Discovering and interpreting transcriptomic drivers of imaging traits using neural networks.

MOTIVATION: Cancer heterogeneity is observed at multiple biological levels. To improve our understanding of these differences and their relevance in medicine, approaches to link organ- and tissue-level information from diagnostic images and cellular-level information from genomics are needed. However, these 'radiogenomic' studies often use linear or shallow models, depend on feature selection, or consider one gene at a time to map images to genes. Moreover, no study has systematically attempted to understand the molecular basis of imaging traits based on the interpretation of what the neural network has learned. These studies are thus limited in their ability to understand the transcriptomic drivers of imaging traits, which could provide additional context for determining clinical outcomes. RESULTS: We present a neural network-based approach that takes high-dimensional gene expression data as input and performs non-linear mapping to an imaging trait. To interpret the models, we propose gene masking and gene saliency to extract learned relationships from radiogenomic neural networks. In glioblastoma patients, our models outperformed comparable classifiers (>0.10 AUC) and our interpretation methods were validated using a similar model to identify known relationships between genes and molecular subtypes. We found that tumor imaging traits had specific transcription patterns, e.g. edema and genes related to cellular invasion, and 10 radiogenomic traits were significantly predictive of survival. We demonstrate that neural networks can model transcriptomic heterogeneity to reflect differences in imaging and can be used to derive radiogenomic traits with clinical value. AVAILABILITY AND IMPLEMENTATION: https://github.com/novasmedley/deepRadiogenomics. CONTACT: whsu@mednet.ucla.edu. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Medical Imaging Informatics.

Imaging is one of the most important sources of clinically observable evidence that provides broad coverage, can provide insight on low-level scale properties, is noninvasive, has few side effects, and can be performed frequently. Thus, imaging data provides a viable observable that can facilitate the instantiation of a theoretical understanding of a disease for a particular patient context by connecting imaging findings to other biologic parameters in the model (e.g., genetic, molecular, symptoms, and patient survival). These connections can help inform their possible states and/or provide further coherent evidence. The field of radiomics is particularly dedicated to this task and seeks to extract quantifiable measures wherever possible. Example properties of investigation include genotype characterization, histopathology parameters, metabolite concentrations, vascular proliferation, necrosis, cellularity, and oxygenation. Important issues within the field include: signal calibration, spatial calibration, preprocessing methods (e.g., noise suppression, motion correction, and field bias correction), segmentation of target anatomic/pathologic entities, extraction of computed features, and inferencing methods connecting imaging features to biological states.

Automatic Classification of Ultrasound Screening Examinations of the Abdominal Aorta.

Our work facilitates the identification of veterans who may be at risk for abdominal aortic aneurysms (AAA) based on the 2007 mandate to screen all veteran patients that meet the screening criteria. The main research objective is to automatically index three clinical conditions: pertinent negative AAA, pertinent positive AAA, and visually unacceptable image exams. We developed and evaluated a ConText-based algorithm with the GATE (General Architecture for Text Engineering) development system to automatically classify 1402 ultrasound radiology reports for AAA screening. Using the results from JAPE (Java Annotation Pattern Engine) transducer rules, we developed a feature vector to classify the radiology reports with a decision table classifier. We found that ConText performed optimally on precision and recall for pertinent negative (0.99 (0.98-0.99), 0.99 (0.99-1.00)) and pertinent positive AAA detection (0.98 (0.95-1.00), 0.97 (0.92-1.00)), and respectably for determination of non-diagnostic image studies (0.85 (0.77-0.91), 0.96 (0.91-0.99)). In addition, our algorithm can determine the AAA size measurements for further characterization of abnormality. We developed and evaluated a regular expression based algorithm using GATE for determining the three contextual conditions: pertinent negative, pertinent positive, and non-diagnostic from radiology reports obtained for evaluating the presence or absence of abdominal aortic aneurysm. ConText performed very well at identifying the contextual features. Our study also discovered contextual trigger terms to detect sub-standard ultrasound image quality. Limitations of performance included unknown dictionary terms, complex sentences, and vague findings that were difficult to classify and properly code.

Carotid artery stenosis: wide variability in reporting formats--a review of 127 Veterans Affairs medical centers.

