Radiology reports: assessment of a 5,000-word speech recognizer

A prototype 5,000-word recognizer for the generation of radiologic reports by voice entry was evaluated. The system had a capacity sufficient enough to include all radiologic examinations and all desired words in one lexicon. The lack of such a capacity had been identified as a major limitation of a 1,000-word system previously evaluated. Overall reliability in word recognition was 98%. The device may be widely applicable for use in any radiology practice.     

Academic radiology and the emergency department: does it need changing?

RATIONAL AND OBJECTIVES: The increasing importance of imaging for both diagnosis and management in patient care has resulted in a demand for radiology services 7 days a week, 24 hours a day, especially in the emergency department (ED). We hypothesized the resident preliminary reports were better than generalist radiology interpretations, although inferior to subspecialty interpretations. MATERIALS AND METHODS: Total radiology volume through our Level I pediatric and adult academic trauma ED was obtained from the radiology information system. We conducted a literature search for error and discordant rates between radiologists of varying experience. For a 2-week prospective period, all preliminary reports generated by the residents and final interpretations were collected. Significant changes in the report were tabulated. RESULTS: The ED requested 72,886 imaging studies in 2004 (16% of the total radiology department volume). In a 2-week period, 12 of 1929 (0.6%) preliminary reports by residents were discordant to the final subspecialty dictation. In the 15 peer-reviewed publications documenting error rates in radiology, the error rate between American Board of Radiology (ABR)-certified radiologists is greater than that between residents and subspecialists in the literature and in our study. However, the perceived error rate by clinicians outside radiology is significantly higher. CONCLUSION: Sixteen percent of the volume of imaging studies comes through the ED. The residents handle off-hours cases with a radiology-detected error rate below the error rate between ABR-certified radiologists. To decrease the perceived clinician-identified error rate, we need to change how academic radiology handles ED cases.     

Emergency radiology fellowship training in the USA: a web-based survey of academic programs

Interest in emergency radiology as a distinct subspecialty within radiology continues to rise in the USA and globally. While acute care imaging has been performed since the earliest days of the specialty, fellowship training in emergency radiology is a relatively new phenomenon. The purpose of this study was to examine the current status of emergency radiology training in the USA, using data derived from the official websites of US residency training programs. The most current list of radiology residency programs participating in the 2017 match was obtained from the official Electronic Residency Application Service (ERAS) website. The total number of emergency radiology fellowships was recorded after visiting available websites of each academic radiology program. The total number of subspecialty fellowships offered by each academic radiology program was also recorded. There were 12 confirmed emergency radiology fellowships offered in the USA for a combined total of 22 fellowship positions. Eleven programs were 1 year in duration, with one program offering a one- or two-year option. One hundred eight of the 174 (approximately 62 %) surveyed academic radiology programs offered at least one subspecialty fellowship. Emergency radiology fellowships are on the rise, paralleling the growth of emergency radiology as a distinct subspecialty within radiology.     

A new database system for radiological reports

We have designed and developed a new database system to facilitate automatic feedback of the content of radiology reports to radiologists. The prototype of this database system has been implemented in the RGSS-IDJ, a developmental computer system that applies artificial intelligence methods to a reporting system. This prototype system was constructed to test the feasibility of overcoming the limitations of conventional database systems. The new database system is based on our semantic model for radiology reports and is able to treat data with unnormalized relations. Operations specific to our database system include the ability to acquire information about a set of reports that contains any semantic expression included in the lexicon and the ability to obtain the expressions that belong to a set of several semantic expressions in the reports. Thus, our new database system will offer a more powerful tool for analyzing the content of reports than conventional database systems.     

Integration of a Community Radiology Division into a Subspecialty-Focused Academic Radiology Department

