Optimizing healthcare delivery: leveraging large language models to do pre-consultation interactions
Medical resources are scarce, especially in densely populated areas where there is a high demand for hospital diagnoses. Often, there are long queues for appointments, which can be frustrating for patients. If patients could express their symptoms effectively and receive preliminary diagnoses prompt...
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis-Master by Coursework |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/172684 |
_version_ | 1811685770988093440 |
---|---|
author | Liu, Linfeng |
author2 | Wang Lipo |
author_facet | Wang Lipo Liu, Linfeng |
author_sort | Liu, Linfeng |
collection | NTU |
description | Medical resources are scarce, especially in densely populated areas where there is a high demand for hospital diagnoses. Often, there are long queues for appointments, which can be frustrating for patients. If patients could express their symptoms effectively and receive preliminary diagnoses promptly, it would free up significant medical resources and enhance the efficiency of patients gaining the right knowledge to manage their conditions. This article leverages the open-source MetaAI language model LLaMA2 as the base model. Firstly using TF-IDF Vectorization and Cosine Similarity Filtering to finish text de-duplicates job. The model utilizes Huggingface's PEFT Library to perform LoRA fine-tuning technique and Quantization Techniques to fine-tune LLaMA2 on NVIDIA 3090 device, enabling it to make initial symptom assessments based on patient descriptions. Finally, an attempt will be made to have this Language Model (LM) participate in the USMLE examination for evaluation. |
first_indexed | 2024-10-01T04:49:49Z |
format | Thesis-Master by Coursework |
id | ntu-10356/172684 |
institution | Nanyang Technological University |
language | English |
last_indexed | 2024-10-01T04:49:49Z |
publishDate | 2023 |
publisher | Nanyang Technological University |
record_format | dspace |
spelling | ntu-10356/1726842023-12-22T15:45:28Z Optimizing healthcare delivery: leveraging large language models to do pre-consultation interactions Liu, Linfeng Wang Lipo School of Electrical and Electronic Engineering ELPWang@ntu.edu.sg Engineering::Electrical and electronic engineering Medical resources are scarce, especially in densely populated areas where there is a high demand for hospital diagnoses. Often, there are long queues for appointments, which can be frustrating for patients. If patients could express their symptoms effectively and receive preliminary diagnoses promptly, it would free up significant medical resources and enhance the efficiency of patients gaining the right knowledge to manage their conditions. This article leverages the open-source MetaAI language model LLaMA2 as the base model. Firstly using TF-IDF Vectorization and Cosine Similarity Filtering to finish text de-duplicates job. The model utilizes Huggingface's PEFT Library to perform LoRA fine-tuning technique and Quantization Techniques to fine-tune LLaMA2 on NVIDIA 3090 device, enabling it to make initial symptom assessments based on patient descriptions. Finally, an attempt will be made to have this Language Model (LM) participate in the USMLE examination for evaluation. Master of Science (Communications Engineering) 2023-12-18T05:52:30Z 2023-12-18T05:52:30Z 2023 Thesis-Master by Coursework Liu, L. (2023). Optimizing healthcare delivery: leveraging large language models to do pre-consultation interactions. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/172684 https://hdl.handle.net/10356/172684 en application/pdf Nanyang Technological University |
spellingShingle | Engineering::Electrical and electronic engineering Liu, Linfeng Optimizing healthcare delivery: leveraging large language models to do pre-consultation interactions |
title | Optimizing healthcare delivery: leveraging large language models to do pre-consultation interactions |
title_full | Optimizing healthcare delivery: leveraging large language models to do pre-consultation interactions |
title_fullStr | Optimizing healthcare delivery: leveraging large language models to do pre-consultation interactions |
title_full_unstemmed | Optimizing healthcare delivery: leveraging large language models to do pre-consultation interactions |
title_short | Optimizing healthcare delivery: leveraging large language models to do pre-consultation interactions |
title_sort | optimizing healthcare delivery leveraging large language models to do pre consultation interactions |
topic | Engineering::Electrical and electronic engineering |
url | https://hdl.handle.net/10356/172684 |
work_keys_str_mv | AT liulinfeng optimizinghealthcaredeliveryleveraginglargelanguagemodelstodopreconsultationinteractions |