Marta Heilbrun - Academia.edu (original) (raw)

Papers by Marta Heilbrun

Fig. 1. VISCARETRAILS session on a dataset of pancreatic cancer patients. The central top display... more Fig. 1. VISCARETRAILS session on a dataset of pancreatic cancer patients. The central top display shows a Timed Word Tree with staging events (STAGE I, STAGE II, STAGE III, STAGE IV) and rooted in the death event (DEAD). Selecting the stage nodes, corresponding to severity and extent of disease, the bottom left plot presents survival curves indicating the fraction of each of the four sets of staged subjects that were still alive after t days, and the box-plot represents the distribution of the time distance the death event. This visualization confirms that this specific dataset follows the known patterns for pancreatic cancer patients and is obtained with just a few intuitive mouse gestures. Abstract — As a mandate in the 2009 ARRS act, all US health care systems are moving toward electronic health record (EHR) systems to capture and store patient data. The EHR is a rich source of health information about individual patients and/or populations. The ability to analyze and identify me...

Journal of the American College of Radiology, 2019

Recent advances in machine learning and artificial intelligence offer promising applications to r... more Recent advances in machine learning and artificial intelligence offer promising applications to radiology quality improvement initiatives as they relate to the radiology value network. Coordination within the interlocking web of systems, events, and stakeholders in the radiology value network may be mitigated though standardization, automation, and a focus on workflow efficiency. In this article the authors present applications of these various strategies via use cases for quality improvement projects at different points in the radiology value network. In addition, the authors discuss opportunities for machine-learning applications in data aggregation as opposed to traditional applications in data extraction.

Journal of Trauma and Acute Care Surgery, 2019

The Journal of Urology, 2018

Introduction: Altered renal function commonly affects patients with cirrhosis, a consequence of c... more Introduction: Altered renal function commonly affects patients with cirrhosis, a consequence of chronic liver disease. From lowdose contrast material-enhanced magnetic resonance (MR) renography, we can estimate the Glomerular Filtration Rate (GFR), an important parameter to assess renal function. Two-dimensional MR images are acquired every 2 seconds for approximately 5 minutes during free breathing, which results in a dynamic series of 140 images representing kidney filtration over time. This specific acquisition presents dynamic contrast changes but is also challenged by organ motion due to breathing. Rather than use conventional image registration techniques, we opted for an alternative method based on object detection. We developed a novel analysis framework available under a stand-alone toolkit to efficiently register dynamic kidney series, manually select regions of interest, visualize the concentration curves for these ROIs, and fit them into a model to obtain GFR values. Thi...

© 2010 Mosby, Inc. All rights reserved. Corresponding Author: Marta E. Heilbrun, MD, Dept. of Rad... more © 2010 Mosby, Inc. All rights reserved. Corresponding Author: Marta E. Heilbrun, MD, Dept. of Radiology, University of Utah, 30 North 1900 East #1A071, Salt Lake City, UT 84132-2140, Phone: 801-581-7553, Fax: 801-581-2414, marta.heilbrun@hsc.utah.edu. Publisher's Disclaimer: This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final citable form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

As a mandate in the 2009 ARRS act, all US health care systems are moving toward electronic health... more As a mandate in the 2009 ARRS act, all US health care systems are moving toward electronic health record (EHR) systems to capture and store patient data. The EHR is a rich source of health information about individual patients and/or populations. The ability to analyze and identify meaningful patterns in this data has the potential to produce important knowledge. Yet, there is still a considerable gap between what answers are captured in this record and what answers can be effectively extracted from it. To reduce this gap, more intuitive ways of posing questions and obtaining answers are needed. In this paper we present VISCARETRAILS, a system based on timed word trees visualization that summarizes event paths relative to a given root event and are obtained through a simple drag-and-drop user interface. These summaries visually convey information about the nature, frequency and average timing of the event paths, and serve as a natural starting point to obtain further details and com...

