Optimization of Appointment Scheduling for Hospitals Based on a Multilingual Virtual Assistant in an Instant Messaging Application
In Peru's public healthcare system, the process of scheduling medical appointments faces inefficiencies that lead to long waiting times and communication difficulties, especially for patients who speak different languages. These problems cause frustration and anxiety, delaying access to medical care and worsening health conditions. Poor communication can result in misunderstandings about treatment, increasing the risk of errors and making the patient experience more challenging. Moreover, lengthy phone calls to schedule appointments overwhelm administrative staff, reducing their efficiency. To address these issues, a chatbot was developed to operate through a messaging app, using artificial intelligence to understand various languages in a hospital setting. The chatbot is designed to improve the user experience by answering questions, providing information, and solving problems automatically. AI in this context refers to a branch of computer science focused on creating systems that perform tasks requiring human-like intelligence. The chatbot was tested in a hospital environment with a group of local and foreign users. The results showed that the majority of users completed the booking process quickly and without errors. Most participants expressed satisfaction with the booking experience, while foreign users found it particularly helpful to use the chatbot in their preferred language. These outcomes demonstrate the chatbot's effectiveness in enhancing accessibility, reducing waiting times, and meeting patient needs in a healthcare setting.
Authors
- Emilio Antonio Herrera-Trujillo (ORCID: https://orcid.org/0000-0001-8548-4849)
- Benjamín Ramos
- Jefferson Abner Cuenca Benites
Institutions
- Peruvian University of Applied Sciences (PE)
Publication Details
- Published
- 2024-12-10
- DOI
- https://doi.org/10.1109/icalter65499.2024.10819217
- Citations
- 1
- Primary Topic
- AI in Service Interactions
- Type
- article
- Field-Weighted Citation Impact
- 0.35