Extracting PICO elements from RCT abstracts using 1-2gram analysis and multitask classification

TL;DR

This paper presents a multitask SVM model utilizing 1-2gram TF-IDF features for extracting PICO elements from RCT abstracts, demonstrating superior performance over other models on a BioNLP dataset.

Contribution

The study introduces a novel multitask SVM classification approach with specialized feature engineering for PICO element extraction from medical abstracts.

Findings

Multitask SVM with 1-2gram TF-IDF features outperforms other models.

The proposed method effectively extracts PICO elements from RCT abstracts.

Model tested on BioNLP 2018 dataset shows high accuracy.

Abstract

The core of evidence-based medicine is to read and analyze numerous papers in the medical literature on a specific clinical problem and summarize the authoritative answers to that problem. Currently, to formulate a clear and focused clinical problem, the popular PICO framework is usually adopted, in which each clinical problem is considered to consist of four parts: patient/problem (P), intervention (I), comparison (C) and outcome (O). In this study, we compared several classification models that are commonly used in traditional machine learning. Next, we developed a multitask classification model based on a soft-margin SVM with a specialized feature engineering method that combines 1-2gram analysis with TF-IDF analysis. Finally, we trained and tested several generic models on an open-source data set from BioNLP 2018. The results show that the proposed multitask SVM classification model based on 1-2gram TF-IDF features exhibits the best performance among the tested models.