The "National Integrated Medical Imaging System" [NIMIS]-friend, not nimesis!

INTRODUCTION: The "National Integrated Medical Imaging System" or NIMIS went live in 2011 and allows the movement of patient radiology imaging throughout the Irish health system. At the time of its launch, NIMIS was not only going to allow the filmless passage of patient radiology imaging but it was also envisaged that it would act as a medical image archive. The aim of this study was to assess the awareness and use of non-consultant hospital doctors and hospital consultants with regard to this medical image archive/referral function of NIMIS. METHODS: A survey was carried out on 50 doctors across all specialities and grades at Tullamore Hospital looking at different aspects of the use of NIMIS. RESULTS: Ninety-four percent of respondents use NIMIS on a daily basis and 6% use it on a weekly basis. The primary reason for using NIMIS was found to be "Viewing and Ordering Imaging" in 92% of those surveyed with 8% stating it was "Viewing imaging/reports". Ninety-eight percent surveyed said they had never used NIMIS to send a referral form or clinical photograph and 82% were not aware of this potential function. The majority of those surveyed stated that they either agreed or strongly agreed NIMIS is user-friendly. CONCLUSION: NIMIS allows the safe and confidential flow of patient images and clinical information in the Irish health system. It could provide definite potential in the areas of clinical conferencing, multidisciplinary meetings and remote patient assessment along with collaborative research and education.

The LOINC RSNA radiology playbook - a unified terminology for radiology procedures.

Objective: This paper describes the unified LOINC/RSNA Radiology Playbook and the process by which it was produced. Methods: The Regenstrief Institute and the Radiological Society of North America (RSNA) developed a unification plan consisting of six objectives 1) develop a unified model for radiology procedure names that represents the attributes with an extensible set of values, 2) transform existing LOINC procedure codes into the unified model representation, 3) create a mapping between all the attribute values used in the unified model as coded in LOINC (ie, LOINC Parts) and their equivalent concepts in RadLex, 4) create a mapping between the existing procedure codes in the RadLex Core Playbook and the corresponding codes in LOINC, 5) develop a single integrated governance process for managing the unified terminology, and 6) publicly distribute the terminology artifacts. Results: We developed a unified model and instantiated it in a new LOINC release artifact that contains the LOINC codes and display name (ie LONG_COMMON_NAME) for each procedure, mappings between LOINC and the RSNA Playbook at the procedure code level, and connections between procedure terms and their attribute values that are expressed as LOINC Parts and RadLex IDs. We transformed all the existing LOINC content into the new model and publicly distributed it in standard releases. The organizations have also developed a joint governance process for ongoing maintenance of the terminology. Conclusions: The LOINC/RSNA Radiology Playbook provides a universal terminology standard for radiology orders and results.

Medical Devices; Radiology Devices; Classification of the Absorbable Perirectal Spacer. Final order.

The Food and Drug Administration (FDA or we) is classifying the absorbable perirectal spacer into class II (special controls). The special controls that apply to the device type are identified in this order and will be part of the codified language for the absorbable perirectal spacer's classification. We are taking this action because we have determined that classifying the device into class II (special controls) will provide a reasonable assurance of safety and effectiveness of the device. We believe this action will also enhance patients' access to beneficial innovative devices, in part by reducing regulatory burdens.

Expanding a radiology lexicon using contextual patterns in radiology reports.

Objective: Distributional semantics algorithms, which learn vector space representations of words and phrases from large corpora, identify related terms based on contextual usage patterns. We hypothesize that distributional semantics can speed up lexicon expansion in a clinical domain, radiology, by unearthing synonyms from the corpus. Materials and Methods: We apply word2vec, a distributional semantics software package, to the text of radiology notes to identify synonyms for RadLex, a structured lexicon of radiology terms. We stratify performance by term category, term frequency, number of tokens in the term, vector magnitude, and the context window used in vector building. Results: Ranking candidates based on distributional similarity to a target term results in high curation efficiency: on a ranked list of 775 249 terms, >50% of synonyms occurred within the first 25 terms. Synonyms are easier to find if the target term is a phrase rather than a single word, if it occurs at least 100× in the corpus, and if its vector magnitude is between 4 and 5. Some RadLex categories, such as anatomical substances, are easier to identify synonyms for than others. Discussion: The unstructured text of clinical notes contains a wealth of information about human diseases and treatment patterns. However, searching and retrieving information from clinical notes often suffer due to variations in how similar concepts are described in the text. Biomedical lexicons address this challenge, but are expensive to produce and maintain. Distributional semantics algorithms can assist lexicon curation, saving researchers time and money.

Temporal bone radiology report classification using open source machine learning and natural langue processing libraries.

