Diagnostic Radiology Resident and Fellow Workloads: A 12-Year Longitudinal Trend Analysis Using National Medicare Aggregate Claims Data

Dedicated software to harmonize the follow-up of oncological patients

Objective

To test and evaluate a sofware dedicated to the follow-up of oncological CT scans for potential use in the Radiology department.

Materials and methods

In this retrospective study, 37 oncological patients with baseline and follow-up CT scans were reinterpreted using a dedicated software. Baseline CT scans were chosen from the imaging reports available in our PACS (picture archiving and communicatin systems). Follow-up interpretations were independently assessed with the software. We evaluated the target lesion sums and the tumor response based on RECIST 1.1 (Response Evaluation Criteria in Solid Tumors).

Results

There was no significant difference in the target lesion sums and the tumor response assessments between the PACS data and the imaging software. There was no over or underestimation of the disease with the software. There was a sigificant deviation (progression versus stability) in three cases. For two patients, this difference was related to the evaluation of the response of non-target lesions. The difference in the third patient was due to comparison with a previous CT scan than to the baseline exam. There was a miscalculation in 13 % of the reports and in 28 % of the cases the examination was compared to the previous CT scan. Finally, the tumor response was not detailed in 43 % of the follow-up reports.

Conclusion

The use of dedicated oncology monitoring software could help in reducing intepretation time and in limiting human errors.

Coronal Diffusion-Weighted Imaging Does Not Improve Detection of Posterior Fossa Infarcts Compared With Conventional Axial Diffusion-Weighted Imaging

PURPOSE

Recent publications have suggested incorporating coronal diffusion-weighted imaging (DWI) sequences and axial DWI sequences to enhance the detection of posterior fossa infarcts (PFIs). This study evaluated the utility of coronal DWIs compared with axial DWIs for assessing PFIs in the emergency department (ED).

METHODS

A retrospective, institutional review board-approved study was conducted at a level I stroke center, including 118 patients who presented to the ED between 2016 and 2023 with suspected PFI. Inclusion criteria involved patients who underwent emergent 1.5 T magnetic resonance imaging (MRI) and had axial and coronal DWI sequences. Two neuroradiologists independently evaluated the DWI sequences for PFI detection in 2 rounds, with a 4-week interval between rounds. The neuroradiologists assessed the quality of axial and coronal DWIs using a 5-point Likert scale. Descriptive statistics, interrater reliability, and marginal homogeneity tests were performed.

RESULTS

Among the 118 MRI scans, 23 (19%) showed PFI on axial and coronal DWI sequences. All 23 cases were identified on axial DWI, whereas 8 cases of PFI (35%) were not detected on coronal DWI ( P value = 0.013). No PFIs were observed on coronal DWI that was not identified on axial DWI. The quality scores for both raters were significantly higher for axial DWIs than coronal DWIs ( P value <0.00001).

CONCLUSION

Despite recent recommendations advocating for the inclusion of coronal DWI in PFI detection, this study's findings indicate no improvement in PFI detection or image quality using coronal DWI. Further research is necessary to validate these results and explore the potential benefits of incorporating coronal DWI in assessing posterior fossa strokes.

Artificial Intelligence in Lung Cancer Screening: The Future Is Now

Lung cancer has one of the worst morbidity and fatality rates of any malignant tumour. Most lung cancers are discovered in the middle and late stages of the disease, when treatment choices are limited, and patients' survival rate is low. The aim of lung cancer screening is the identification of lung malignancies in the early stage of the disease, when more options for effective treatments are available, to improve the patients' outcomes. The desire to improve the efficacy and efficiency of clinical care continues to drive multiple innovations into practice for better patient management, and in this context, artificial intelligence (AI) plays a key role. AI may have a role in each process of the lung cancer screening workflow. First, in the acquisition of low-dose computed tomography for screening programs, AI-based reconstruction allows a further dose reduction, while still maintaining an optimal image quality. AI can help the personalization of screening programs through risk stratification based on the collection and analysis of a huge amount of imaging and clinical data. A computer-aided detection (CAD) system provides automatic detection of potential lung nodules with high sensitivity, working as a concurrent or second reader and reducing the time needed for image interpretation. Once a nodule has been detected, it should be characterized as benign or malignant. Two AI-based approaches are available to perform this task: the first one is represented by automatic segmentation with a consequent assessment of the lesion size, volume, and densitometric features; the second consists of segmentation first, followed by radiomic features extraction to characterize the whole abnormalities providing the so-called "virtual biopsy". This narrative review aims to provide an overview of all possible AI applications in lung cancer screening.

