Showing papers by "James J. Cimino published in 2016"

Impending Challenges for the Use of Big Data.

Abstract: Advances in data storage and data analysis materialized also in health care data. In recent years, we have seen an emphasis on using the full potential (1, 2) of these data to answer questions such as: who were the patients that received radiation therapy as primary treatment? Who among such patients experienced radiation therapyerelated complications? Given everything you know about my case, what is the chance that if I choose radiation therapy, I will experience incontinence in the next year? Factors contributing to this trend include more rapid data querying technologies, cheaper data storage, addition of genomic data to traditional clinical data sets, “meaningful use incentives” for increasing the adoption of electronic health records, and recent emergence of precision medicine (3). In this perspective paper, we discuss several challenges ahead for big data, some that are being addressed now and others that will need to be addressed in the near future. The list of challenges presented here is not meant to be an exhaustive list but is rather driven by our big data experience. For each challenge, we provide comments on current approaches to address the challenge.

Visual assessment of the similarity between a patient and trial population: Is This Clinical Trial Applicable to My Patient?

Abstract: Background: A critical consideration when applying the results of a clinical trial to a particular patient is the degree of similarity of the patient to the trial population. However, similarity assessment rarely is practical in the clinical setting. Here, we explore means to support similarity assessment by clinicians. Methods: A scale chart was developed to represent the distribution of reported clinical and demographic characteristics of clinical trial participant populations. Constructed for an individual patient, the scale chart shows the patient’s similarity to the study populations in a graphical manner. A pilot test case was conducted using case vignettes assessed by clinicians. Two pairs of clinical trials were used, each addressing a similar clinical question. Scale charts were manually constructed for each simulated patient. Clinicians were asked to estimate the degree of similarity of each patient to the populations of a pair of trials. Assessors relied on either the scale chart, a summary table (aligning characteristics of 2 trial populations), or original trial reports. Assessment time and between-assessor agreement were compared. Population characteristics considered important by assessors were recorded. Results: Six assessors evaluated 6 cases each. Using a visual scale chart, agreement between physicians was higher and the time required for similarity assessment was comparable Conclusion: We suggest that further research is warranted to explore visual tools facilitating the choice of the most applicable clinical trial to a specific patient. Automating patient and trial population characteristics extraction is key to support this effort.

Performance Comparison between Two Solutions for Filtering Data Sets with Hierarchical Structures

Abstract: Performance Comparison between Two Solutions for Filtering Data Sets with Hierarchical Structures Controlled terminologies with hierarchical structures are utilized widely to code diagnoses (eg, International Classification of Diseases, ICD) and other medical concepts (eg, Medical Subject Headings, MeSH) in healthcare data sets The coded data sets can be useful for advanced statistical analysis or to explore aggregated effects by using multiple data sets across institutions The analysis of results can be evidence for administrative decisions (eg, resources allocation) or to validate hypotheses However, publicly accessible analytic tools for such data sets are lacking Our research team has developed and published the methods for filtering, analysing and visualizing such data sets Current work focuses on the development of an online tool to assist other researchers with applying our methods We report on a comparison of two approaches to developing the tool in order to provide evidence about the selection of tools and programming language

i3b3: Infobuttons for i2b2 as a Mechanism for Investigating the Information Needs of Clinical Researchers.

Abstract: The information needs of clinicians, as they interact with the EHR, are well-studied. Clinical researchers also interact with the EHR and, while they might be expected to have some similar needs, the unique needs that arise due to nature of their work remain largely unstudied. For clinicians, infobuttons (context-aware hyperlinks) provide a mechanism of studying these information needs. Here we describe the integration of infobuttons into i2b2, a popular data warehouse commonly used by clinical researchers, using a plugin. A preliminary survey of i2b2 developers suggests a general interest in infobuttons for i2b2 and indicates good likelihood for their deployment, where they may be used as a tool for further studying these needs in greater detail.