Pramath Shukla
Computer science
Hometown: Gandhinagar, Gujarat, India
Graduation date: Fall 2025
FURI | Spring 2025
Using Natural Language Processing on EMS Call Recordings to Provide Clinically Relevant Outcomes
This research project explores the feasibility of applying Natural Language Processing to EMS radio calls. The research specifically explores the methods to extract clinically relevant information. This research utilizes machine learning techniques, including fine-tuning a BERT model and constructing a Multi-Layer Perceptron for classification with 92% accuracy on Whisper transcribed data. The model analyzes EMS call transcripts to predict key clinical factors before the patient arrives at the emergency department. The classification results provide actionable insights that enhance decision-making for emergency responders and hospital staff. By improving the accuracy and speed of clinical assessments, this research contributes to more efficient emergency care and better patient outcomes.
Mentor: Nakul Gopalan
It’s hip to be square.
Students presenting projects at the Fulton Forge Student Research Expo are encouraged to download this personal QR code and include it within your poster. This allows expo attendees to explore more about your project and about you in the future.
Right click the image to save it to your computer.