Diagnostic captioning: a survey

Diagnostic captioning (DC) concerns the automatic generation of a diagnostic text from a set of medical images of a patient collected during an examination. DC can assist inexperienced physicians, reducing clinical errors. It can also help experienced physicians produce diagnostic reports faster. Following the advances of deep learning, especially in generic image captioning, DC has recently attracted more attention, leading to several systems and datasets. This article is an extensive overview of DC. It presents relevant datasets, evaluation measures, and up-to-date systems. It also highlights shortcomings that hinder DC’s progress and proposes future directions.

Evolving Radiology Trainee Neuroimaging Workloads: A National Medicare Claims-based Analysis

RATIONALE AND OBJECTIVES

While radiology training programs aim to prepare trainees for clinical practice, the relationship between trainee, and national radiology workforce demands is unclear. This study assesses changing radiology trainee neuroimaging workloads nationwide for neuroimaging studies.

MATERIALS AND METHODS

Using aggregate Medicare claims files from 2002 to 2018, we identified all computed tomography (CT) and magnetic resonance (MR) examinations of the brain, head and neck, and spine (hereafter "neuroimaging") in Medicare fee-for-service beneficiaries nationwide. Using separate Medicare files, we calculated population utilization rates, and work relative value unit (wRVU) weights of all diagnostic neuroradiology services. Using claims modifiers, we identified services rendered by radiology trainees. Using separate national trainee enrollment files, we calculated mean annual per trainee wRVUs.

RESULTS

Between 2002 and 2018, total Medicare neuroimaging claims increased for both radiologists overall (86.1%) and trainees (162.5%), including increases in both CT (102.9% vs 196.8%), and MR (59.9% vs 106.6%). The national percentage of all radiologist neuroimaging wRVUs rendered by trainees increased 46.1% (3.8% of all wRVUs nationally in 2002 to 5.6% in 2018). National trainee increases were present across all neuroimaging services but greatest for head and neck CT (+86.5%). Mean annual per radiology trainee neuroimaging Medicare wRVUs increased +174.9% (42.1 per trainee in 2002 to 115.70 in 2018). Mean per trainee wRVU increases were greatest for spine CT (+394.2%) but present across all neuroimaging services.

CONCLUSION

As neuroimaging utilization in Medicare beneficiaries has grown, radiology trainee neuroimaging workloads have increased disproportionately.

Automated Color-Coding of Lesion Changes in Contrast-Enhanced 3D T1-Weighted Sequences for MRI Follow-up of Brain Metastases

BACKGROUND AND PURPOSE

MR imaging is the technique of choice for follow-up of patients with brain metastases, yet the radiologic assessment is often tedious and error-prone, especially in examinations with multiple metastases or subtle changes. This study aimed to determine whether using automated color-coding improves the radiologic assessment of brain metastases compared with conventional reading.

MATERIALS AND METHODS

One hundred twenty-one pairs of follow-up examinations of patients with brain metastases were assessed. Two radiologists determined the presence of progression, regression, mixed changes, or stable disease between the follow-up examinations and indicated subjective diagnostic certainty regarding their decisions in a conventional reading and a second reading using automated color-coding after an interval of 8 weeks.

RESULTS

The rate of correctly classified diagnoses was higher (91.3%, 221/242, versus 74.0%, 179/242, P < .01) when using automated color-coding, and the median Likert score for diagnostic certainty improved from 2 (interquartile range, 2-3) to 4 (interquartile range, 3-5) (P < .05) compared with the conventional reading. Interrater agreement was excellent (κ = 0.80; 95% CI, 0.71-0.89) with automated color-coding compared with a moderate agreement (κ = 0.46; 95% CI, 0.34-0.58) with the conventional reading approach. When considering the time required for image preprocessing, the overall average time for reading an examination was longer in the automated color-coding approach (91.5 [SD, 23.1] seconds versus 79.4 [SD, 34.7 ] seconds, P < .001).

CONCLUSIONS

Compared with the conventional reading, automated color-coding of lesion changes in follow-up examinations of patients with brain metastases significantly increased the rate of correct diagnoses and resulted in higher diagnostic certainty.

Panoramic Dental Reconstruction for Faster Detection of Dental Pathology on Medical Non-dental CT Scans: a Proof of Concept from CT Neck Soft Tissue

Even though teeth are often included in the field of view for a variety of medical CT studies, dental pathology is often missed by radiologists. Given the myriad morbidity and occasional mortality associated with sequelae of dental pathology, an important goal is to decrease these false negatives. However, given the ever-increasing volume of cases studies that radiologists have to read and the number of structures and diseases they have to evaluate, it is important not to place undue time restraints on the radiologist to this end. We hypothesized that generating panoramic dental radiographs from non-dental CT scans can permit identification of key diseases, while not adding much time to interpretation. The key advantage of panoramic dental radiographs is that they display the plane of the teeth in two dimensions, thereby facilitating fast and accurate assessment. We found that interpreting panoramic radiographic reconstructions compared to the full CT volumes reduced time-to-diagnosis of key dental pathology on average by roughly a factor of four. This expedition was statistically significant, and the average time-to-diagnosis for panoramic reconstructions was on the order of seconds, without a loss in accuracy compared to full CT. As such, we posit that panoramic reconstruction can serve as a one-slice additional series in any CT image stack that includes the teeth in its field of view.

