Presenter(s)
Nicole Braun
Abstract
In the modern healthcare landscape, managing medical technology efficiently is vital to patient outcomes. However, healthcare facilities often struggle with equipment management during volatile, influenza-driven patient surges. This project presents a data-driven reporting framework designed to transition Agiliti Health from reactive equipment management to a proactive consultative approach, ensuring hospital preparedness during peak seasonal demand. The primary objective was to design a reporting suite that transforms disconnected data streams into actionable strategic insights. The methodology involved centralizing internal logistics data from Azure Databricks and integrating external trends from the Center of Disease Control. Technical implementation required rigorous data cleaning using Python and Polars to unify disparate date formats and aggregate rental history. This prepared data was then used to develop a relational semantic model within Power BI, utilizing a live SQL Server connection to ensure continuous data updates. A core feature of the framework is a custom DAX-based algorithm that calculates a 180-day projected rental count based on three-year rolling averages. This predictive tool allows sales teams to provide evidence-based suggestions for critical assets, such as infusion pumps and ventilators, specifically for the peak influenza season from October to March. To provide clinical context, the dashboard also visualizes state-level influenza spikes, helping hospital administrators align equipment needs with viral activity. Initial deployment results indicate that the framework effectively bridges the gap in strategic planning by providing visual, quantitative foundations for inventory scaling. While currently limited to statewide influenza data, future iterations aim to automate CDC data ingestion and refine predictive logic to include emerging trends like COVID-19. Ultimately, this framework establishes a standardized methodology that ensures logistical constraints do not impede clinical care during high-volume periods.
College
College of Science & Engineering
Department
Mathematics & Statistics
Campus
Winona
First Advisor/Mentor
April Kerby
Location
Kryzsko Great River Ballroom, Winona, Minnesota; United States
Start Date
4-23-2026 9:00 AM
End Date
4-23-2026 10:00 AM
Presentation Type
Poster Session
Format of Presentation or Performance
In-Person
Session
1a=9am-10am
Poster Number
7
Agiliti Health Rental Model Development
Kryzsko Great River Ballroom, Winona, Minnesota; United States
In the modern healthcare landscape, managing medical technology efficiently is vital to patient outcomes. However, healthcare facilities often struggle with equipment management during volatile, influenza-driven patient surges. This project presents a data-driven reporting framework designed to transition Agiliti Health from reactive equipment management to a proactive consultative approach, ensuring hospital preparedness during peak seasonal demand. The primary objective was to design a reporting suite that transforms disconnected data streams into actionable strategic insights. The methodology involved centralizing internal logistics data from Azure Databricks and integrating external trends from the Center of Disease Control. Technical implementation required rigorous data cleaning using Python and Polars to unify disparate date formats and aggregate rental history. This prepared data was then used to develop a relational semantic model within Power BI, utilizing a live SQL Server connection to ensure continuous data updates. A core feature of the framework is a custom DAX-based algorithm that calculates a 180-day projected rental count based on three-year rolling averages. This predictive tool allows sales teams to provide evidence-based suggestions for critical assets, such as infusion pumps and ventilators, specifically for the peak influenza season from October to March. To provide clinical context, the dashboard also visualizes state-level influenza spikes, helping hospital administrators align equipment needs with viral activity. Initial deployment results indicate that the framework effectively bridges the gap in strategic planning by providing visual, quantitative foundations for inventory scaling. While currently limited to statewide influenza data, future iterations aim to automate CDC data ingestion and refine predictive logic to include emerging trends like COVID-19. Ultimately, this framework establishes a standardized methodology that ensures logistical constraints do not impede clinical care during high-volume periods.
