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.     

Guidelines for the Evaluation of Pulmonary Nodules Detected Incidentally or by Screening: A Survey of Radiologist Awareness,Agreement, and Adherence From the Watch the Spot Trial

PurposeThe aim of this study was to examine radiologists’ beliefs about existing guidelines for pulmonary nodule evaluation.MethodsA self-administered survey was developed to ascertain awareness of, agreement with, and adherence to published guidelines, including those from the Fleischner Society and the Lung CT Screening Reporting and Data System (Lung-RADS™). Surveys were distributed to 514 radiologists at 13 health care systems that are participating in a large, pragmatic trial of pulmonary nodule evaluation. Prespecified comparisons were made among groups defined by type of health system, years of experience, reader volume, and study arm.ResultsThe response rate was 26.3%. Respondents were most familiar with guidelines from Fleischner (94%) and Lung-RADS (71%). For both incidental and screening-detected nodules, self-reported adherence to preferred guidelines was very high (97% and 94%, respectively), and most respondents believed that the benefits of adherence outweigh the harms (81% and 74%, respectively). Underlying evidence was thought to be high in quality by 68% of respondents for screening-detected nodules and 41% for incidental nodules. Approximately 70% of respondents believed that the frequency of recommended follow-up was “just right” for both guidelines. Radiologists who practice in nonintegrated health care systems were more likely to believe that the evidence was high in quality (79.5% versus 57.1%) and that the benefits of adherence outweigh the harms (85.1% versus 67.5%). Low-volume readers had lower awareness and self-reported adherence than higher volume readers.ConclusionsRadiologists reported high levels of familiarity and agreement with and adherence to guidelines for pulmonary nodule evaluation, but many overestimated the quality of evidence in support of the recommendations.     

A Multidisciplinary Approach to Improving Appropriate Follow-Up Imaging of Ovarian Cysts: A Quality Improvement Initiative

PurposeIncidental ovarian cysts are frequently detected on imaging. Despite published follow-up consensus statements, there remains variability in radiologist follow-up recommendations and clinician practice patterns. The aim of this study was to evaluate if collaborative ovarian cyst management recommendations and a radiologist decision support tool can improve adherence to follow-up recommendations.MethodsGynecologic oncologists and abdominal radiologists convened to develop collaborative institutional recommendations for the management of incidental, asymptomatic simple ovarian cysts detected on ultrasound, CT, and MRI. The recommendations were developed by modifying the published consensus recommendations developed by the Society of Radiologists in Ultrasound on the basis of local practice patterns and the experience of the group members. A less formal process involved the circulation of the published consensus recommendations, followed by suggestions for revisions and subsequent consensus, in similar fashion to the ACR Incidental Findings Committee II. The recommendations were developed by building on the published work of experienced groups to provide the authors’ medical community with a set of recommendations that could be endorsed by both the Department of Gynecology and the Department of Radiology to provide supportive guidance to the clinicians who manage incidental ovarian cysts. The recommendations were integrated into a radiologist decision support tool accessible from the dictation software. Nine months after tool launch, institutional review board approval was obtained, and radiology reports mentioning ovarian cysts in the prior 34 months were retrospectively reviewed. For cysts detected on ultrasound, adherence rates to Society of Radiologists in Ultrasound recommendations were calculated for examinations before tool launch and compared with adherence rates to the collaborative institutional recommendations after tool launch. Additionally, electronic medical records were reviewed to determine the follow-up chosen by the clinician.ResultsFor cysts detected on ultrasound, radiologist adherence to recommendations improved from 50% (98 of 197) to 80% (111 of 139) (P < .05). Overmanagement decreased from 34% (67 of 197) to 10% (14 of 139) (P < .05). A recommendation was considered “overmanaged” if the radiologist recommended follow-up when it was not indicated or if the recommended follow-up time was at a shorter interval than indicated. Clinician adherence to radiologist recommendations showed statistically nonsignificant improvement from 49% (36 of 73) to 57% (27 of 47) (P = .5034).ConclusionsManagement recommendations developed through collaboration with clinicians may help standardize follow-up of ovarian cysts and reduce overutilization.     