Personalising lung cancer screening: An overview of risk-stratification opportunities and challenges

Randomised clinical trials have shown the efficacy of computed tomography lung cancer screening, initiating discussions on whether and how to implement population‐based screening programs. Due to smoking behaviour being the primary risk‐factor for lung cancer and part of the criteria for determining screening eligibility, lung cancer screening is inherently risk‐based. In fact, the selection of high‐risk individuals has been shown to be essential in implementing lung cancer screening in a cost‐effective manner. Furthermore, studies have shown that further risk‐stratification may improve screening efficiency, allow personalisation of the screening interval and reduce health disparities. However, implementing risk‐based lung cancer screening programs also requires overcoming a number of challenges. There are indications that risk‐based approaches can negatively influence the trade‐off between individual benefits and harms if not applied thoughtfully. Large‐scale implementation of targeted, risk‐based screening programs has been limited thus far. Consequently, questions remain on how to efficiently identify and invite high‐risk individuals from the general population. Finally, while risk‐based approaches may increase screening program efficiency, efficiency should be balanced with the overall impact of the screening program. In this review, we will address the opportunities and challenges in applying risk‐stratification in different aspects of lung cancer screening programs, as well as the balance between screening program efficiency and impact.

Teaching Physician Supervision: Medicare's Ongoing Imperative for Academic Radiologists

OBJECTIVE. Medicare permits radiologists to bill for trainee work but only in narrowly defined circumstances and with considerable consequences for noncompliance. The purpose of this article is to introduce relevant policy rationale and definitions, review payment requirements, outline documentation and operational considerations for diagnostic and interventional radiology services, and offer practical suggestions for academic radiologists striving to optimize regulatory compliance. CONCLUSION. As academic radiology departments advance their missions of service, teaching, and scholarship, most rely on residents and fellows to support expanding clinical demands. Given the risks of technical noncompliance, institutional commitment and ongoing education regarding teaching supervision compliance are warranted.

Developing a Resident-led First-year Radiology Resident Lecture Series

The first year of radiology residency presents many unique challenges, from transitioning into a completely new, specialized field to preparing for call. Implementation of a longitudinal lecture series dedicated towards the clinical demands of being a first-year radiology resident may improve their knowledge and comfort level, as well as benefit the entire program. In this article, we outline our experience with the development of a resident-led dedicated first-year radiology resident lecture series providing targeted, high-yield instruction on rotation logistics, basic physics and artifacts, examination protocolling, and common and "don't miss" pathology.

Relative Prevalence and Characteristics of Malpractice Litigation Involving Radiology Trainees

PURPOSE

To assess the prevalence and characteristics of medical malpractice litigation involving radiology trainees.

METHODS

Using a LexisNexis legal database keyword search, we identified all state and federal lawsuits between 2009 and 2018 yielding formal appellate and lower court opinions (precedent setting "complex litigation") potentially involving physician trainees. Available judicial records were systematically reviewed to identify malpractice matters with material trainee involvement. Cases were categorized by criteria including specialty and location. Incidence rates were calculated for all specialties. Radiology lawsuits were characterized further.

RESULTS

Initial LexisNexis Boolean database search yielded 8,935 potentially relevant cases with 580 confirmed as malpractice materially involving physician trainees. Annual cases trended downward (high 70, low 37). Most originated in New York (195 of 580; 33.6%), Ohio (41; 7.1%), and Pennsylvania (34; 5.9%) and involved surgery (204; 35.2%), obstetrics and gynecology (114; 19.7%), and medicine (105; 18.1%). The case incidence rate for all trainees was 0.63 per 1,000 trainee years. Of 309 cases with known outcomes, defendant physicians prevailed in 238 (77.0%). Radiology trainees represented only 23 cases (4.0%), corresponding to an incidence rate ratio of 0.79 (confidence interval 0.52-1.20). Radiology litigation most frequently involved alleged missed diagnoses (14 of 23; 60.8%) and procedural complications (7; 30.4%). Defendant radiologists prevailed in 9 of the 13 cases with known outcomes (69.2%).