BACKGROUND: Radiology reports are a rich resource for biomedical research. Prior to utilization, trained experts must manually review reports to identify discrete outcomes. The Audiological and Genetic Database (AudGenDB) is a public, de-identified research database that contains over 16,000 radiology reports. Because the reports are unlabeled, it is difficult to select those with specific abnormalities. We implemented a classification pipeline using a human-in-the-loop machine learning approach and open source libraries to label the reports with one or more of four abnormality region labels: inner, middle, outer, and mastoid, indicating the presence of an abnormality in the specified ear region. METHODS: Trained abstractors labeled radiology reports taken from AudGenDB to form a gold standard. These were split into training (80 %) and test (20 %) sets. We applied open source libraries to normalize and convert every report to an n-gram feature vector. We trained logistic regression, support vector machine (linear and Gaussian), decision tree, random forest, and naïve Bayes models for each ear region. The models were evaluated on the hold-out test set. RESULTS: Our gold-standard data set contained 726 reports. The best classifiers were linear support vector machine for inner and outer ear, logistic regression for middle ear, and decision tree for mastoid. Classifier test set accuracy was 90 %, 90 %, 93 %, and 82 % for the inner, middle, outer and mastoid regions, respectively. The logistic regression method was very consistent, achieving accuracy scores within 2.75 % of the best classifier across regions and a receiver operator characteristic area under the curve of 0.92 or greater across all regions. CONCLUSIONS: Our results indicate that the applied methods achieve accuracy scores sufficient to support our objective of extracting discrete features from radiology reports to enhance cohort identification in AudGenDB. The models described here are available in several free, open source libraries that make them more accessible and simplify their utilization as demonstrated in this work. We additionally implemented the models as a web service that accepts radiology report text in an HTTP request and provides the predicted region labels. This service has been used to label the reports in AudGenDB and is freely available.

Novedades de la 5ª edición del sistema breast imaging reporting and data system (BI-RADS(R)) del Colegio Americano de Radiología / Novel features of the 5th edition of the breast imaging reporting and data system (BI-RADS(R)) of the American College of Radiology

En 1992 el Colegio Americano de Radiología (ACR) publicó la primera edición del breast imaging reporting and data system (BI-RADS(R)), un sistema para clasificar los hallazgos mamográficos. Desde entonces se ha convertido en una herramienta fundamental en: la descripción de los hallazgos por imagen de la mama, la asignación en categorías diagnósticas estableciendo el grado de sospecha, la actitud a seguir en cada caso y la estandarización del informe radiológico. Los cambios principales de la 5.a edición del BI-RADS(R) tienen como objeto dar más flexibilidad en situaciones donde las ediciones pasadas creaban confusión. La nueva edición ha introducido cambios en el léxico radiológico, en la estandarización del informe, en la monitorización de los resultados y en el manejo del paciente en algunas situaciones clínicas. Para facilitar la comprensión del informe radiológico, algunos descriptores se han eliminado y otros se han modificado. También se han unificado los descriptores de determinados hallazgos en los distintos métodos de imagen (mamografía, ultrasonidos y resonancia magnética). En cuanto a la categoría BI-RADS(R), ahora los radiólogos pueden añadir información adicional y especificar si se debe hacer biopsia en lugar de seguimiento en base a circunstancias clínicas. En el atlas se incluye un mayor número de imágenes y citas bibliográficas (AU)

The breast imaging reporting and data system (BI-RADS(R)) was first published by the American College of Radiology in 1992, with the objective of classifying mammographic findings. Since then, it has become an essential tool for the description of imaging findings in breast lesions, the determination of diagnostic categories to establish the degree of suspicion, the approach to be taken, and the standardization of the radiology report. The main changes in the 5.th edition aim to provide greater flexibility in those situations that gave rise to confusion in the previous editions. The new edition has introduced changes in the radiological lexicon, report standardization, monitoring of the results and management of the patient in specific clinical situations. To simplify the report, some descriptors have been eliminated and others have been modified. Additionally, some descriptors have been unified among different imaging techniques (mammography, ultrasound and magnetic resonance). Concerning BI-RADS(R) category, radiologists can now add additional information to specify if a biopsy should be performed instead of clinical follow-up. More images and literature references have been included in the atlas (AU)

Oh No, New Codes!

It would be easy to think that there is no way that there could be more coding changes, but alas, that is not the case. A new year is upon us and so are new coding changes. This year there are more changes for interventional services than regular diagnostic services but the new changes will impact every radiology organization. As of the writing of this article all of the supporting guidance that we look to for additional information is not yet available so more guidance will be needed to ensure proper code assignment. The following information will allow you to start on the update journey within your organization.

Understanding and Confronting Our Mistakes: The Epidemiology of Error in Radiology and Strategies for Error Reduction.

