IMPROVING PATIENT EXPERIENCE WITH EMOTION-SENSITIVE LARGE MODELS

In the contemporary digital healthcare landscape, technological innovations have significantly improved access and efficiency; yet, an essential question persists: can these technologies also address the emotional needs of patients? This study investigates the role of Large Language Models (LLMs), a class of foundation models trained on vast datasets, in improving both administrative efficiency and patient-centered care within healthcare environments. This study demonstrates the feasibility of employing LLMs to develop a custom, clinicoriented booking assistant capable of automating appointment scheduling, reducing administrative workload, and improving access to healthcare services. This system was implemented using Google Apps Script, a cloud-based JavaScript platform that enables automation of workflows and integration with Google services. Beyond administrative applications, the study examines the ability of LLMs to detect patient emotions by leveraging established facial expression datasets to simulate real world telehealth interactions. The findings from technical implementation and experiments underscore the broader promise of LLMs in healthcare; specifically, by combining administrative efficiency with emotionally adaptive interventions, LLMs can contribute to the creation of more patient centered digital healthcare systems that not only streamline operations but also address patients’ psychological and emotional needs.

Name thesis:degree_name

Master of Science (M.Sc.)

Level thesis:degree_level

Masters

Discipline thesis:degree_discipline

Mechanical Engineering

Grantor

University of Saskatchewan

Year dc:date.issued

2025

Author dc:creator

• DEL ROSARIO, INDIRA

Committee members dc:contributor.committeemember

• Zhang, Chris
• Lin, Randy
• Ip, Andrew
• Ko, Seok-Bum

• Telehealth
• Patient Experience
• Large Language Models
• Emotion Detection
• AI in Healthcare

Language dc:language.iso

en

Handle dc:identifier.uri

https://hdl.handle.net/10388/17612

OAI identifier oai:identifier

oai:harvest.usask.ca:10388/17612