CONCLUSION

Complex medical malpractice litigation involving physician trainees is infrequent and decreasing over time. Lawsuits involving radiology trainees are uncommon, less likely than for many nonradiology trainees, and typically involve alleged missed diagnoses or procedural complications. Defendant radiologists usually prevail.

Radiology workload in clinical implementation of thrombectomy for acute ischemic stroke: experience from The Netherlands

PURPOSE

To investigate the number of acute stroke patients undergoing CT angiography (CTA) for suspected large vessel occlusion (LVO) and those eligible for thrombectomy in relation to the population.

METHODS

Consecutive patients in a Western population who underwent CTA for suspected LVO of the proximal anterior circulation between January and August 2019 were included. The date and time of CTA and the number of patients eligible for thrombectomy were assessed. Our hospital's service area population was estimated using the Central Bureau for Statistics data. One-way analysis of variance with post-hoc tests and chi-squared tests were used for statistical analyses.

RESULTS

Of 520 patients (49% males, mean age of 72 years) undergoing CTA, 84 (16.2%) were eligible for thrombectomy. Our hospital's service area population was estimated at 420,000. Therefore, 3.6 CTA scans were performed and 0.6 patients were eligible for thrombectomy per 100,000 people per week. The number of patients undergoing CTA and the number of patients eligible for thrombectomy both did not significantly differ between any days of the week (P > 0.05). A total of 236 (45%) and 284 patients (55%) underwent CTA during office and on-call hours, respectively. The percentage of patients eligible for thrombectomy did not significantly differ between office and on-call hours (P = 0.834).

CONCLUSION

Our study estimated the number of stroke patients undergoing CTA for suspected LVO and those eligible for thrombectomy in relation to the population. Numbers were essentially the same throughout the week, and during office and on-call hours. Our data can be used to make adequate staffing plans.

Changing National Medicare Utilization of Catheter, Computed Tomography, and Magnetic Resonance Extremity Angiography: A Specialty-focused 16-Year Analysis

To assess changing utilization of extremity angiography from 2001 to 2016, focusing on modalities and provider specialties. Medicare PSPS Master Files from 2001-2016 and POSPUF from 2016 were used to determine overall and specialty utilization of diagnostic catheter angiography (DCA), CT angiography (CTA), and MR angiography (MRA). From 2001 to 2016, extremity angiography increased from 1107 to 1590 extremities imaged per 100,000 beneficiaries, with rapid expansion of CTA (22 in 2001 to 619 in 2009; plateau of 645 in 2016), but declines in DCA (1039 to 914) and MRA (45 to 30). Over time, extremity angiography shifted from 94% DCA, 4% MRA, and 2% CTA to 58% DCA, 41% CTA, and 2% MRA. For radiologists, extremity angiography increased slightly (741 to 767) with increases in CTA (20 to 595) and large decreases in DCA (681 to 145), with MRA remaining low (40 to 27). Extremity angiography increased for cardiologists (197 to 349) and vascular surgeons (87 to 351), both overwhelmingly performing DCA. Radiologists' share of all extremity angiography shifted from 67% to 48%, with interventionalists (47%), generalists (43%), and abdominal radiologists (7.4%) providing most radiologist services in 2016. Throughout, radiologists were the dominant providers of CTA (89% to 92%) and MRA (89% to 90%). Extremity angiography utilization in Medicare beneficiaries increased nearly 50% from 2001 to 2016, largely related to CTA performed by radiologists. Of radiologists, interventionalists and generalists together render most services. Cardiologists and surgeons assumed a large share of DCA previously performed by radiologists.

The Radiology Resident as Teaching Consultant: An Innovative Peer-to-Peer Teaching Consultation Service to Strengthen Relationships With Referring Colleagues in the Era of Imaging 3.0

BACKGROUND

The American College of Radiology Imaging 3.0 paradigm emphasizes the need for radiologists to serve as imaging consultants to their referring colleagues. However, outside the reading room, teaching interactions between radiology and nonradiology residents are limited. Internal Medicine Morning Report (IMMR) is a resident-run educational program widely employed by internal medicine (IM) residencies. Although medical imaging is regularly discussed in IMMR, radiology residents are not typically involved in case preparation. We aimed to develop a peer-to-peer imaging teaching consultation service (TCS) incorporated into the well-established structure of IMMR. By creating illustrative, "dynamic" teaching slides for use at these conferences, we sought to provide salient radiology teaching material, demystify jargon, discuss appropriate imaging use, and review relevant anatomy. We hypothesized that TCS could improve the quality of IMMR as perceived by the IM presenter.