IntroductionAssimilate a general radiology division into a subspecialty-focused radiology department at an academic medical center.MethodsThis Institutional Review Board-approved quality improvement initiative was performed at an academic medical centers’ subspecialty-focused academic radiology department, aiming to assimilate a general radiology division providing interpretive services for a distributed set of community ambulatory practices. An Oversight Committee charged by the department chair created a charter with unambiguous goal, timelines, clear decision-making, and conflict resolution processes. The Committee assessed the resources and clinical capabilities of the general radiologists, and the anticipated shift in exam volume from the community into subspecialty divisions. Primary outcome, percentage of targeted organ systems-specific interpretations by general radiologists based on assigned subspecialty division, and secondary outcome of report turnaround time (TAT) for all ambulatory exams, were compared before and after sub-specialization.ResultsAmong 10 general radiologists, 4.5 were assigned to subspecialty divisions; 5.5 continued to cover an independent general radiology practice in a for-profit delivery network. In the 5 months’ post-transition, a total 86.6% (11,668/13,477) of reports by the integrated general radiologists were within designated subspecialty divisions vs 23.9% (2,586/10,829) pre-transition (P < 0.01). There was no change in ambulatory radiology report TAT for non-urgent care center (UCC) or UCC exams pre- vs post-integration.DiscussionA quality improvement initiative with unambiguous decision-making and conflict resolution processes incorporated a general radiology practice (radiologists and exams) into a subspecialty-focused academic radiology practice without negatively impacting TAT metrics. Future studies would be needed to assess impact on quality of interpretations.     

Discordance rates between preliminary and final radiology reports on cross-sectional imaging studies at a level 1 trauma center

RATIONALE AND OBJECTIVES: The goal was to determine discordance rates between preliminary radiology reports provided by on-call radiology house staff and final reports from attending radiologists on cross-sectional imaging studies requested by emergency department staff after hours. MATERIALS AND METHODS: A triplicate carbon copy reporting form was developed to provide permanent records of preliminary radiology reports and to facilitate communication of discrepant results to the emergency department. Data were collected over 21 weeks to determine the number of discordant readings. Patients' medical records were reviewed to show whether discrepancies were significant or insignificant and to assess their impact on subsequent management and patient outcome. RESULTS: The emergency department requested 2830 cross-sectional imaging studies after hours and 2311 (82%) had a copy of the triplicate form stored in radiology archives. Discrepancies between the preliminary and final report were recorded in 47 (2.0%), with 37 (1.6%) considered significant: 14 patients needed no change, 13 needed a minor change, and 10 needed a major change in subsequent management. Ten (0.43%) of the discordant scans were considered insignificant. A random sample of 104 (20%) of the 519 scans without a paper triplicate form was examined. Seventy-one (68%) did have a scanned copy of the triplicate form in the electronic record, with a discrepancy recorded in 3 (4.2%), which was not statistically different from the main cohort (P = .18). CONCLUSION: Our study suggests a high level of concordance between preliminary reports from on-call radiology house staff and final reports by attending subspecialty radiologists on cross-sectional imaging studies requested by the emergency department.     

Is terminology used effectively to convey diagnostic certainty in radiology reports?

RATIONALE AND OBJECTIVES: This study was performed to assess the extent of agreement among radiologists and nonradiologists in perception of diagnostic certainty conveyed by words and phrases commonly used in radiology reports. MATERIALS AND METHODS: The study was performed in a large academic radiology department. To determine the commonly used terminology for conveying diagnostic certainty in radiology reports, 12 randomly selected radiologists from six different subspecialties were interviewed. The authors identified the 15 most commonly used words and phrases and included these in random order in a questionnaire sent to all staff radiologists (n = 45) and to 158 referring physicians. Physicians were asked to rank the 15 phrases in order of the diagnostic certainty conveyed by each, from 1 (most certain) to 15 (least certain), using each number only once. The kappa statistic was used to assess agreement in rank order among physicians. RESULTS: The questionnaire response rate was 76% (n = 34) for radiologists and 49% (n = 78) for nonradiologists. There was excellent agreement among radiologists (kappa = 0.95) and nonradiologists (kappa = 0.93) in the rank order for the phrase diagnostic of. Although there was good agreement (kappa = 0.45) among radiologists for the word unlikely, agreement among nonradiologists was poor (kappa = 0.27). There was very poor agreement among all physicians for the rank order of the other 13 phrases. CONCLUSION: Among radiologists and nonradiologists, concordance was poor regarding the diagnostic certainty associated with phrases commonly used in radiology reports. Because poor agreement could lead to suboptimal quality of care, the standardization of terminology would benefit all parties.     

National Survey to Identify Subspecialties at Risk for Physician Shortages in Canadian Academic Radiology Departments

Purpose

To identify subspecialty fields in Canadian academic radiology departments that are at risk for future manpower shortages. To determine reasons for the potential shortages and suggest potential solutions.

Methods

An anonymous online survey was sent by e-mail to radiology residents and academic radiology department heads in Canada. The survey was open from April 1 to August 1, 2006. Statistical analysis by using the SAS Frequency Procedure was performed on the results.