PURPOSE: To determine whether radiology reports describe clinically significant carotid arterial stenosis in a consistent format that is actionable by ordering clinicians. MATERIALS AND METHODS: This study was HIPAA compliant. Informed consent was waived. Institutional review board approval was obtained for this retrospective chart review, which included radiology reports of carotid artery imaging for patients hospitalized with ischemic stroke at 127 Veterans Affairs medical centers in 2006-2007. "Clinically significant results" were defined as results with at least 50% stenosis or at least moderate stenosis, excluding complete occlusion. How often clinically significant results were reported as an exact percentage stenosis (such as 60%), range (such as 50%-69%), or category (such as moderate) was determined. Among results reported as a range, how often the range bracketed clinical thresholds of 50% and 70% (typically used to determine appropriateness of carotid arterial revascularization) was determined. RESULTS: Among 2675 patients, there were 6618 carotid imaging results, of which 1015 (15%) were considered clinically significant. Among 695 clinically significant results at ultrasonography (US), 348 (50%) were described as a range, and another 314 (45%) were reported as an exact percentage stenosis. Among the 348 clinically significant US results reported as a range, 259 (74%) bracketed the thresholds of 50% or 70%. For magnetic resonance angiographic results, 48% (106 of 221) qualitatively described clinically significant results as a category, 38% (84 of 221) as an exact percentage stenosis, and 14% (31 of 221) as a range. CONCLUSION: In this national health care system, the manner in which clinically significant carotid arterial stenosis was reported varied widely.

Identifying acute ischemic stroke patients within the thrombolytic treatment window using deep learning.

BACKGROUND AND PURPOSE: Treatment of acute ischemic stroke is heavily contingent upon time, as there is a strong relationship between time clock and tissue progression. Work has established imaging biomarker assessments as surrogates for time since stroke (TSS), namely, by comparing signal mismatch between diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) imaging. Our goal was to develop an automatic technique for determining TSS from imaging that does not require subspecialist radiology expertise. METHODS: Using 772 patients (66 ± 9 years, 319 women), we developed and externally evaluated a deep learning network for classifying TSS from MR images and compared algorithm predictions to neuroradiologist assessments of DWI-FLAIR mismatch. Models were trained to classify TSS within 4.5 hours and performance metrics with confidence intervals were reported on both internal and external evaluation sets. RESULTS: Three board-certified neuroradiologists' DWI-FLAIR mismatch assessments, based on majority vote, yielded a sensitivity of .62, a specificity of .86, and a Fleiss' kappa of .46 when used to classify TSS. The deep learning method performed similarly to radiologists and outperformed previously reported methods, with the best model achieving an average evaluation accuracy, sensitivity, and specificity of .726, .712, and .741, respectively, on an internal cohort and .724, .757, and .679, respectively, on an external cohort. CONCLUSION: Our model achieved higher generalization performance on external evaluation datasets than the current state-of-the-art for TSS classification. These results demonstrate the potential of automatic assessment of onset time from imaging without the need for expertly trained radiologists.

Lamotrigine for Treating Anger in Veterans With Posttraumatic Stress Disorder.

ABSTRACT: Lamotrigine is an antiepileptic drug that was Food and Drug Administration approved in 2003 for use in the maintenance treatment of bipolar I disorder to delay the time to recurrence of new mood episodes. The mechanism by which lamotrigine achieves its therapeutic effect in the treatment of bipolar disorder is unknown. Here, we report on 2 Veterans with combat-related posttraumatic stress disorder (PTSD) endorsing significant anger, aggression, and agitation, who were treated with selective serotonin reuptake inhibitors, but whose residual symptoms of anger and aggression were ultimately successfully managed with lamotrigine augmentation. The authors would like to make mental health providers aware of the impact that lamotrigine may have on PTSD symptomology, especially when used to treat anger and aggression in patients with PTSD.

Intra-domain task-adaptive transfer learning to determine acute ischemic stroke onset time.

Treatment of acute ischemic strokes (AIS) is largely contingent upon the time since stroke onset (TSS). However, TSS may not be readily available in up to 25% of patients with unwitnessed AIS. Current clinical guidelines for patients with unknown TSS recommend the use of MRI to determine eligibility for thrombolysis, but radiology assessments have high inter-reader variability. In this work, we present deep learning models that leverage MRI diffusion series to classify TSS based on clinically validated thresholds. We propose an intra-domain task-adaptive transfer learning method, which involves training a model on an easier clinical task (stroke detection) and then refining the model with different binary thresholds of TSS. We apply this approach to both 2D and 3D CNN architectures with our top model achieving an ROC-AUC value of 0.74, with a sensitivity of 0.70 and a specificity of 0.81 for classifying TSS < 4.5 h. Our pretrained models achieve better classification metrics than the models trained from scratch, and these metrics exceed those of previously published models applied to our dataset. Furthermore, our pipeline accommodates a more inclusive patient cohort than previous work, as we did not exclude imaging studies based on clinical, demographic, or image processing criteria. When applied to this broad spectrum of patients, our deep learning model achieves an overall accuracy of 75.78% when classifying TSS < 4.5 h, carrying potential therapeutic implications for patients with unknown TSS.