METHODS

TCS was piloted over a 7-month period. Each referred case was reviewed by a senior radiology resident who produced a set of "dynamic" teaching slides for each case. These included patient imaging overlayed with extensive annotations and animations highlighting teaching points, with particular attention to radiologic terminology. Slides were shared with the IM presenter, who could use them for preparation and include the animations in the talk if desired. TCS effectiveness was evaluated with a survey distributed to participating IM residents.

RESULTS

In the pilot period, 12 TCS requests were received and 10 were performed in collaboration with 6 IM residents. Survey results indicated that most IM residents did not consult radiologists prior to TCS (5/6, 83%). IM residents used the "dynamic" teaching slides to both prepare for and present at IMMR (5/6, 83%). TCS improved IM residents' perceived ability to engage their audience (6/6, 100%), confidence in teaching radiology material (4/6, 67%), ability to understand radiology reports (4/6, 67%) and appreciation for what radiologists do (6/6, 100%).

CONCLUSIONS

The TCS pilot resulted in successful radiology-IM collaboration and improved knowledge and confidence in teaching imaging concepts. Continuous program evaluation will be performed and future work will assess the effect of TCS on radiologist confidence in real-world clinical consultations.

How is the Doctor Feeling? ICU Provider Sentiment is Associated with Diagnostic Imaging Utilization

The judgment of intensive care unit (ICU) providers is difficult to measure using conventional structured electronic medical record (EMR) data. However, provider sentiment may be a proxy for such judgment. Utilizing 10 years of EMR data, this study evaluates the association between provider sentiment and diagnostic imaging utilization. We extracted daily positive / negative sentiment scores of written provider notes, and used a Poisson regression to estimate sentiment association with the total number of daily imaging reports. After adjusting for confounding factors, we found that (1) negative sentiment was associated with increased imaging utilization $(p < 0.01)$, (2) sentiment's association was most pronounced at the beginning of the ICU stay $(p < 0.01)$, and (3) the presence of any form of sentiment increased diagnostic imaging utilization up to a critical threshold $(p < 0.01)$. Our results indicate that provider sentiment may clarify currently unexplained variance in resource utilization and clinical practice.

The Integration of Active Learning Teaching Strategies Into a Radiology Rotation for Medical Students Improves Radiological Interpretation Skills and Attitudes Toward Radiology

PURPOSE

In recent years, there has been increased recognition of the benefits of teaching by active learning. However, there is a paucity of experimental studies utilizing active learning in undergraduate radiology rotations, which is traditionally a passive learning experience. We designed a new radiology rotation that integrated teaching by active learning. We prospectively examined the efficacy of this new rotation compared to our standard rotation in terms of students' radiological competency and attitudes toward radiology, as well as impact on departmental efficiency.

METHODS

This was a prospective cohort study involving fourth year medical students completing a 1-week radiology rotation at our department between January and April 2018. One cohort completed a rotational model which incorporated active learning sessions (integrated cohort) while the remainder were taught using traditional passive learning methods (standard cohort). All participants completed a radiology examination before and after the rotation and were surveyed on their attitudes toward radiology.

RESULTS

A total of 105 students enrolled in the study. The mean postrotation competency score obtained by the integrated cohort was significantly higher than that obtained by the standard cohort (82% vs 62%; P < 0.001). The integrated rotation freed up 7 hours of radiologists' time per week. While the students completing the integrated rotation had a more positive perception of radiology, they were no more likely to express a desire to pursue a career in radiology.

CONCLUSIONS

The integration of active learning sessions into an undergraduate radiology rotation results in an improvement in students' postrotation radiological competency and attitudes toward radiology.

In comparison with other abdominal imaging modalities, which radiologists interpret abdominal MRI?

PURPOSE

To assess subspecialty mix and case volumes of general and abdominal subspecialty radiologists interpreting abdominal MRI.

METHODS

The 2016 CMS Physician/Supplier Procedure Summary Master File was used to obtain billed counts of radiologist-interpreted abdominal fluoroscopy, US, CT, and MRI examinations. The CMS Physician and Other Supplier Public Use File was used to assess the subspecialty mix and case volume of the radiologists interpreting those examinations.

RESULTS

The fraction of all abdominal imaging examinations interpreted by generalists and abdominal subspecialty radiologists was 70.7% and 16.5% for fluoroscopy; 68.7% and 21.0% for US; 71.4% and 19.2% for CT; and 41.9% and 52.5% for MRI. In 2016, the fraction of general and abdominal radiologists interpreting > 50 fluoroscopy examinations on Medicare fee-for-service beneficiaries was 15.1% and 16.2%. For > 50 US examinations, the fraction was 61.5% and 60.5%; for > 50 CT examinations, 91.2% and 79.6%; and for > 50 MRI examinations, 4.0% and 28.5%. The fraction of abdominal imaging examinations interpreted overall by low-volume providers (those interpreting ≤ 50 examinations in 2016) was 59.5% for fluoroscopy, 17.5% for US, 6.3% for CT, and 50.6% for MRI.

