PULSAR at MEDIQA-Sum 2023: Large Language Models Augmented by Synthetic Dialogue Convert Patient Dialogues to Medical Records

2023/07/05 by Schlegel, Viktor, Li, Hao, Wu, Yuping +8 · 2 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2307.02006

Abstract

This paper describes PULSAR, our system submission at the ImageClef 2023 MediQA-Sum task on summarising patient-doctor dialogues into clinical records. The proposed framework relies on domain-specific pre-training, to produce a specialised language model which is trained on task-specific natural data augmented by synthetic data generated by a black-box LLM. We find limited evidence towards the efficacy of domain-specific pre-training and data augmentation, while scaling up the language model yields the best performance gains. Our approach was ranked second and third among 13 submissions on task B of the challenge. Our code is available at https://github.com/yuping-wu/PULSAR.

Cited by

• Term2Note: Synthesising Differentially Private Clinical Notes from Medical Terms
• MIRA: Medical Time Series Foundation Model for Real-World Health Data

Related

• WangLab at MEDIQA-Chat 2023: Clinical Note Generation from Doctor-Patient Conversations using Large Language Models
• PULSAR: Pre-training with Extracted Healthcare Terms for Summarising Patients' Problems and Data Augmentation with Black-box Large Language Models
• PMC-LLaMA: Towards Building Open-source Language Models for Medicine
• DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation
• Large Language Model Benchmarks in Medical Tasks