Scholarlink

This study introduces “Talk-A-Bot,” an advanced AI chatbot developed in Python to improve healthcare accessibility and support through intelligent, user-friendly interactions. Leveraging machine learning techniques like LSTM-based response generation, TF-IDF vectorization, and cosine similarity, “Talk-A-Bot” can interpret complex user intent, delivering contextually accurate responses that enhance user experience. Built around a Seq2Seq model, the chatbot is specifically tailored for healthcare applications, including preliminary symptom assessment, information dissemination, and real-time patient guidance, enabling private, accessible, and responsive health support. Additionally, it incorporates text preprocessing and adaptive learning capabilities, allowing it to evolve based on user interactions. The flexible codebase supports customization, extending its utility to fields like customer service and information retrieval. In pilot testing, “Talk-A-Bot” has shown high accuracy in handling diverse health-related inquiries, underscoring its potential to improve access to health information for underserved populations and aid healthcare professionals in efficiently addressing common questions. This project exemplifies the potential of AI in healthcare, enhancing patient engagement, broadening access to essential information, and ultimately advancing the quality of care.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI Chatbot for Medical Care Using Machine Learning with Python

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Subhash Kumar Wary,
  • Rajendra Oraon,
  • Mandwip Baruah,
  • Bipul Roy

摘要

This study introduces “Talk-A-Bot,” an advanced AI chatbot developed in Python to improve healthcare accessibility and support through intelligent, user-friendly interactions. Leveraging machine learning techniques like LSTM-based response generation, TF-IDF vectorization, and cosine similarity, “Talk-A-Bot” can interpret complex user intent, delivering contextually accurate responses that enhance user experience. Built around a Seq2Seq model, the chatbot is specifically tailored for healthcare applications, including preliminary symptom assessment, information dissemination, and real-time patient guidance, enabling private, accessible, and responsive health support. Additionally, it incorporates text preprocessing and adaptive learning capabilities, allowing it to evolve based on user interactions. The flexible codebase supports customization, extending its utility to fields like customer service and information retrieval. In pilot testing, “Talk-A-Bot” has shown high accuracy in handling diverse health-related inquiries, underscoring its potential to improve access to health information for underserved populations and aid healthcare professionals in efficiently addressing common questions. This project exemplifies the potential of AI in healthcare, enhancing patient engagement, broadening access to essential information, and ultimately advancing the quality of care.