CONCLUSION

Nationally, most abdominal fluoroscopy, US, and CT examinations are interpreted by general radiologists, who have similar annual volumes of these examinations as abdominal subspecialty radiologists. In contrast, most abdominal MRI examinations are interpreted by abdominal subspecialty radiologists, who attain considerably higher volumes. These findings have implications for workforce planning and abdominal imaging fellowship design to ensure their graduates are optimally prepared to contribute to their future practices.

Follow-up MRI in multiple sclerosis patients: automated co-registration and lesion color-coding improves diagnostic accuracy and reduces reading time

OBJECTIVES

In multiple sclerosis (MS), the heterogeneous and numerous appearances of lesions may impair diagnostic accuracy. This study investigates if a combined automated co-registration and lesion color-coding method (AC) improves assessment of MS follow-up MRI compared with conventional reading (CR).

METHODS

We retrospectively assessed 70 follow-up MRI of 53 patients. Heterogeneous datasets of diverse scanners and institutions were used. Two readers determined presence of (a) progression, (b) regression, (c) mixed change, or (d) stable disease between the two examinations using corresponding FLAIR sequences in CR and AC-assisted reading. Consensus reference reading was provided by two blinded radiologists. Kappa statistics tested interrater agreement, McNemar's test dichotomous variables, and Wilcoxon's test continuous variables (statistical significance p ≤ 0.05).

RESULTS

The cohort comprised 41 female and 12 male patients with a mean age of 40 (± 14) years. Average rating time was reduced from 78 (± 36) to 44 (±22) s with the AC approach (p < 0.001). The time needed to start and match datasets with AC was 14 (± 1) s. Compared with CR, AC improved interrater agreement, both between raters (0.52 vs. 0.67) and between raters and consensus reference reading (0.47/0.5 vs. 0.83/0.78). Compared with CR, the diagnostic accuracy increased from 67 to 90% (reader 1, p < 0.01) and from 70 to 87% (reader 2, p < 0.05) in the AC-assisted reading.

CONCLUSIONS

Compared with CR, automated co-registration and lesion color-coding of MS-associated FLAIR-lesions in follow-up MRI increased diagnostic accuracy and reduced the time required for follow-up evaluation significantly. The AC algorithm therefore appears to be helpful to improve MS follow-up assessments in clinical routine.

KEY POINTS

• Automated co-registration and lesion color-coding increases diagnostic accuracy in the assessment of MRI follow-up examinations in patients with multiple sclerosis. • Automated co-registration and lesion color-coding reduces reading time of MRI follow-up examinations in patients with multiple sclerosis. • Automated co-registration and lesion color-coding improved interrater agreement in the assessment of MRI follow-up examinations in patients with multiple sclerosis.

Detecting insertion, substitution, and deletion errors in radiology reports using neural sequence-to-sequence models

Background

Errors in grammar, spelling, and usage in radiology reports are common. To automatically detect inappropriate insertions, deletions, and substitutions of words in radiology reports, we proposed using a neural sequence-to-sequence (seq2seq) model.

Methods

Head CT and chest radiograph reports from Mount Sinai Hospital (MSH) (n=61,722 and 818,978, respectively), Mount Sinai Queens (MSQ) (n=30,145 and 194,309, respectively) and MIMIC-III (n=32,259 and 54,685) were converted into sentences. Insertions, substitutions, and deletions of words were randomly introduced. Seq2seq models were trained using corrupted sentences as input to predict original uncorrupted sentences. Three models were trained using head CTs from MSH, chest radiographs from MSH, and head CTs from all three collections. Model performance was assessed across different sites and modalities. A sample of original, uncorrupted sentences were manually reviewed for any error in syntax, usage, or spelling to estimate real-world proofreading performance of the algorithm.

Results

Seq2seq detected 90.3% and 88.2% of corrupted sentences with 97.7% and 98.8% specificity in same-site, same-modality test sets for head CTs and chest radiographs, respectively. Manual review of original, uncorrupted same-site same-modality head CT sentences demonstrated seq2seq positive predictive value (PPV) 0.393 (157/400; 95% CI, 0.346-0.441) and negative predictive value (NPV) 0.986 (789/800; 95% CI, 0.976-0.992) for detecting sentences containing real-world errors, with estimated sensitivity of 0.389 (95% CI, 0.267-0.542) and specificity 0.986 (95% CI, 0.985-0.987) over n=86,211 uncorrupted training examples.