A Machine Learning Approach for Classifying Ischemic Stroke Onset Time From Imaging.

Current clinical practice relies on clinical history to determine the time since stroke (TSS) onset. Imaging-based determination of acute stroke onset time could provide critical information to clinicians in deciding stroke treatment options, such as thrombolysis. The patients with unknown or unwitnessed TSS are usually excluded from thrombolysis, even if their symptoms began within the therapeutic window. In this paper, we demonstrate a machine learning approach for TSS classification using routinely acquired imaging sequences. We develop imaging features from the magnetic resonance (MR) images and train machine learning models to classify the TSS. We also propose a deep-learning model to extract hidden representations for the MR perfusion-weighted images and demonstrate classification improvement by incorporating these additional deep features. The cross-validation results show that our best classifier achieved an area under the curve of 0.765, with a sensitivity of 0.788 and a negative predictive value of 0.609, outperforming existing methods. We show that the features generated by our deep-learning algorithm correlate with the MR imaging features, and validate the robustness of the model on imaging parameter variations (e.g., year of imaging). This paper advances magnetic resonance imaging analysis one-step-closer to an operational decision support tool for stroke treatment guidance.

Predicting ischemic stroke tissue fate using a deep convolutional neural network on source magnetic resonance perfusion images.

Predicting infarct volume from magnetic resonance perfusion-weighted imaging can provide helpful information to clinicians in deciding how aggressively to treat acute stroke patients. Models have been developed to predict tissue fate, yet these models are mostly built using hand-crafted features (e.g., time-to-maximum) derived from perfusion images, which are sensitive to deconvolution methods. We demonstrate the application of deep convolution neural networks (CNNs) on predicting final stroke infarct volume using only the source perfusion images. We propose a deep CNN architecture that improves feature learning and achieves an area under the curve of 0.871 ± 0.024 , outperforming existing tissue fate models. We further validate the proposed deep CNN with existing 2-D and 3-D deep CNNs for images/video classification, showing the importance of the proposed architecture. Our work leverages deep learning techniques in stroke tissue outcome prediction, advancing magnetic resonance imaging perfusion analysis one step closer to an operational decision support tool for stroke treatment guidance.

Informatics in radiology: A prototype Web-based reporting system for onsite-offsite clinician communication.

The communication of imaging findings to a referring physician is an important role of the radiologist. However, communication between onsite and offsite physicians is a time-consuming process that can obstruct work flow and frequently involves no exchange of visual information, which is especially problematic given the importance of radiologic images for diagnosis and treatment. A prototype World Wide Web-based image documentation and reporting system was developed for use in supporting a "communication loop" that is based on the concept of a classic "wet-read" system. The proposed system represents an attempt to address many of the problems seen in current communication work flows by implementing a well-documented and easily accessible communication loop that is adaptable to different types of imaging study evaluation. Images are displayed in a native (DICOM) Digital Imaging and Communications in Medicine format with a Java applet, which allows accurate presentation along with use of various image manipulation tools. The Web-based infrastructure consists of a server that stores imaging studies and reports, with Web browsers that download and install necessary client software on demand. Application logic consists of a set of PHP (hypertext preprocessor) modules that are accessible with an application programming interface. The system may be adapted to any clinician-specialist communication loop, and, because it integrates radiologic standards with Web-based technologies, can more effectively communicate and document imaging data.

OpenSourcePACS: an extensible infrastructure for medical image management.

The development of comprehensive picture archive and communication systems (PACS) has mainly been limited to proprietary developments by vendors, though a number of freely available software projects have addressed specific image management tasks. The openSourcePACS project aims to provide an open source, common foundation upon which not only can a basic PACS be readily implemented, but to also support the evolution of new PACS functionality through the development of novel imaging applications and services. openSourcePACS consists of four main software modules: 1) image order entry, which enables the ordering and tracking of structured image requisitions; 2) an agent-based image server framework that coordinates distributed image services including routing, image processing, and querying beyond the present digital image and communications in medicine (DICOM) capabilities; 3) an image viewer, supporting standard display and image manipulation tools, DICOM presentation states, and structured reporting; and 4) reporting and result dissemination, supplying web-based widgets for creating integrated reports. All components are implemented using Java to encourage cross-platform deployment. To demonstrate the usage of openSourcePACS, a preliminary application supporting primary care/specialist communication was developed and is described herein. Ultimately, the goal of openSourcePACS is to promote the wide-scale development and usage of PACS and imaging applications within academic and research communities.

