Preethi Raghavan

A review of approaches to identifying patient phenotype cohorts using electronic health records

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.

Enterprise Interaction Ontology for Change Impact Analysis of Complex Systems

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 enterprisepsilas 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.

Cross-narrative Temporal Ordering of Medical Events

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.

Leveraging natural language processing of clinical narratives for phenotype modeling

This paper will explore methods for effectively extracting information from clinical narratives. The proposed research will investigate the application of state of the art natural language processing techniques to clinical narratives, such as medical admission notes, discharge summaries, progress notes, and pathology reports to extract information of interest. The objective of this knowledge discovery task is the ability to generate a chronology of events, for a given patient, ultimately leading to patient cohort discovery. This in turn facilitates efficient information retrieval and enables patient specific question answering. The paper details the proposed research problem which spans across areas of information extraction, temporal relation extraction and reasoning, and machine learning with the help of two use case scenarios: 1) Automatic patient accrual for clinical trials and 2) Information retrieval over a biorepository.

Medical event coreference resolution using the UMLS metathesaurus and temporal reasoning

We study the problem of medical event coreference resolution in clinical text. Clinical text found in clinical narratives and patient case reports usually reflects a sublanguage with medicine specific terminology. It is also frequently characterized by temporal expressions co-occurring with medical events. In this paper, we outline a method for quantifying the similarity between medical events found in the New England Journal of Medicine patient case reports. We believe this method will be valuable in classifying medical events as coreferential. We approach this problem by determining the overlap between pairs of medical events in terms of 1) the relation between medical events in the UMLS graph structure and 2) the temporal relation between the medical events. We demonstrate our ideas on a corpus of New England Journal of Medicine case reports annotated with coreference information. Preliminary results indicate a precision of 78.5% and recall of 95.5% in identifying pairs of coreferential medical events.