Arriving at a medical diagnosis is a highly complex process that is extremely error prone. Missed or delayed diagnoses often lead to patient harm and missed opportunities for treatment. Since medical imaging is a major contributor to the overall diagnostic process, it is also a major potential source of diagnostic error. Although some diagnoses may be missed because of the technical or physical limitations of the imaging modality, including image resolution, intrinsic or extrinsic contrast, and signal-to-noise ratio, most missed radiologic diagnoses are attributable to image interpretation errors by radiologists. Radiologic interpretation cannot be mechanized or automated; it is a human enterprise based on complex psychophysiologic and cognitive processes and is itself subject to a wide variety of error types, including perceptual errors (those in which an important abnormality is simply not seen on the images) and cognitive errors (those in which the abnormality is visually detected but the meaning or importance of the finding is not correctly understood or appreciated). The overall prevalence of radiologists' errors in practice does not appear to have changed since it was first estimated in the 1960s. The authors review the epidemiology of errors in diagnostic radiology, including a recently proposed taxonomy of radiologists' errors, as well as research findings, in an attempt to elucidate possible underlying causes of these errors. The authors also propose strategies for error reduction in radiology. On the basis of current understanding, specific suggestions are offered as to how radiologists can improve their performance in practice.

Magnitude of Impact, Overall and on Subspecialties, of Transitioning in Radiology from ICD-9 to ICD-10 Codes.

PURPOSE: Converting the nation's International Classification of Diseases (ICD) diagnosis coding system, from 14,025 ICD-9 to 69,823 ICD-10 codes, is projected to have enormous financial and operational implications. We aimed to assess the magnitude of impact that this code conversion will have on radiology claims. METHODS: The most frequently billed ICD-9 diagnosis codes for 588,523 radiology claims from five hospitals and affiliated outpatient sites during a 12-month period were mapped to matching ICD-10 codes using a Medicare-endorsed tool. The code-conversion impact factor was calculated for the entire radiology system, and each individual subspecialty division. RESULTS: Of all ICD-9 codes, only 3,407 (24.3%) were used to report any primary diagnosis. Of all claims, 50% were billed using just 37 (0.3%) primary codes; 75% with 131 (0.5%), and 90% with 348 (2.5%). Those 348 ICD-9 codes mapped onto 2,048 ICD-10 codes (5.9-fold impact), representing just 2.9% of all ICD-10 codes. By subspecialty, the conversion impact factor varied greatly, from 1.1 for breast (11 ICD-9 to 12 ICD-10 codes) to 28.8 for musculoskeletal imaging (146 to 4,199). The community division, reflecting a general practice mix, saw a conversion impact factor of 5.8 (254 to 1,471). CONCLUSIONS: Fewer than 3% of all ICD-9 and ICD-10 codes are used to report an overwhelming majority of all radiology claims. Although the number of commonly used codes will expand 5.9-fold overall, musculoskeletal imaging will experience a projected 28.8-fold explosion. Radiology practices should target their ICD educational and operational conversion efforts in an evidence-based manner.

Integrating ontologies of rare diseases and radiological diagnosis.

PURPOSE: The author sought to integrate an ontology of rare diseases with a large ontological model of radiological diagnosis. MATERIALS AND METHODS: The Orphanet Rare Disease Ontology (ORDO) comprised 6794 rare diseases. The Radiology Gamuts Ontology (RGO) incorporated 16 197 terms and 53,425 causal relations linking disorders to imaging manifestations. Semi-automated string-matching was used to match ORDO terms to RGO terms. RESULTS: Of 6794 ORDO terms, 1587 (23.3%) were matched to RGO terms. An additional 700 ORDO terms whose names were hyphenated lists of phenotypic features were added to RGO with causal links from the disease name to the various features. Matched terms were more likely to have higher disease prevalence. CONCLUSIONS: Integrating these ontologies expanded the set of terms and scope of knowledge available for radiological differential diagnosis, and can support translational rare-disease research by linking knowledge of genetics and imaging phenotypes.

Automated classification of radiology reports to facilitate retrospective study in radiology.

Retrospective research is an import tool in radiology. Identifying imaging examinations appropriate for a given research question from the unstructured radiology reports is extremely useful, but labor-intensive. Using the machine learning text-mining methods implemented in LingPipe [1], we evaluated the performance of the dynamic language model (DLM) and the Naïve Bayesian (NB) classifiers in classifying radiology reports to facilitate identification of radiological examinations for research projects. The training dataset consisted of 14,325 sentences from 11,432 radiology reports randomly selected from a database of 5,104,594 reports in all disciplines of radiology. The training sentences were categorized manually into six categories (Positive, Differential, Post Treatment, Negative, Normal, and History). A 10-fold cross-validation [2] was used to evaluate the performance of the models, which were tested in classification of radiology reports for cases of sellar or suprasellar masses and colloid cysts. The average accuracies for the DLM and NB classifiers were 88.5% with 95% confidence interval (CI) of 1.9% and 85.9% with 95% CI of 2.0%, respectively. The DLM performed slightly better and was used to classify 1,397 radiology reports containing the keywords "sellar or suprasellar mass", or "colloid cyst". The DLM model produced an accuracy of 88.2% with 95% CI of 2.1% for 959 reports that contain "sellar or suprasellar mass" and an accuracy of 86.3% with 95% CI of 2.5% for 437 reports of "colloid cyst". We conclude that automated classification of radiology reports using machine learning techniques can effectively facilitate the identification of cases suitable for retrospective research.