StructConsult: structured real-time wet read consultation infrastructure to support patient care.

Our research addresses how to improve physician to physician communication of patient information, and how to prevent lapses of patient care as they are referred to other clinicians within the healthcare system. The wet read consultation is defined as a rapid response to a clinical question posed by a referring physician to a clinical specialist. This research involves the development of an imaging-based wet read consultation system called StructConsult (SC), which facilitates communication between non-imaging specialist (i.e., primary care physician (PCP), emergency room (ER) physician, or referring physician), and an imaging specialist-radiologist. To facilitate data mining and effective recall, SC utilizes a data model based on the Digital Image Communications in Medicine (DICOM) standard for grayscale presentation state and structured reporting. SC requires information from four sources: (a) patient-specific demographics, clinical hypothesis, and reason for exam, (b) sentinel image capture from a DICOM image study, (c) direct capture of radiologist's image operations and annotations, and (d) radiologist's response to the chief compliant, and the reason for examination. SC allows users to add additional functionality to a Picture Archiving System to improve patient care.

Classifying Acute Ischemic Stroke Onset Time using Deep Imaging Features.

Models have been developed to predict stroke outcomes (e.g., mortality) in attempt to provide better guidance for stroke treatment. However, there is little work in developing classification models for the problem of unknown time-since-stroke (TSS), which determines a patient's treatment eligibility based on a clinical defined cutoff time point (i.e., <4.5hrs). In this paper, we construct and compare machine learning methods to classify TSS<4.5hrs using magnetic resonance (MR) imaging features. We also propose a deep learning model to extract hidden representations from the MR perfusion-weighted images and demonstrate classification improvement by incorporating these additional imaging features. Finally, we discuss a strategy to visualize the learned features from the proposed deep learning model. The cross-validation results show that our best classifier achieved an area under the curve of 0.68, which improves significantly over current clinical methods (0.58), demonstrating the potential benefit of using advanced machine learning methods in TSS classification.

Assessing Variability in Brain Tumor Segmentation to Improve Volumetric Accuracy and Characterization of Change.

Brain tumor analysis is moving towards volumetric assessment of magnetic resonance imaging (MRI), providing a more precise description of disease progression to better inform clinical decision-making and treatment planning. While a multitude of segmentation approaches exist, inherent variability in the results of these algorithms may incorrectly indicate changes in tumor volume. In this work, we present a systematic approach to characterize variability in tumor boundaries that utilizes equivalence tests as a means to determine whether a tumor volume has significantly changed over time. To demonstrate these concepts, 32 MRI studies from 8 patients were segmented using four different approaches (statistical classifier, region-based, edge-based, knowledge-based) to generate different regions of interest representing tumor extent. We showed that across all studies, the average Dice coefficient for the superset of the different methods was 0.754 (95% confidence interval 0.701-0.808) when compared to a reference standard. We illustrate how variability obtained by different segmentations can be used to identify significant changes in tumor volume between sequential time points. Our study demonstrates that variability is an inherent part of interpreting tumor segmentation results and should be considered as part of the interpretation process.

Sonographic NASCET index: a new doppler parameter for assessment of internal carotid artery stenosis.

BACKGROUND AND PURPOSE: Established Doppler parameters for carotid stenosis assessment do not reflect North American Symptomatic Carotid Endarterectomy Trial (NASCET)-style methodology. We derived a Doppler parameter, termed sonographic NASCET index (SNI), and hypothesized that the SNI would provide greater angiographic correlation and better accuracy in predicting stenosis of 70% or greater than that of currently used peak systolic velocity (PSV) measurements. METHODS: Inclusion criteria of angiographically proved carotid stenoses of 40-95% and measured proximal and distal internal carotid artery Doppler PSV values were established. Occlusions and near occlusions were specifically excluded. Doppler and angiographic data meeting the inclusion criteria from 32 carotid bifurcations were identified; actual angiographic stenoses ranged 40-89%. SNI values were calculated for each vessel. PSV and SNI were correlated with angiography by using linear regression analysis. Accuracies of SNI and PSV in predicting stenosis of 70% or greater were compared at two thresholds. RESULTS: Correlation between SNI and angiography was superior to that between PSV and angiography (r2=0.64 vs 0.38). PSV and SNI values that corresponded to 70% angiographic stenosis were 345 cm/s and 45.5, respectively. Accuracy of PSV of 345 cm/s or greater in predicting stenosis of 70% or greater was 78%, compared with 88% for SNI of 45.5 or greater. The SNI value that corresponded to a PSV threshold of 250 cm/s was 33. Accuracy of PSV of 250 cm/s or greater in predicting stenosis of 70% or greater was 81%, compared with 88% for SNI of 33 or greater. CONCLUSION: Correlation between SNI and angiography was greater than that between PSV and angiography. Accuracy of SNI in predicting stenosis of 70% or greater was also superior to that of PSV at two thresholds. These results suggest that SNI may be a better predictor of high-grade carotid stenosis than is PSV.

