We propose a novel methodology to generate domain-specific large-scale question answering (QA) datasets by re-purposing existing annotations for other NLP tasks. We demonstrate an instance of this methodology in generating a large-scale QA dataset for electronic medical records by leveraging existing expert annotations on clinical notes for various NLP tasks from the community shared i2b2 datasets. The resulting corpus (emrQA) has 1 million question-logical form and 400,000+ question-answer evidence pairs. We characterize the dataset and explore its learning potential by training baseline models for question to logical form and question to answer mapping.

We seek to address the lack of labeled data (and high cost of annotation) for textual entailment in some domains.To that end, we first create (for experimental purposes) an entailment dataset for the clinical domain, and a highly competitive supervised entailment system, ENT, that is effective (out of the box) on two domains.We then explore self-training and active learning strategies to address the lack of labeled data.With self-training, we successfully exploit unlabeled data to improve over ENT by 15% F-score on the newswire domain, and 13% F-score on clinical data.On the other hand, our active learning experiments demonstrate that we can match (and even beat) ENT using only 6.6% of the training data in the clinical domain, and only 5.8% of the training data in the newswire domain.

Cross-narrative temporal ordering of medical events is essential to the task of generating a comprehensive timeline over a patient's history.We address the problem of aligning multiple medical event sequences, corresponding to different clinical narratives, comparing the following approaches: (1) A novel weighted finite state transducer representation of medical event sequences that enables composition and search for decoding, and (2) Dynamic programming with iterative pairwise alignment of multiple sequences using global and local alignment algorithms.The cross-narrative coreference and temporal relation weights used in both these approaches are learned from a corpus of clinical narratives.We present results using both approaches and observe that the finite state transducer approach performs performs significantly better than the dynamic programming one by 6.8% for the problem of multiple-sequence alignment.

OBJECTIVE: To summarize literature describing approaches aimed at automatically identifying patients with a common phenotype. MATERIALS AND METHODS: We performed a review of studies describing systems or reporting techniques developed for identifying cohorts of patients with specific phenotypes. Every full text article published in (1) Journal of American Medical Informatics Association, (2) Journal of Biomedical Informatics, (3) Proceedings of the Annual American Medical Informatics Association Symposium, and (4) Proceedings of Clinical Research Informatics Conference within the past 3 years was assessed for inclusion in the review. Only articles using automated techniques were included. RESULTS: Ninety-seven articles met our inclusion criteria. Forty-six used natural language processing (NLP)-based techniques, 24 described rule-based systems, 41 used statistical analyses, data mining, or machine learning techniques, while 22 described hybrid systems. Nine articles described the architecture of large-scale systems developed for determining cohort eligibility of patients. DISCUSSION: We observe that there is a rise in the number of studies associated with cohort identification using electronic medical records. Statistical analyses or machine learning, followed by NLP techniques, are gaining popularity over the years in comparison with rule-based systems. CONCLUSIONS: There are a variety of approaches for classifying patients into a particular phenotype. Different techniques and data sources are used, and good performance is reported on datasets at respective institutions. However, no system makes comprehensive use of electronic medical records addressing all of their known weaknesses.

Reasoning about the impact of change is critical throughout the Information Technology (IT) architecture lifecycle management processes and this is especially challenging because installed architectures are complex, evolve constantly, and most changes have some global impact. We present an enterprise-interaction ontology for integrated query, analysis, and monitoring that supports features to allow architects and engineers pin-point the impact of change to the installed architecture before implementation. The ontology represents select associations between the enterprise’s business processes, services and infrastructure so that significant consequences of a change are propagated to affected areas based on underlying rules. Thus, interdependencies and relationships that are not obvious are identified and the impact is quantified. This allows the architect to know the complete scope of modifications required in order to accomplish a change in a manner consistent with best practices (like ITIL version 3). We illustrate - 1) the rules and taxonomy relationships that give us the ability to propagate changes and determine the impact, and 2) how actual questions and decision-making during the architecture management processes can be better supported using a more precise and factual understanding. Not only does the interaction methodology help analyze the potential impact of adding a new component, a change due to an incident, or the deletion of an existing component from the architecture, it also supports business-IT alignment processes like chargeback, capacity management and disaster recovery.