Results

Interventional radiology, neuroradiology, mammography, cardiac imaging, and pediatric radiology were identified as areas in which there will be increasing workforce demands. Mammography, pediatric radiology, and cardiac imaging were identified as areas in which there will be a potential decrease in supply. Of the residents, 65.83% intended on pursuing subspecialty training. Priorities were interesting work, job availability, and work schedule. Nuclear medicine, mammography, pediatric radiology, and interventional radiology were identified as the top 4 areas in which residents specifically did not want to pursue further subspecialty training. Only 15% of resident respondents received career counseling during residency, and only 50% of those residents thought it was adequate.

Conclusions

Our survey results indicate that mammography, cardiac imaging, and pediatric radiology are at risk for manpower shortages, and interventional radiology may be at risk. Increased efforts to recruit trainees may be necessary to ensure that these subspecialties maintain their presence in the future. Only 15% of the surveyed residents received career counseling during residency. This is a relatively untapped forum that academic staff could use to help recruit new trainees into these underserved subspecialties.     

The current position of cardiac radiology in the United Kingdom

A questionnaire was sent to 39 hospitals, in the United Kingdom, 38 with a cardiosurgical unit and one with a cardiac radiology department. The object was to ascertain the commitment of consultant radiologists to cardiovascular radiology and cardiac radiology in particular and to evaluate training given to non-consultant radiologists in this subspecialty. Thirty-five (90%) departments responded, 33 of which had a cardiac radiology consultant. All but three of the 63 consultant cardiac radiologists report cine angiography. Of the 63, 26 perform one additional imaging technique and 21 perform two or more additional imaging techniques. The remaining 16 consultants only report on cine angiography. Only nine of 21 departments in which some form of cardiac radiology training was given, had a rotation through the subspecialty at registrar or senior registrar level. Twenty-one departments thought that an additional post in cardiac radiology would be sought if trained people were available.     

Genitourinary imaging: the past 40 years

During the past 40 years, there has been a dramatic evolution in genitourinary imaging. This evolution has resulted in fundamental changes in the subspecialty. Uroradiology initially focused on radiographic imaging of the urinary tract and was practiced primarily by urologists. After the development of safe intravenous contrast materials, radiologists who focused on the urinary tract and worked closely with urologists forged major advances in urinary tract imaging and intervention. More recently, imaging of the extraurinary genital organs has been added to the subspecialty. Cross-sectional imaging techniques have supplanted radiographic imaging for both urinary and genital imaging. The emergence of the cross-sectional techniques, however, has blurred the traditional organ system-based distinction between gastrointestinal radiology and genitourinary radiology, as both organ systems are imaged simultaneously, and has resulted in a new amalgamation, abdominal radiology, with roots in both specialties. The challenge for the new generation of abdominal radiologists, trained predominantly in cross-sectional techniques, will be to maintain the close interaction with our clinical colleagues that the traditional organ system orientation fostered.     

Radioembolization with 90Yttrium microspheres: a state-of-the-art brachytherapy treatment for primary and secondary liver malignancies. Part 1: Technical and methodologic considerations

Microsphere and particle technology represent the next-generation agents that have formed the basis of interventional oncology, an evolving subspecialty of interventional radiology. One of these platforms, yttrium-90 microspheres, is rapidly being adopted in the medical community as an adjunctive therapeutic tool in the management of primary and secondary liver malignancies. Given the complexity of the treatment algorithm of patients who may be candidates for this therapy and the need for clinical guidance, a comprehensive review of the methodologic and technical considerations was undertaken. This experience is based on more than 900 (90)Y infusions performed over a 5-year period.     

