Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations

Using language models and ontology topology to perform semantic mapping of traits between biomedical datasets

MOTIVATION

Human traits are typically represented in both the biomedical literature and large population studies as descriptive text strings. Whilst a number of ontologies exist, none of these perfectly represent the entire human phenome and exposome. Mapping trait names across large datasets is therefore time-consuming and challenging. Recent developments in language modelling have created new methods for semantic representation of words and phrases, and these methods offer new opportunities to map human trait names in the form of words and short phrases, both to ontologies and to each other. Here, we present a comparison between a range of established and more recent language modelling approaches for the task of mapping trait names from UK Biobank to the Experimental Factor Ontology (EFO), and also explore how they compare to each other in direct trait-to-trait mapping.

RESULTS

In our analyses of 1191 traits from UK Biobank with manual EFO mappings, the BioSentVec model performed best at predicting these, matching 40.3% of the manual mappings correctly. The BlueBERT-EFO model (finetuned on EFO) performed nearly as well (38.8% of traits matching the manual mapping). In contrast, Levenshtein edit distance only mapped 22% of traits correctly. Pairwise mapping of traits to each other demonstrated that many of the models can accurately group similar traits based on their semantic similarity.

AVAILABILITY AND IMPLEMENTATION

Our code is available at https://github.com/MRCIEU/vectology.

A hybrid algorithm for clinical decision support in precision medicine based on machine learning

PURPOSE

The objective of the manuscript is to propose a hybrid algorithm combining the improved BM25 algorithm, k-means clustering, and BioBert model to better determine biomedical articles utilizing the PubMed database so, the number of retrieved biomedical articles whose content contains much similar information regarding a query of a specific disease could grow larger.

DESIGN/METHODOLOGY/APPROACH

In the paper, a two-stage information retrieval method is proposed to conduct an improved Text-Rank algorithm. The first stage consists of employing the improved BM25 algorithm to assign scores to biomedical articles in the database and identify the 1000 publications with the highest scores. The second stage is composed of employing a method called a cluster-based abstract extraction to reduce the number of article abstracts to match the input constraints of the BioBert model, and then the BioBert-based document similarity matching method is utilized to obtain the most similar search outcomes between the document and the retrieved morphemes. To realize reproducibility, the written code is made available on https://github.com/zzc1991/TREC_Precision_Medicine_Track .

FINDINGS

The experimental study is conducted based on the data sets of TREC2017 and TREC2018 to train the proposed model and the data of TREC2019 is used as a validation set confirming the effectiveness and practicability of the proposed algorithm that would be implemented for clinical decision support in precision medicine with a generalizability feature.

ORIGINALITY/VALUE

This research integrates multiple machine learning and text processing methods to devise a hybrid method applicable to domains of specific medical literature retrieval. The proposed algorithm provides a 3% increase of P@10 than that of the state-of-the-art algorithm in TREC 2019.

Social Media Toxicity Classification Using Deep Learning: Real-World Application UK Brexit

Social media has become an essential facet of modern society, wherein people share their opinions on a wide variety of topics. Social media is quickly becoming indispensable for a majority of people, and many cases of social media addiction have been documented. Social media platforms such as Twitter have demonstrated over the years the value they provide, such as connecting people from all over the world with different backgrounds. However, they have also shown harmful side effects that can have serious consequences. One such harmful side effect of social media is the immense toxicity that can be found in various discussions. The word toxic has become synonymous with online hate speech, internet trolling, and sometimes outrage culture. In this study, we build an efficient model to detect and classify toxicity in social media from user-generated content using the Bidirectional Encoder Representations from Transformers (BERT). The BERT pre-trained model and three of its variants has been fine-tuned on a well-known labeled toxic comment dataset, Kaggle public dataset (Toxic Comment Classification Challenge). Moreover, we test the proposed models with two datasets collected from Twitter from two different periods to detect toxicity in user-generated content (tweets) using hashtages belonging to the UK Brexit. The results showed that the proposed model can efficiently classify and analyze toxic tweets.