White matter changes in chronic alcoholic liver disease: Hypothesized association and putative biochemical mechanisms.

Advanced liver disease has long been associated with cerebral abnormalities. These abnormalities, termed acquired hepatocerebral degeneration, are typically visualized as T1 weighted hyperintensity on MRI in the deep gray matter of the basal ganglia. Recent reports, however, have demonstrated that a subset of patients with chronic alcoholic liver disease may also develop white matter abnormalities. Thus far, the morphology of these changes is not well characterized. Previous studies have described these changes as patchy, sporadic white matter abnormalities but have not posited localization of these changes to any particular white matter tracts. This paper hypothesizes that the white matter findings associated with advanced alcoholic liver disease localize to the corticocerebellar tracts. As an initial investigation of this hypothesis, 78 patients with a diagnosis of liver cirrhosis and an MRI showing clearly abnormal T1 weighted hyperintensity in the bilateral globus pallidus, characteristic of chronic liver disease, were examined for white matter signal abnormalities in the corticocerebellar tracts using FLAIR and T2 weighted images. The corticocerebellar tracts were subdivided into two regions: periventricular white matter (consisting of the sum of the centrum-semiovale and corona radiata), and lower white matter (consisting of the corona radiata, internal capsules, middle cerebral peduncles, middle cerebellar peduncles and cerebellum). As compared to matched controls, significantly greater signal abnormalities in both the periventricular white matter and lower white matter regions of the corticocerebellar tracts were observed in patients with known liver cirrhosis and abnormal T1 W hyperintensity in the globi pallidi. This difference was most pronounced in the lower white matter region of the corticocerebellar tract, with statistical significance of p<0.0005. Furthermore, the pathophysiologic mechanism underlying these changes remains unknown. This paper hypothesizes that the etiology of white matter changes associated with advanced liver disease may resemble that of white matter findings in subacute combined degeneration secondary to vitamin B12 deficiency. Specifically, significant evidence suggests that dysfunctional methionine metabolism as well as dysregulated cytokine production secondary to B12 deficiency play a major role in the development of subacute combined degeneration. Similar dysfunction of methionine metabolism and cytokine regulation is seen in alcoholic liver disease and is hypothesized in this paper to, at least in part, lead to white matter findings associated with alcoholic liver disease.

Structured reporting in neuroradiology.

We have developed a system to structure free-text neuroradiology reports using a natural language processing program and formatted the output into the digital image and communication in medicine (DICOM) standard for structured reporting (SR). DICOM SR formats the correspondence of pertinent diagnostic images to the radiologist's dictated report of clinical findings. In addition, DICOM SR allows the information to be organized into a tree structure. Individual nodes of the tree can contain individual items or lists. Structuring the content of free-text information allows the creation of hierarchies with defined relationships between the concepts contained within the report.

Accuracy of contrast-enhanced MR angiography in predicting angiographic stenosis of the internal carotid artery: linear regression analysis.