Characteristics and Trends of Radiology Research: A Survey of Original Articles Published in AJR and Radiology between 2001 and 2010

Purpose: To determine the characteristics and trends of the original articles published in two major American radiology journals, AJR American Journal of Roentgenology (AJR) and Radiology, between 2001 and 2010. Materials and Methods: This was a retrospective bibliometric analysis that did not involve human subjects and was exempt from institutional review board approval. All 6542 original articles published in AJR and Radiology between 2001 and 2010 were evaluated. The following information was abstracted from each article: radiologic subspecialty, radiologic technique used, type of research, sample size, study design, statistical analysis, study outcome, declared funding, number of authors, affiliation of the first author, and country of the first author. In addition, all the variables examined were presented along with the trend over time. Results: The most common subspecialty of study was abdominal (1219 of 6542, 18.6%), followed by vascular/interventional (804 of 6542, 12.3%). A total of 3744 (57.2%) original articles used magnetic resonance (MR) imaging or computed tomography (CT), 5495 (84.1%) were clinical research articles, 3060 (46.8%) had sample size of more than 50, 4087 (62.5%) were retrospective, 4714 (72.1%) performed statistical analysis, 6225 (95.2%) showed positive study outcome, 4784 (73.1%) were not funded, 3942 (60.3%) had four to seven authors, and 5731 (87.6%) were written by the primary author who was from a department of radiology or radiology-related specialties. The United States published 45.5% (2975 of 6542) of the articles, followed by Japan (n = 525, 8.0%), Germany (n = 485, 7.4%), and South Korea (n = 455, 7.0%). In the time trend analysis, the following variables showed a significantly positive trend: cardiac subspecialty, CT and MR imaging as the radiologic techniques, type of research as other (nonbasic, nonclinical), sample size of more than 50, four to seven as the number of authors, medicine-related department of the first author, and South Korea and Italy as countries of the first author. On the other hand, pediatric subspecialty, combined (basic and clinical) type of research, and number of authors fewer than four showed a significantly negative trend. Conclusion: The bibliometric analysis of the AJR and Radiology journals with articles published between 2001 and 2010 revealed characteristics and trends of the current radiology research that may provide useful information to researchers and editorial staff in radiology. ? RSNA, 2012.     

From shared data to sharing workflow: Merging PACS and teleradiology

Due to a host of technological, interface, operational and workflow limitations, teleradiology and PACS/RIS were historically developed as separate systems serving different purposes. PACS/RIS handled local radiology storage and workflow management while teleradiology addressed remote access to images. Today advanced PACS/RIS support complete site radiology workflow for attending physicians, whether on-site or remote. In parallel, teleradiology has emerged into a service of providing remote, off-hours, coverage for emergency radiology and to a lesser extent subspecialty reading to subscribing sites and radiology groups.When attending radiologists use teleradiology for remote access to a site, they may share all relevant patient data and participate in the site's workflow like their on-site peers. The operation gets cumbersome and time consuming when these radiologists serve multi-sites, each requiring a different remote access, or when the sites do not employ the same PACS/RIS/Reporting Systems and do not share the same ownership. The least efficient operation is of teleradiology companies engaged in reading for multiple facilities. As these services typically employ non-local radiologists, they are allowed to share some of the available patient data necessary to provide an emergency report but, by enlarge, they do not share the workflow of the sites they serve.Radiology stakeholders usually prefer to have their own radiologists perform all radiology tasks including interpretation of off-hour examinations. It is possible with current technology to create a system that combines the benefits of local radiology services to multiple sites with the advantages offered by adding subspecialty and off-hours emergency services through teleradiology. Such a system increases efficiency for the radiology groups by enabling all users, regardless of location, to work “local” and fully participate in the workflow of every site. We refer to such a system as SuperPACS.     

Radiologist Variation in the Rates of Follow-up Imaging Recommendations Made for Pulmonary Nodules

ObjectiveDetermine whether differences exist in rates of follow-up recommendations made for pulmonary nodules after accounting for multiple patient and radiologist factors.MethodsThis Institutional Review Board–approved, retrospective study was performed at an urban academic quaternary care hospital. We analyzed 142,001 chest and abdominal CT reports from January 1, 2016, to December 31, 2018, from abdominal, thoracic, and emergency radiology subspecialty divisions. A previously validated natural language processing (NLP) tool identified 24,512 reports documenting pulmonary nodule(s), excluding reports NLP-positive for lung cancer. A second validated NLP tool identified reports with follow-up recommendations specifically for pulmonary nodules. Multivariable logistic regression was used to determine the likelihood of pulmonary nodule follow-up recommendation. Interradiologist variability was quantified within subspecialty divisions.ResultsNLP classified 4,939 of 24,512 (20.1%) reports as having a follow-up recommendation for pulmonary nodule. Male patients comprised 45.3% (11,097) of the patient cohort; average patient age was 61.4 years (±14.1 years). The majority of reports were from outpatient studies (62.7%, 15,376 of 24,512), were chest CTs (75.9%, 18,615 of 24,512), and were interpreted by thoracic radiologists (63.7%, 15,614 of 24,512). In multivariable analysis, studies for male patients (odds ratio [OR]: 0.9 [0.8-0.9]) and abdominal CTs (OR: 0.6 [0.6-0.7] compared with chest CT) were less likely to have a pulmonary nodule follow-up recommendation. Older patients had higher rates of follow-up recommendation (OR: 1.01 for each additional year). Division-level analysis showed up to 4.3-fold difference between radiologists in the probability of making a follow-up recommendation for a pulmonary nodule.DiscussionSignificant differences exist in the probability of making a follow-up recommendation for pulmonary nodules among radiologists within the same subspecialty division.     