Conclusions

Seq2seq models can be highly effective at detecting erroneous insertions, deletions, and substitutions of words in radiology reports. To achieve high performance, these models require site- and modality-specific training examples. Incorporating additional targeted training data could further improve performance in detecting real-world errors in reports.

Radiology Education in the 21st Century: Threats and Opportunities

Over the past 25 years, radiology has seen tremendous growth in interpretive demands, including increasing imaging volumes and shorter turnaround times, as well as increased noninterpretive demands often targeting value-adding opportunities. These mounting pressures have led to increased burnout among radiologists nationwide and, in the academic setting, have begun to threaten the core educational mission. Despite these threats, radiology has also proven itself over the years to be a leader when it comes to innovation, and as such, no other field is better suited to confront these challenges with innovative solutions. This article explores the impact these workload trends have had on radiology education and educators, as well as opportunities to confront these challenges.

Advanced diagnostic imaging utilization during emergency department visits in the United States: A predictive modeling study for emergency department triage

Background

Emergency department (ED) crowding is associated with negative health outcomes, patient dissatisfaction, and longer length of stay (LOS). The addition of advanced diagnostic imaging (ADI), namely CT, ultrasound (U/S), and MRI to ED encounter work up is a predictor of longer length of stay. Earlier and improved prediction of patients’ need for advanced imaging may improve overall ED efficiency. The aim of the study was to detect the association between ADI utilization and the structured and unstructured information immediately available during ED triage, and to develop and validate models to predict utilization of ADI during an ED encounter.

Methods

We used the United States National Hospital Ambulatory Medical Care Survey data from 2009 to 2014 to examine which sociodemographic and clinical factors immediately available at ED triage were associated with the utilization of CT, U/S, MRI, and multiple ADI during a patient’s ED stay. We used natural language processing (NLP) topic modeling to incorporate free-text reason for visit data available at time of ED triage in addition to other structured patient data to predict the use of ADI using multivariable logistic regression models.

Results

Among the 139,150 adult ED visits from a national probability sample of hospitals across the U.S, 21.9% resulted in ADI use, including 16.8% who had a CT, 3.6% who had an ultrasound, 0.4% who had an MRI, and 1.2% of the population who had multiple types of ADI. The c-statistic of the predictive models was greater than or equal to 0.78 for all imaging outcomes, and the addition of text-based reason for visit information improved the accuracy of all predictive models.

Conclusions

Patient information immediately available during ED triage can accurately predict the eventual use of advanced diagnostic imaging during an ED visit. Such models have the potential to be incorporated into the ED triage workflow in order to more rapidly identify patients who may require advanced imaging during their ED stay and assist with medical decision-making.

Altered Mental Status in ICU Patients: Diagnostic Yield of Noncontrast Head CT for Abnormal and Communicable Findings

OBJECTIVE

To evaluate the diagnostic yield of noncontrast head CT for acute communicable findings in ICU patients specifically scanned for altered mental status.

DESIGN

Retrospective observational cohort study.

SETTING

University Hospital Neuroscience, Medical, and Surgical ICUs.

PATIENTS

ICU patients with new-onset altered mental status.

INTERVENTION

Noncontrast head CT.

MEASUREMENTS AND MAIN RESULTS

Reports on head CTs from two university hospitals performed for the sole indication of altered mental status in ICU patients between July 2011 and June 2013 were reviewed for 1) acute (new or worsening) hemorrhage, 2) mass effect/herniation, 3) infarction, and 4) hydrocephalus. Subgroup analyses of positive findings were performed by 1) ICU group type, 2) age, and 3) race. A total of 2,486 head CTs were performed in 1,357 patients whose age ranged from 14 to 116 years (median, 59; mean, 57.6 ± 16). Acute communicable findings in at least one of four categories were present in 22.8% (566/2,486) of examinations, with hydrocephalus being most common (11.5% [286/2,486]). The frequency of any acute communicable findings in neuroscience, medical, and surgical ICUs was 28.6% (471/1,648), 9.8% (43/440), and 13.1% (52/398), respectively. Neuroscience ICU head CTs had significantly higher rates of acute communicable findings in all categories, except for acute infarction, compared with the other two ICUs (p < 0.001). Acute hydrocephalus (13.6% vs 7.4%; p < 0.001) and mass effect (6.7% vs 4.3%; p = 0.01) were more common in patients less than 65 years. For other acute categories, no significant difference was noted by age. There was no significant difference in the likelihood of a positive examination by race.

CONCLUSIONS

Almost one in four head CTs in a university ICU patient population performed for primary indication of altered mental status yields abnormal communicable findings. In this patient population, utilization management barriers to examination ordering should be minimized.