BACKGROUND AND PURPOSE: We sought to assess whether contrast-enhanced MR angiography is able to predict the degree of angiographic stenosis of the internal carotid artery within a clinically acceptable margin of error, thereby decreasing the need for angiography. In addition, we sought to assess whether adding ultrasound peak systolic velocity (PSV) as an additional regressor improves the accuracy of prediction. METHODS: A retrospective review of our institution's records for a 4-year period was conducted to identify all patients who had undergone evaluation of their carotid arteries using digital subtraction angiography, contrast-enhanced MR angiography, and ultrasonography. All internal carotid artery stenoses ranging from 10% to 90% at carotid angiography were selected (n = 22). Measurements were then obtained based on the North American Symptomatic Carotid Endarterectomy Trial style by using the digital subtraction angiograms and contrast-enhanced MR angiograms in a blinded fashion. The correlation between digital subtraction angiography data and contrast-enhanced MR angiography data was assessed by conducting linear regression analysis. Multiple regression analysis was then conducted to determine whether the inclusion of ultrasound PSV as an additional regressor increased the accuracy of prediction. RESULTS: The correlation between the degree of stenosis measured by digital subtraction angiography and that measured by contrast-enhanced MR angiography was r = 0.967. The 95% confidence interval for the line of means showed low errors bounds, ranging as low as +/-2.8%. The 95% confidence interval for individual prediction of angiographic stenosis based on a given contrast-enhanced MR angiographic measurement, however, was significantly larger, being no less than +/-13.6%. With the inclusion of PSV, the adjusted correlation was r = 0.965. CONCLUSION: A clear linear relationship exists between digital subtraction angiographic and contrast-enhanced MR angiographic measurements of carotid stenosis. Increasing severity of stenosis as measured by contrast-enhanced MR angiography corresponds to increasing severity at angiography. Although the predictive value of contrast-enhanced MR angiography is excellent in the mean, it is less reliable for predicting the degree of angiographic stenosis in the individual patient, showing rather wide confidence intervals. Furthermore, the inclusion of PSV as an additional regressor does not improve the predictive accuracy beyond that of contrast-enhanced MR angiography alone.

Effect of an imaging-based streamlined electronic healthcare process on quality and costs.

RATIONALE AND OBJECTIVES: A streamlined process of care supported by technology and imaging may be effective in managing the overall healthcare process and costs. This study examined the effect of an imaging-based electronic process of care on costs and rates of hospitalization, emergency room (ER) visits, specialist diagnostic referrals, and patient satisfaction. MATERIALS AND METHODS: A healthcare process was implemented for an employer group, highlighting improved patient access to primary care plus routine use of imaging and teleconsultation with diagnostic specialists. An electronic infrastructure supported patient access to physicians and communication among healthcare providers. The employer group, a self-insured company, manages a healthcare plan for its employees and their dependents: 4,072 employees were enrolled in the test group, and 7,639 in the control group. Outcome measures for expenses and frequency of hospitalizations, ER visits, traditional specialist referrals, primary care visits, and imaging utilization rates were measured using claims data over 1 year. Homogeneity tests of proportions were performed with a chi-square statistic, mean differences were tested by two-sample t-tests. Patient satisfaction with access to healthcare was gauged using results from an independent firm. RESULTS: Overall per member/per month costs post-implementation were lower in the enrolled population (126 dollars vs 160 dollars), even though occurrence of chronic/expensive diseases was higher in the enrolled group (18.8% vs 12.2%). Lower per member/per month costs were seen for inpatient (33.29 dollars vs 35.59 dollars); specialist referrals (21.36 dollars vs 26.84 dollars); and ER visits (3.68 dollars vs 5.22 dollars). Moreover, the utilization rate for hospital admissions, ER visits, and traditional specialist referrals were significantly lower in the enrolled group, although primary care and imaging utilization were higher. Comparison to similar employer groups showed that the company's costs were lower than national averages (119.24 dollars vs 146.32 dollars), indicating that the observed result was not attributable to normalization effects. Patient satisfaction with access to healthcare ranked in the top 21st percentile. CONCLUSION: A streamlined healthcare process supported by technology resulted in higher patient satisfaction and cost savings despite improved access to primary care and higher utilization of imaging.

Evidence-based radiology: requirements for electronic access.

RATIONALE AND OBJECTIVES: The purpose of this study was to determine the electronic requirements for supporting evidence-based radiology in today's medical environment. MATERIALS AND METHODS: A software engineering technique, use case modeling, was performed for several clinical settings to determine the use of imaging and its role in evidence-based practice, with particular attention to issues relating to data access and the usage of clinical information. From this basic understanding, the analysis was extended to encompass evidence-based radiologic research and teaching. RESULTS: The analysis showed that a system supporting evidence-based radiology must (a) provide a single point of access to multiple clinical data sources so that patient data can be readily used and incorporated into comprehensive radiologic consults and (b) provide quick access to external evidence in the way of similar patient cases and published medical literature, thus supporting evidence-based practice. CONCLUSION: Information infrastructures that aim to support evidence-based radiology not only must address issues related to the integration of clinical data from heterogeneous databases, but must facilitate access and filtering of patient data in order to improve radiologic consultation.