Assessing the performance of LOINC® and RadLex for coverage of CT scans across three sites in a health information exchange.

We evaluated the performance of LOINC® and RadLex standard terminologies for covering CT test names from three sites in a health information exchange (HIE) with the eventual goal of building an HIE-based clinical decision support system to alert providers of prior duplicate CTs. Given the goal, the most important parameter to assess was coverage for high frequency exams that were most likely to be repeated. We showed that both LOINC® and RadLex provided sufficient coverage for our use case through calculations of (a) high coverage of 90% and 94%, respectively for the subset of CTs accounting for 99% of exams performed and (b) high concept token coverage (total percentage of exams performed that map to terminologies) of 92% and 95%, respectively. With trends toward greater interoperability, this work may provide a framework for those wishing to map radiology site codes to a standard nomenclature for purposes of tracking resource utilization.

Reliability of radiologic classification for cuff tear arthropathy.

BACKGROUND: Several classification schemes have been proposed for cuff tear arthropathy and used for scientific and clinical purposes, even though their reliability has not been established and compared as of yet. MATERIALS AND METHODS: Two observers (O1 and O2) twice independently classified 52 shoulder radiographs into the cuff arthropathy schemes of Favard, Visotsky-Seebauer, Hamada, and Sirveaux. The schemes of Samilson and Prieto as well as Kellgren and Lawrence, commonly used for osteoarthritis of the shoulder, were also used for comparison. Reliability was tested with the κ coefficient. RESULTS: The intraobserver and interobserver reliabilities were 0.812 for O1, 0.710 for O2, and 0.305 for O1 versus O2 for the Favard classification; 0.868, 0.583, and 0.551, respectively, for the Visotsky-Seebauer classification; 1.000, 0.491, and 0.407, respectively, for the Hamada classification; and 0.852, 0.602, and 0.598, respectively, for the Sirveaux classification. For comparison, the Samilson-Prieto classification reached 0.815, 0.710, and 0.507, respectively, and the Kellgren-Lawrence scheme reached 0.815, 0.713, and 0.430, respectively. DISCUSSION: Of the classification schemes tested, the Sirveaux classification displayed the best reliability overall. The Sirveaux classification only respects alterations of the glenoid, however. Among the schemes respecting both the glenoid and the humerus, the Hamada and Visotsky-Seebauer schemes showed similar reliability compared with the Samilson-Prieto and Kellgren-Lawrence systems, whereas the Favard classification was not as reliable. We therefore recommend the Visotsky-Seebauer or Hamada classification scheme.

Radiological and clinical evaluation of hemophilic arthropathy in Egyptian patients

Background: In hemophilic patients, recurrent hemorrhages in the same joint lead to significant hypertrophic synovitis followed by progressive cartilage degradation. Gross arthritic alterations have been evaluated by clinical scoring and plain radiography scores. At present, magnetic resonance imaging (MRI) seems to be the most accurate radiological technique in joint assessment of the articular and periarticular structures. Aim: To assess arthritic changes clinically and radiologically by plain radiography and MRI and correlate the 3 scoring systemsas well as to correlate these findings with the number of joint bleeds. Patients and methods: The study was conducted on 20 patients with Hemophilia A and B and one patient with type 3 von Willebrand disease. Twenty-six joints were assessed clinically by the orthopedic score and the radiologically by Arnold Hilgartner score and 17 were assessed by MRI as well using the Denver and the European scores. Results: On the radiological evaluation, the main changes were an enlarged epiphysis and osteoporosis whereas the MRI findings included cysts, erosions, synovial hypertrophy, hemosiderin deposits and effusion. Correlation of the clinicalscore with the x-ray was non significant but that with the Denver MRI score was significant (r= 0.6, p= 0.02) as well as that of the plain x-ray and Denver score (r= 0.6, p= 0.007). The number of joint bleeds per year correlated significantly with plain x-ray and MRI scores (r= 0.5, p= 0.01*; r= 0.5, p= 0.02and r= 0.6, p= 0.02*) respectively but not with the clinical score. Conclusion: The available clinical and radiological scoring detects the more advanced changes in hemophilic children. However, MRI is a sensitive diagnostic tool in documenting early changes especially in those with no obvious clinical signs; therefore it plays a role for the selection of patients on demand or prophylactic treatment (AU)