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

PurposeConverting 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.MethodsThe 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.ResultsOf 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).ConclusionsFewer 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.     

Improving the quality of care through routine teleradiology consultation

RATIONALE AND OBJECTIVES: The hypotheses of this study were as follows: (a) University subspecialty radiologists can provide consultations effectively to general radiologists as part of routine clinical operations; (b) these consultations will improve the quality of the final radiologic report; and (c) the consultations will improve the care process and may save money, as well. MATERIALS AND METHODS: For 2,012 consecutive computed tomographic or magnetic resonance (MR) imaging studies, the initial interpretations provided by radiology generalists were subsequently reviewed by specialists, with a final consensus report available. "Truth" was established by final consensus reports. To control for potential bias, 150 adult MR imaging and 250 pediatric radiologic studies were interpreted initially by specialists and then by generalists. Again, truth was established by final consensus reports. RESULTS: There was disagreement between generalist and specialist radiologist interpretations in 427 (21.2%) of the cases reviewed. These disagreements were stratified further by independent specialists, who graded them as important, very important, or unimportant. Differences were considered important or very important in 99% of the cases reviewed. CONCLUSION: Consultations by subspecialty radiologists improved the quality of the radiology reports studied and, at least in some cases, improved the process of care by eliminating unnecessary procedures or suggesting more specific follow-up examinations. The consultation services can be provided cost-effectively from the payer's perspective and may save additional costs when unnecessary procedures can be eliminated.     

Automatic voice recognition for radiologic reports. Experiment with a prototype in an operational environment

Large vocabulary speech recognition, its techniques and its software and hardware technology, are being developed, aimed at providing the office user with a tool that could significantly improve both quantity and quality of his work: the dictation machine, which allows memos and documents to be input using voice and a microphone instead of fingers and a keyboard. The IBM Rome Science Center, together with the IBM Research Division, has built a prototype recognizer that accepts sentences in natural language from a 20,000-word Italian vocabulary. The unit runs on a personal computer equipped with a special hardware capable of giving all the necessary computing power. The first laboratory experiments yielded very interesting results and pointed out such system characteristics to make its use possible in operational environments. To this purpose, the dictation of medical reports was considered as a suitable application. In cooperation with the 2nd Radiology Department of S. Maria della Misericordia Hospital (Udine, Italy), a system was experimented by radiology department doctors during their everyday work. The doctors were able to directly dictate their reports to the unit. The text appeared immediately on the screen, and eventual errors could be corrected either by voice or by using the keyboard. At the end of report dictation, the doctors could both print and archive the text. The report could also be forwarded to hospital information system, when the latter was available. Our results have been very encouraging: the system proved to be robust, simple to use, and accurate (over 95% average recognition rate). The experiment was precious for suggestions and comments, and its results are useful for system evolution towards improved system management and efficiency.     

Do clinicians read our reports? Integrating the radiology information system with the electronic patient record: experiences from the first 2 years

This study aimed to determine how clinicians adapted to and utilized new routines for accessing radiology reports after the integration of an electronic patient record (EPR) with a radiology information system (RIS). Activity-related data describing the availability and receipt of radiology reports were collected from the EPR and the RIS over a period of 2 years. Twelve percent of the final radiology reports had not been opened 4 weeks after they had been entered into the EPR. For opened reports, the median time after a report was available in the EPR until it was first opened by a clinician was less than 1 h for preliminary reports and less than 4 h for final radiology reports. The use of radiology reports was stable during the second observation year. Some reports were not opened for professional as well as technical reasons. The integrated information systems offered a potential for improving routines related to the transmission of radiology reports. Clinicians did not fully take advantage of this potential in the 2 years after its introduction.