Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.15380921 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901682813665280 |
|---|---|
| author | Soundarya Waghe, Shruti Barhe, Sandeep Kulkarni |
| author_facet | Soundarya Waghe, Shruti Barhe, Sandeep Kulkarni |
| contents | <p>The research paper proposes an intelligent, AI-powered healthcare chatbot intended for use in preliminary complaint detection by analyzing various inputs such as speech, text, photos, and expressions. It encompasses slice-edge technology such as that used in Groq to make speedy yet effective processing possible of AI; OpenAI Whisper to transcribe speech recaps accurately; LLaMA 3 Vision for diagnosis from medical pictures; and gTTS and ElevenLabs for providing explicit and natural-voiced feedback. A minimal and interactive stoner interface is built with Gradio, and the whole system is created in Python to provide inflexibility, velocity, and ease of integration. In contrast to conventional text-grounded chatbots, this model introduces another<br>subcaste of intelligence by interpreting facial expressions, tasting voice tones, and celebrating image patterns to provide more precise health assessments. It utilizes natural language processing (NLP) to engage in conversation with druggies, pose relevant health questions, read symptoms, and provide backed feedback. MedMentor's chatbot looks to enhance distant health observation, encourage premature opinion, and simplify telemedicine for access. Nevertheless, challenges like data sequestration and trustworthiness of AI for deciding health opinions when used wider are to be precisely addressed. </p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_15380921 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | MedMentor: The Multi-Model AI-Based Health Chatbot Development Soundarya Waghe, Shruti Barhe, Sandeep Kulkarni <p>The research paper proposes an intelligent, AI-powered healthcare chatbot intended for use in preliminary complaint detection by analyzing various inputs such as speech, text, photos, and expressions. It encompasses slice-edge technology such as that used in Groq to make speedy yet effective processing possible of AI; OpenAI Whisper to transcribe speech recaps accurately; LLaMA 3 Vision for diagnosis from medical pictures; and gTTS and ElevenLabs for providing explicit and natural-voiced feedback. A minimal and interactive stoner interface is built with Gradio, and the whole system is created in Python to provide inflexibility, velocity, and ease of integration. In contrast to conventional text-grounded chatbots, this model introduces another<br>subcaste of intelligence by interpreting facial expressions, tasting voice tones, and celebrating image patterns to provide more precise health assessments. It utilizes natural language processing (NLP) to engage in conversation with druggies, pose relevant health questions, read symptoms, and provide backed feedback. MedMentor's chatbot looks to enhance distant health observation, encourage premature opinion, and simplify telemedicine for access. Nevertheless, challenges like data sequestration and trustworthiness of AI for deciding health opinions when used wider are to be precisely addressed. </p> |
| title | MedMentor: The Multi-Model AI-Based Health Chatbot Development |
| url | https://doi.org/10.5281/zenodo.15380921 |