INTRODUCTION:Identification of adverse events and determination of their seriousness ensures timely detection of potential patient safety concerns. Adverse event seriousness is a key factor in defining reporting timelines and is often performed manually by pharmacovigilance experts. The dramatic increase in the volume of safety reports necessitates exploration of scalable solutions that also meet reporting timeline requirements.OBJECTIVE:The aim of this study was to develop an augmented intelligence methodology for automatically identifying adverse event seriousness in spontaneous, solicited, and medical literature safety reports. Deep learning models were evaluated for accuracy and/or the F1 score against a ground truth labeled by pharmacovigilance experts.METHODS:Using a stratified random sample of safety reports received by Celgene, we developed three neural networks for addressing identification of adverse event seriousness: (1) a binary adverse-event level seriousness classifier; (2) a classifier for determining seriousness categorization at the adverse-event level; and (3) an annotator for identifying seriousness criteria terms to provide supporting evidence at the document level.RESULTS:The seriousness classifier achieved an accuracy of 83.0% in post-marketing reports, 92.9% in solicited reports, and 86.3% in medical literature reports. F1 scores for seriousness categorization were 77.7 for death, 78.9 for hospitalization, and 75.5 for important medical events. The seriousness annotator achieved an F1 score of 89.9 in solicited reports, and 75.2 in medical literature reports.CONCLUSIONS:The results of this study indicate that a neural network approach can provide an accurate and scalable solution for potentially augmenting pharmacovigilance practitioner determination of adverse event seriousness in spontaneous, solicited, and medical literature reports.

Regulations are increasing the scope of activities that fall under the remit of drug safety. Currently, individual case safety report (ICSR) collection and collation is done manually, requiring pharmacovigilance professionals to perform many transactional activities before data are available for assessment and aggregated analyses. For a biopharmaceutical company to meet its responsibilities to patients and regulatory bodies regarding the safe use and distribution of its products, improved business processes must be implemented to drive the industry forward in the best interest of patients globally. Augmented intelligent capabilities have already demonstrated success in capturing adverse events from diverse data sources. It has potential to provide a scalable solution for handling the ever-increasing ICSR volumes experienced within the industry by supporting pharmacovigilance professionals’ decision-making.

A mechanism is provided in a data processing system having a processor and a memory. The memory comprises instructions which are executed by the processor to cause the processor to implement a training system for finding an optimal surface for hierarchical classification task on an ontology. The training system receives a training data set and a hierarchical classification ontology data structure. The training system generates a neural network architecture based on the training data set and the hierarchical classification ontology data structure. The neural network architecture comprises an indicative layer, a parent tier (PT) output and a lower leaf tier (LLT) output. The training system trains the neural network architecture to classify the training data set to leaf nodes at the LLT output and parent nodes at the PT output. The indicative layer in the neural network architecture determines a surface that passes through each path from a root to a leaf node in the hierarchical ontology data structure. The training system trains a classifier model for a cognitive system using the surface and the training data set.

Scientific progress depends on formulating testable hypotheses informed by the literature. In many domains, however, this model is strained because the number of research papers exceeds human readability. Here, we developed computational assistance to analyze the biomedical literature by reading PubMed abstracts to suggest new hypotheses. The approach was tested experimentally on the tumor suppressor p53 by ranking its most likely kinases, based on all available abstracts. Many of the best-ranked kinases were found to bind and phosphorylate p53 (P value = 0.005), suggesting six likely p53 kinases so far. One of these, NEK2, was studied in detail. A known mitosis promoter, NEK2 was shown to phosphorylate p53 at Ser315 in vitro and in vivo and to functionally inhibit p53. These bona fide validations of text-based predictions of p53 phosphorylation, and the discovery of an inhibitory p53 kinase of pharmaceutical interest, suggest that automated reasoning using a large body of literature can generate valuable molecular hypotheses and has the potential to accelerate scientific discovery.

State-of-the-art methods for product recommendation encounter a significant performance drop in categories where a user has no purchase history. This problem needs to be addressed since current online retailers are moving beyond single category and attempting to be diversified. In this article, we investigate the challenging problem of product recommendation in unexplored categories and discover that the price, a factor comparable across categories, can improve the recommendation performance significantly. We introduce the price utility concept to characterize users’ sense of price and propose three different utility functions. We show that user price preference in a category is a distribution and we mine typical user price preference patterns based on three different types of distance between distributions. We fuse user price preference through regularization and joint factorization to boost recommendation performance in both browsing and buying shopping orientations. Experimental results show that fusing user price preference improves performance in a series of recommendation tasks: unexplored category recommendation, product recommendation under a given unexplored category, and product recommendation under generic unexplored categories.

