Search

Tables in biomedical articles often contain important information of research findings. However, they are often not available for direct uses by downstream computational applications due to its unstructured nature, with both structural and semantic complexity. In this study, we developed a deep learning-based approach that takes contextual information into consideration to recognize biomedical entities in tables headers in Randomized Controlled Trial (RCT) articles, using a manually annotated corpus. Our evaluation shows that it achieved good performance with an F1 score of 92.60% for entity recognition in headers. We believe the proposed approach for table information extraction, as well as the developed annotated corpus, would be great resources for biomedical text mining, thus facilitating other biomedical research and applications.

We propose a biomedical literature retrieval approach that incorporates a domain-specific BERT model as an auxiliary re-ranker. Experiments on TREC Precision Medicine dataset show its effectiveness in improving retrieval performance by 6.2% in inferred NDCG and 6.8% in R-precision over the best-published results. The contribution of this study is to provide evidence of incorporating BERT in a biomedical literature retrieval system, which serves the overall goal to improve the information retrieval for precision medicine.

Background Accurately recognizing rare diseases based on symptom description is an important task in patient triage, early risk stratification, and target therapies. However, due to the very nature of rare diseases, the lack of historical data poses a great challenge to machine learning-based approaches. On the other hand, medical knowledge in automatically constructed knowledge graphs (KGs) has the potential to compensate the lack of labeled training examples. This work aims to develop a rare disease classification algorithm that makes effective use of a knowledge graph, even when the graph is imperfect. Method We develop a text classification algorithm that represents a document as a combination of a “bag of words” and a “bag of knowledge terms,” where a “knowledge term” is a term shared between the document and the subgraph of KG relevant to the disease classification task. We use two Chinese disease diagnosis corpora to evaluate the algorithm. The first one, HaoDaiFu, contains 51,374 chief complaints categorized into 805 diseases. The second data set, ChinaRe, contains 86,663 patient descriptions categorized into 44 disease categories. Results On the two evaluation data sets, the proposed algorithm delivers robust performance and outperforms a wide range of baselines, including resampling, deep learning, and feature selection approaches. Both classification-based metric (macro-averaged F1 score) and ranking-based metric (mean reciprocal rank) are used in evaluation. Conclusion Medical knowledge in large-scale knowledge graphs can be effectively leveraged to improve rare diseases classification models, even when the knowledge graph is incomplete.

As a special kind of "big data," text data can be regarded as data reported by human sensors. Since humans are far more intelligent than physical sensors, text data contains useful information and knowledge about the real world, making it possible to make predictions about real-world phenomena based on text. As all application domains involve humans, text-based prediction has widespread applications, especially for optimization of decision making. While the problem of text-based prediction resembles text classification when formulated as a supervised learning problem, it is more challenging because the variable to be predicted may not be directly derivable from the text and thus there is a semantic gap between the target variable and the surface features that are often used for representing text data in conventional approaches. In this paper, we propose to bridge this gap by using knowledge graph to construct more effective features for text representation. We propose a two-step filtering algorithm to enhance such a knowledge-aware text representation for a family of entity-centric text regression tasks where the response variable can be treated as an attribute of a group of central entities. We evaluate the proposed algorithm by using two revenue prediction tasks based on reviews. The results show that the proposed algorithm can effectively leverage knowledge graphs to construct interpretable features, leading to significant improvement of the prediction accuracy over traditional features.

The dissemination of medical misinformation online presents a challenge to human health. Machine learning techniques provide a unique opportunity for decreasing the cognitive load associated with deciding upon whether any given user comment is likely to contain misinformation, but a paucity of labeled data of medical misinformation makes supervised approaches a challenge. In order to ameliorate this condition, we present a new labeled dataset of misinformative and non-misinformative comments developed over posted questions and comments on a health discussion forum. This required extraction of candidate misinformative entries from the corpus using information retrieval techniques, development of a codex and labeling strategy for the dataset, and the creation of features for use in machine learning tasks. By identifying the nine most descriptive features with regard to classification as misinformative or non-misinformative through the use of Recursive Feature Elimination, we achieved a classification accuracy of 90.1%, where the dataset is comprised 85.8% of non-misinformative comments. In our opinion, this dataset and analysis will aid the machine learning community in the development of an online misinformation classification system over user-generated content such as medical forum posts.

The popularity of smartphones and tablet computers in recent years makes mobile apps burst. Mobile apps have become the main consumers of the Internet-based services. Compared to traditional applications in the desktop computing era, mobile devices with their apps bring new opportunities and challenges to service computing community, in various aspects like service publication, discovery, interaction, composition, et al. In this paper, we propose a novel data-driven, content-based mobile apps composition approach, called Mash Droid, by leveraging a novel In-App Search mechanism, i.e., Discovering relevant services for the data and content in apps. Rather than existing techniques that usually integrate fixed Web services, our approach relies on the dynamic service discovery and flexible data exchange between several apps. The unique feature of our approach is enabling the data communication channel between apps by the content index services provided by a leading Android appstore, Wandoujia, which now has over 1,000,000 apps and 200 million users. We employ the In-App Search mechanism to define a Restful-style app model and resource-oriented app description model. Based on the models, we design a framework for dynamically discovering relevant apps that could be composed with current app's contexts. We implement a prototype to demonstrate our approach.

The prevalence of Web 2.0 techniques has led to the boom of various online communities, where topics spread ubiquitously among user-generated documents. Working together with this diffusion process is the evolution of topic content, where novel contents are introduced by documents which adopt the topic. Unlike explicit user behavior (e.g., buying a DVD), both the diffusion paths and the evolutionary process of a topic are implicit, making their discovery challenging. In this paper, we track the evolution of an arbitrary topic and reveal the latent diffusion paths of that topic in a social community. A novel and principled probabilistic model is proposed which casts our task as an joint inference problem, which considers textual documents, social influences, and topic evolution in a unified way. Specifically, a mixture model is introduced to model the generation of text according to the diffusion and the evolution of the topic, while the whole diffusion process is regularized with user-level social influences through a Gaussian Markov Random Field. Experiments on both synthetic data and real world data show that the discovery of topic diffusion and evolution benefits from this joint inference, and the probabilistic model we propose performs significantly better than existing methods.

The growth of the web has directly influenced the increase in the availability of relational data. One of the key problems in mining such data is computing the similarity between objects with heterogeneous feature types. For example, publications have many heterogeneous features like text, citations, authorship information, venue information, etc. In most approaches, similarity is estimated using each feature type in isolation and then combined in a linear fashion. However, this approach does not take advantage of the dependencies between the different feature spaces. In this paper, we propose a novel approach to combine the different sources of similarity using a regularization framework over edges in multiple graphs. We show that the objective function induced by the framework is convex. We also propose an efficient algorithm using coordinate descent [1] to solve the optimization problem. We extrinsically evaluate the performance of the proposed unified similarity measure on two different tasks, clustering and classification. The proposed similarity measure outperforms three baselines and a state-of-the-art classification algorithm on a variety of standard, large data sets.