Teaching Critical Thinking in Graduate Medical Education: Lessons Learned in Diagnostic Radiology

The 2014 Institute of Medicine report, Graduate Medical Education that Meets the Nation's Health Needs, challenged the current graduate medical training process and encouraged new opportunities to redefine the fundamental skills and abilities of the physician workforce. This workforce should be skilled in critically evaluating the current systems to improve care delivery and health. To meet these goals, current challenges, motivations, and educational models at the medical school and graduate medical education levels related to formal training in nonclinical aspects of medicine, especially critical thinking, are reviewed. Our diagnostic radiology training program is presented as a "case study" to frame the review.

Implementation of a Longitudinal Introduction to Radiology Course During Internship Year Improves Diagnostic Radiology Residents' Academic and Clinical Skills: A Canadian Experience

RATIONALE AND OBJECTIVES

In order to ease the transition from internship to diagnostic radiology residency, a year-long didactic introduction to radiology course was offered to post-graduate year one (PGY-1) diagnostic radiology residents during their internship, which consisted of 27 hours of lecture over 9 months. The purpose of this study was to determine the quantitative and qualitative educational value of this course and its effect with respect to on-call preparedness.

MATERIALS AND METHODS

Two consecutive cohorts of Diagnostic Radiology residents were included: the first cohort (PGY-1s in 2011-2012) did not participate in the new course (Old Curriculum Residents) and the second cohort (PGY-1s in 2012-2013) completed the new course (New Curriculum Residents). These two cohorts were compared both qualitatively and quantitatively. Scores were compared from the standardized Canadian National Pre-Call Observed Standardized Clinical Examination and American College of Radiology Diagnostic Radiology In-Training examination, which are taken in the PGY-2 year, at months 5 and 7, respectively. In addition, staff observation of on-call resident performance and resident self-reported preparedness were considered. Cohorts were compared using Mann-Whitney U test with significance defined as P value <0.05. P values from 0.05 to 0.10 were noted as possibly significant and further analyzed using a Cohen d test where the difference was determined to be small (0.2), medium (0.5), or large (0.8).

RESULTS

New Curriculum Residents reported that the content of the PGY1 curriculum was more appropriate than the old curriculum to prepare them for call in PGY2 (P = 0.013). New Curriculum Residents scored better than the Old Curriculum Residents on the Diagnostic Radiology In-Training examination (P = 0.039) and on the emergency cases of the Canadian National Pre-Call Observed Standardized Clinical Examination (P = 0.035). Staff radiologists, who were not blinded, reported that the New Curriculum Residents were better prepared for daytime (P = 0.006) and overnight (P = 0.008) independent call were better prepared to perform common ultrasound examinations alone (P = 0.049), and required less guidance while on call for nine competency areas. There was, however, no statistical difference between the residents' self-reported preparedness for independent call.

CONCLUSIONS

Participation in a lecture-based introductory radiology curriculum during the PGY-1 internship year improved both radiology residents' preparedness for call and their performance in PGY-2.

Changing Abdominal Imaging Utilization Patterns: Perspectives From Medicare Beneficiaries Over Two Decades

PURPOSE

To assess changing utilization patterns of abdominal imaging in the Medicare fee-for-service population over the past two decades.

METHODS

Medicare Physician Supplier Procedure Summary master files from 1994 through 2012 were used to study changes in the frequency and utilization rates (per 1,000 Medicare beneficiaries per year) of abdominal CT, MRI, ultrasound, and radiography.

RESULTS

In Medicare beneficiaries, the most frequently performed abdominal imaging modality changed from radiography in 1994 (207.4 per 1,000 beneficiaries) to CT in 2012 (169.0 per 1,000). Utilization rates of abdominal MR (1037.5%), CT (197.0%), and ultrasound (38.0%) all increased from 1994-2012 (but declined briefly from 2007 to 2009). A dramatic 20-year utilization rate decline occurred for gastrointestinal fluoroscopic examinations (-91.9% barium enema, -80.0% upper gastrointestinal series) and urologic radiographic examinations (-95.3%). Radiologists were the dominant providers of all modalities, accounting for >90% of CT and MR studies, and >75% of most ultrasound examination types.

CONCLUSIONS

Medicare utilization of abdominal imaging has markedly changed over the past two decades, with overall dramatic increases in CT and MRI and dramatic decreases in gastrointestinal fluoroscopic and urologic radiographic imaging. Despite these changes, radiologists remain the dominant providers in all abdominal imaging modalities.

Myelography CPT Coding Updates: Effects of 4 New Codes and Unintended Consequences

The Current Procedural Terminology of the American Medical Association has recently introduced coding changes for myelography with the introduction of new bundled codes. The aim of this review was to help neuroradiologists understand these code changes and their unintended consequences and to discuss various scenarios in which permutations of various codes could occur in clinical practice.