GASCADE: Grouped Summarization of Adverse Drug Event for Enhanced Cancer Pharmacovigilance

TL;DR

The paper addresses cancer pharmacovigilance by introducing a task of grouped ADE summarization for cancer drugs and presenting the MCADRS dataset of 2,000 posts with ADE labels and summaries. It proposes GASCADE, a four-component pipeline that uses LLM-based ADE extraction with QLoRA, a drug-grouping and severity-based clustering module, and a T5-based abstractive summarization with alignment via Direct Preference Optimization on synthetic preferences. The approach demonstrates superior performance against baselines on automated metrics and through human evaluations, validating the value of two-stage ADE extraction and DPO alignment for accurate, severity-ranked ADE summaries. The work contributes a cancer-focused dataset, a novel multitasking framework, and publicly available code and data to advance cancer pharmacovigilance and personalized decision-making.

Abstract

In the realm of cancer treatment, summarizing adverse drug events (ADEs) reported by patients using prescribed drugs is crucial for enhancing pharmacovigilance practices and improving drug-related decision-making. While the volume and complexity of pharmacovigilance data have increased, existing research in this field has predominantly focused on general diseases rather than specifically addressing cancer. This work introduces the task of grouped summarization of adverse drug events reported by multiple patients using the same drug for cancer treatment. To address the challenge of limited resources in cancer pharmacovigilance, we present the MultiLabeled Cancer Adverse Drug Reaction and Summarization (MCADRS) dataset. This dataset includes pharmacovigilance posts detailing patient concerns regarding drug efficacy and adverse effects, along with extracted labels for drug names, adverse drug events, severity, and adversity of reactions, as well as summaries of ADEs for each drug. Additionally, we propose the Grouping and Abstractive Summarization of Cancer Adverse Drug events (GASCADE) framework, a novel pipeline that combines the information extraction capabilities of Large Language Models (LLMs) with the summarization power of the encoder-decoder T5 model. Our work is the first to apply alignment techniques, including advanced algorithms like Direct Preference Optimization, to encoder-decoder models using synthetic datasets for summarization tasks. Through extensive experiments, we demonstrate the superior performance of GASCADE across various metrics, validated through both automated assessments and human evaluations. This multitasking approach enhances drug-related decision-making and fosters a deeper understanding of patient concerns, paving the way for advancements in personalized and responsive cancer care. The code and dataset used in this work are publicly available.

Figures (4)

• Figure 1: Our GASCADE Framework summarising the Adverse Drug Event Information for each drug
• Figure 2: Proposed Model Architecture of Grouping and Abstractive Summarization of Cancer Adverse Drug events (GASCADE).
• Figure 3: Samples summaries generated with and without alignment techniques
• Figure 4: Samples responses generated via our framework and other models