las Vegas should take about four hours, but practice, it often takes six or seven. To fix this, a private company, Brightline West, is building a new high-speed rail line using private funds, as well as a $3 billion grant from the federal government. I argue that while funding high-speed rail is a good idea, giving billions in taxpayer dollars to a private company without enforceable conditions raises ethical concerns. I looked at the project through two Science and Technology Studies (STS) frameworks. First, using Langdon Winner’s idea that "artifacts have politics," we can see how the physical design of the train makes choices about who can ride it. For example, instead of going all the way to downtown LA, the train stops in the suburb of Rancho Cucamonga. This means riders have to pay for a cab or connect to another train to get to the city. Combined with estimated ticket prices of over $100, the system’s design favors business travelers and tourists. Second, I used Jasanoff and Kim’s concept of "sociotechnical imaginaries." The government and Brightline are selling a flashy, futuristic vision of a clean, eco-friendly train. This imaginary makes the project look good on the surface, which risks ignoring the practical problems. It distracts from the argument that average taxpayers are funding a premium service many probably can't afford to use. If the government is going to fund private infrastructure projects like Brightline West, they need to attach conditions. The company should connect to regional transit, have public financial oversight, and guarantee affordable ticket options. Otherwise, we are just using the general public's money to build a service for some.
Linking the Two
While these two projects seem unrelated, working on them both at the same time made me think about how technology and public systems connect. My technical capstone showed me how there is complexity underlying things most people don't notice. Patients don’t think about how long a surgery is scheduled for, but there's a whole team of people working to make that schedule. By improving things like these, people's lives can be bettered. Complimenting this, my STS research about Brightline West taught me to look at technical work through a more critical lens. When viewed though the STS frameworks, just making a system "better" or more efficient - whether that is a high-speed train or an operating room schedule - isn't enough. You have to ask who is benefiting from that efficiency. While my capstone focused purely on optimizing time to reduce hospital delays which will help patients and healthcare providers alike, the STS project reminded me to look out for ethical blind spots in my own designs.
Notes
School of Engineering and Applied Science
Bachelor of Science in Systems Engineering
Technical Advisors: Robert Riggs, Daniel Otero-Leon, Constanza Lorca
STS Advisor: Joshua Earle
Technical Team Members: Mia deLadurantaye, Elise Williamson, Michael Dertke, Mackenzie Craig, Jacob Singer, Nathaniel Kusic
