Biobert Dialogpt Powered Clinical Assistant with Faiss Search and Lightgbm Insights

DOI

10.2991/978-94-6463-718-2_23How to use a DOI?

Keywords

BioBERT; DialogGPT; FAISS search; LightGBM; clinical decision support; natural language processing; machine learning; scalability; interpretability; healthcare systems; global applicability; patient-centric; computational efficiency; actionable insights; fine-tuning; retrieval-augmented systems; clinical NLP; real-time decision-making; robust frameworks; deployment pipeline

Abstract

Advanced natural language processing (NLP) and machine learning (ML) techniques have been integrated into clinical systems paving the way for transformative healthcare solutions. In this paper, we will introduce a unified framework utilizing BioBERT, DialogGPT, FAISS search, and LightGBM to bridge important gaps in clinical decision support systems developed to date. This universal applicability transcends traditional models that are limited by datasets tied to specific domains, enhancing its relevance and utility in a broad range of clinical scenarios. FAISS improves the scalability of long-sequence data and LightGBM generates interpretable actionable insights to close the loop between machine learning outputs and clinical decision making. An additional instance of DialogGPT fine-tuned to clinical datasets allows for nuanced and patient-centric communication capabilities. This framework presents a cost-effective and robust solution for real-time, interpretable decision support in clinical settings, combining the benefits of both machine learning and clinical input while maintaining relevance in global healthcare contexts by addressing computational efficiency and validation. This effort lays the framework for a pipeline that can move a deep learning architecture from theory to reality within a healthcare system, from research to pragmatism.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - M. Venkatesan
AU  - V. Sharmila
AU  - R. Keerthana
AU  - S. Balamaheshwari
AU  - N. Chandni
AU  - K. Manimozhi
PY  - 2025
DA  - 2025/05/23
TI  - Biobert Dialogpt Powered Clinical Assistant with Faiss Search and Lightgbm Insights
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 255
EP  - 268
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_23
DO  - 10.2991/978-94-6463-718-2_23
ID  - Venkatesan2025
ER  -