While we have made significant progress over image understanding and search, how to meet the ultimate goal of satisfying both exploration and exploitation in one single system is still an open challenge. In the context of landmark images, it means that a system should not only be able to help users to quickly locate the photo they are interested in (exploitation), but also to discover different parts of the landmark which have never been seen before (exploration), which is a common request as evidenced by many recent multimedia studies. To the best of our knowledge, existing systems mainly focus on either exploration (e.g., photo browsing) or exploitation (e.g., representative photo identification), while users' need of exploration and exploitation is dynamically mixed. In this paper, we tackle the challenge by organizing landmark images into a hierarchical summary which gives user the flexibility of conducting both exploration and exploitation. In the hierarchical summary construction, we introduce two principles: the coherence principle and the diversity principle. Behind these two principles, the intrinsic concept is “detail-level,” which measures how much detail that an image reflects for a certain landmark. A new objective function is derived from the definition of both exploration and exploitation experience on detail-level. The problem of finding an optimal hierarchical summary is formulated as searching over a space of trees for the one that achieves the best objective score. Extensive quantitative experimental results and comprehensive user studies show that the optimized hierarchical summary is able to satisfy both experiences simultaneously.

Lead curve detection in design drawings is a critical problem in a wide range of applications ranging from checking similar drawings in patent granting to constructing hyperlinks between image and text description in digitalization. The difficulty of the problem are two folds: unknown end point of lead curve and complex crossings. However, most previous curve detection algorithms are usually applied in simple or no crossing situations. We make four contributions in solving the problem: (1) we transform the problem into a new problem that finds an optimal path with the best score in the cross-point graph. We introduce the “cross-point graph” representation which captures the topology of cross-point connectedness. Based on the original drawing and the corresponding cross-point graph, we introduce the coupling concept “curve-path”, which correlates the curve in the original drawing with the corresponding path in the cross-point graph. (2) we design a set of joint feature representations for curve-path which describes different characteristics of a curve and its corresponding path. (3) we define a task specific loss function for our customized structured SVM. We propose a mixed negative instance sampling strategy to learn the weights of different joint feature representations. We prune the search space effectively for fast lead curve detection. (4) we build a software to efficiently facilitate manual lead curve labeling. We release the patent drawing dataset with groundtruth to public for lead curve detection research. The extensive experimental results prove the effectiveness of our methods.

We present KnIT, the Knowledge Integration Toolkit, a system for accelerating scientific discovery and predicting previously unknown protein protein interactions. Such predictions enrich biological research and are pertinent to drug discovery and the understanding of disease. Unlike a prior study, KnIT is now fully automated and demonstrably scalable. It extracts information from the scientific literature, automatically identifying direct and indirect references to protein interactions, which is knowledge that can be represented in network form. It then reasons over this network with techniques such as matrix factorization and graph diffusion to predict new, previously unknown interactions. The accuracy and scope of KnIT's knowledge extractions are validated using comparisons to structured, manually curated data sources as well as by performing retrospective studies that predict subsequent literature discoveries using literature available prior to a given date. The KnIT methodology is a step towards automated hypothesis generation from text, with potential application to other scientific domains.

Topic models have been widely used for text analysis. Previous topic models have enjoyed great success in mining the latent topic structure of text documents. With many efforts made on endowing the resulting document-topic distributions with different motivations, however, none of these models have paid any attention on the resulting topic-word distributions. Since topic-word distribution also plays an important role in the modeling performance, topic models which emphasize only the resulting document-topic representations but pay less attention to the topic-term distributions are limited. In this paper, we propose the Orthogonalized Topic Model (OTM) which imposes an orthogonality constraint on the topic-term distributions. We also propose a novel model fitting algorithm based on the generalized Expectation-Maximization algorithm and the Newthon-Raphson method. Quantitative evaluation of text classification demonstrates that OTM outperforms other baseline models and indicates the important role played by topic orthogonalizing.