Narrative reporting has been the mainstay of the radiologist’s work for as long as the domain of ... more Narrative reporting has been the mainstay of the radiologist’s work for as long as the domain of radiology has been in existence. Structured radiology reporting, containing coded and consistent information, will facilitate information exchange in the digital health record. This chapter will define structured reporting, review recent legislation that incentivizes structured reporting, and discuss the quality and value propositions that are supported by structured reporting. Constrained vocabularies and coded terminologies, including the American College of Radiology’s disease-specific Imaging Reporting and Data Systems (IRADS) and the Radiological Society of North America’s RadLex™, are described. Data exchange tools including the Management of Radiology Report Templates (MRRT) and Common Data Elements (CDEs) are discussed. Benefits of machine learning from report analysis are discussed. Limitations to implementation and realizing the full benefits of structured reporting are also ac...

The communication of critical findings observed in radiology imaging studies between the radiolog... more The communication of critical findings observed in radiology imaging studies between the radiologist and the ordering provider is a key factor in providing efficacious patient care [1]. Currently, the most common form of communication is a physician-to-physician telephone conversation, initiated by the radiologist at the time of image interpretation. This process may be tedious, slow, and inefficient.

Journal of the American College of Radiology

Pyelonephritis refers to infection involving the renal parenchyma and renal pelvis. In most patie... more Pyelonephritis refers to infection involving the renal parenchyma and renal pelvis. In most patients, uncomplicated pyelonephritis is diagnosed clinically and responds quickly to appropriate antibiotic treatment. If treatment is delayed, the patient is immunocompromised, or for other reasons, microabscesses that form during the acute phase of pyelonephritis may coalesce, forming a renal abscess. Patients with underlying diabetes are more vulnerable to complications, including emphysematous pyelonephritis in addition to abscess formation. Additionally, diabetics may not have the typical flank tenderness that helps to differentiate pyelonephritis from a lower urinary tract infection. Additional high-risk populations may include those with anatomic abnormalities of the urinary tract, vesicoureteral reflux, obstruction, pregnancy, nosocomial infection, or infection by treatment-resistant pathogens. Treatment goals include symptom relief, elimination of infection to avoid renal damage, and identification of predisposing factors to avoid future recurrences. The primary imaging modalities used in patients with pyelonephritis are CT, MRI, and ultrasound. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

Journal of the American College of Radiology : JACR, Jan 26, 2018

To quantify the monetary and time costs associated with oral contrast administration in the emerg... more To quantify the monetary and time costs associated with oral contrast administration in the emergency department (ED) for patients with nontraumatic abdominal pain and to evaluate the cost savings associated with an institutional policy change in the criteria for oral contrast administration. A HIPAA-complaint, institutional review board-approved time-driven activity-based costing analysis was performed using both prospective time studies and retrospective data obtained from a quaternary care center. Retrospective data spanned a 1-year period (January 1, 2016, to December 31, 2016). A process map was generated. Examination volume-related data, labor costs, and material costs were determined and applied to a base-case model. Univariate and multivariate sensitivity analyses were conducted. Multivariate analysis was used to estimate the cost savings associated with a policy change eliminating oral contrast for patients with body mass index ≥ 25 kg/m, no prior abdominal surgery within 3...

The journal of trauma and acute care surgery, Jan 21, 2018

Pancreatic trauma results in high morbidity and mortality, in part, due to delay in diagnosis and... more Pancreatic trauma results in high morbidity and mortality, in part, due to delay in diagnosis and subsequent organ dysfunction. Optimal operative management strategies remain unclear. We therefore sought to determine CT accuracy in diagnosing pancreatic injury and the morbidity and mortality associated with varying operative strategies. We created a multi-center, pancreatic trauma registry from 18 level 1 and 2 trauma centers. Adult, blunt or penetrating injured patients from 2005-2012 were analyzed. Sensitivity and specificity of CT scan identification of main pancreatic duct injury was calculated against operative findings. Independent predictors for mortality, ARDS and pancreatic fistula and/or pseudocyst were identified through multivariate regression analysis. The association between outcomes and operative management was measured. We identified 704 pancreatic injury patients of whom 584 (83%) underwent a pancreas-related procedure. CT grade modestly correlated with OR grade (r ...