Oladimeji Farri

Adverse Drug Event Detection in Tweets with Semi-Supervised Convolutional Neural Networks

Current Adverse Drug Events (ADE) surveillance systems are often associated with a sizable time lag before such events are published. Online social media such as Twitter could describe adverse drug events in real-time, prior to official reporting. Deep learning has significantly improved text classification performance in recent years and can potentially enhance ADE classification in tweets. However, these models typically require large corpora with human expert-derived labels, and such resources are very expensive to generate and are hardly available. Semi-supervised deep learning models, which offer a plausible alternative to fully supervised models, involve the use of a small set of labeled data and a relatively larger collection of unlabeled data for training. Traditionally, these models are trained on labeled and unlabeled data from similar topics or domains. In reality, millions of tweets generated daily often focus on disparate topics, and this could present a challenge for building deep learning models for ADE classification with random Twitter stream as unlabeled training data. In this work, we build several semi-supervised convolutional neural network (CNN) models for ADE classification in tweets, specifically leveraging different types of unlabeled data in developing the models to address the problem. We demonstrate that, with the selective use of a variety of unlabeled data, our semi-supervised CNN models outperform a strong state-of-the-art supervised classification model by +9.9% F1-score. We evaluated our models on the Twitter data set used in the PSB 2016 Social Media Shared Task. Our results present the new state-of-the-art for this data set.

Attention-Based Medical Caption Generation with Image Modality Classification and Clinical Concept Mapping

This paper proposes an attention-based deep learning framework for caption generation from medical images. We also propose to utilize the same framework for clinical concept prediction to improve caption generation by formulating the task as a case of sequence-to-sequence learning. The predicted concept IDs are then mapped to corresponding terms in a clinical ontology to generate an image caption. We also investigate if learning to classify images based on the modality e.g. CT scan, MRI etc. can aid in generating precise captions.

Overview of ImageCLEF 2018: Challenges, Datasets and Evaluation

This paper presents an overview of the ImageCLEF 2018 evaluation campaign, an event that was organized as part of the CLEF (Conference and Labs of the Evaluation Forum) Labs 2018. ImageCLEF is an ongoing initiative (it started in 2003) that promotes the evaluation of technologies for annotation, indexing and retrieval with the aim of providing information access to collections of images in various usage scenarios and domains. In 2018, the 16th edition of ImageCLEF ran three main tasks and a pilot task: (1) a caption prediction task that aims at predicting the caption of a figure from the biomedical literature based only on the figure image; (2) a tuberculosis task that aims at detecting the tuberculosis type, severity and drug resistance from CT (Computed Tomography) volumes of the lung; (3) a LifeLog task (videos, images and other sources) about daily activities understanding and moment retrieval, and (4) a pilot task on visual question answering where systems are tasked with answering medical questions. The strong participation, with over 100 research groups registering and 31 submitting results for the tasks, shows an increasing interest in this benchmarking campaign.

Medical Concept Normalization for Online User-Generated Texts

Social media has become an important tool for sharing content in the last decade. People often talk about their experiences and opinions on different health-related issues e.g. they write reviews on medications, describe symptoms and ask informal questions about various health concerns. Due to the colloquial nature of the languages used in the social media, it is often difficult for an automated system to accurately interpret them for appropriate clinical understanding. To address this challenge, this paper proposes a novel approach for medical concept normalization of user-generated texts to map a health condition described in the colloquial language to a medical concept defined in standard clinical terminologies. We use multiple deep learning architectures such as convolutional neural networks (CNN) and recurrent neural networks (RNN) with input word embeddings trained on various clinical domain-specific knowledge sources. Extensive experiments on two benchmark datasets demonstrate that the proposed models can achieve up to 21.28% accuracy improvements over the existing models when we use the combination of all knowledge sources to learn neural embeddings.