Radiology Order Decision Support: Examination-Indication Appropriateness Assessed Using 2 Electronic Systems

PurposeThe goal of the study was to determine the effects of guideline implementation strategy using 2 commercial radiology clinical decision support (CDS) systems.MethodsThe appropriateness and insurance dispositions of MRI and CT orders were evaluated using the Medicalis SmartReq and Nuance RadPort CDS systems during 2 different 3-month periods. Logistic regression was used to compare these outcomes between the 2 systems, after adjusting for patient-mix differences.ResultsApproximately 2,000 consecutive outpatient MRI and CT orders were evaluated over 2 periods of 3 months each. Medicalis scored 60% of exams as “indeterminate” (insufficient information) or “not validated” (no guidelines). Excluding these cases, Nuance scored significantly more exams as appropriate than did Medicalis (80% versus 51%, P < .001) and predicted insurance outcome significantly more often (76% versus 58%, P < .001). Only when the Medicalis “indeterminate” and “not validated” categories were combined with the high- or moderate-utility categories did the 2 CDS systems have similar performance. Overall, 19% of examinations with low-utility ratings were reimbursed. Conversely, 0.8% of examinations with high- or moderate-utility ratings were denied reimbursement.ConclusionsThe chief difference between the 2 CDS systems, and the strongest influence on outcomes, was how exams without relevant guidelines or with insufficient information were handled. Nuance augmented published guidelines with clinical best practice; Medicalis requested additional information utilizing pop-up windows. Thus, guideline implementation choices contributed to decision making and outcomes. User interface, specifically, the number of screens and completeness of indication choices, controlled CDS interactions and, coupled with guidance implementation, influenced willingness to use the CDS system.     

Higher Imaging Yield When Clinical Decision Support Is Used

ObjectiveIncreased utilization of CT pulmonary angiography (CTPA) for the evaluation of pulmonary embolism has been associated with decreasing diagnostic yields and rising concerns about the harms of unnecessary testing. The objective of this study was to determine whether clinical decision support (CDS) use would be associated with increased imaging yields after controlling for selection bias.MethodsWe performed a retrospective cohort study in the emergency departments of two tertiary care hospitals of all CTPAs performed between August 2015 and September 2018. Providers ordering a CTPA are routed to an optional CDS tool, which allows them to use Wells’ Criteria for pulmonary embolism. After propensity score matching, CTPA yield was calculated for the CDS-use and CDS-dismissal groups and stratified by provider type.ResultsA total of 7,367 CTPAs were ordered during the study period. Of those, providers used the CDS tool in 2,568 (35%) cases and did not use the tool in 4,799 (65%) of cases. After propensity score matching, CTPA yield was 11.99% in the CDS-use group and 8.70% in the CDS-dismissal group (P < .001). Attending physicians, residents, and physician assistant CDS users demonstrated a 56.5% (P = .006), 38.7% (P = .01), and 16.7% (P = .03) increased yield compared with those who dismissed the tool, respectively.DiscussionDiagnostic yield was 38% higher for CTPAs when the provider used the CDS tool, after controlling for selection bias. Yields were higher for every provider type. Further research is needed to discover successful strategies to increase provider use of these important tools.     

Retrospective Analysis of Emergency Computed Tomography Imaging Utilization at an Academic Centre: An Analysis of Clinical Indications and Outcomes

PurposeTo explore resource utilization through evaluation of computed tomography (CT) imaging trends in the emergency department by examining common indications/outcomes for imaging in this setting.MethodsA retrospective analysis of clinical indications/outcomes for all CT imaging in 3 emergency departments over a 1-year period was conducted. Scans were divided by body part and the most common indications for each type of scan were determined. Clinical outcomes from each study were extracted from final interpretations by the reporting radiologist.ResultsA total of 4556 CT scans were performed in the emergency department over a 1-year period. A total of 3.6% of all-comers to our emergency departments underwent CT scan as part of their investigation. There were 2107 head CTs (46%), 1296 (28%) abdominal CTs, 468 (10%) CTs of the chest, 408 (9%) CTs of the neck/spine, and 101 (2%) extremity CTs performed. The most common clinical indication for performing a CT head was focal neurological defect comprising 1534 (73%) of all CT heads. Twenty-four percent of abdominal CTs were for investigation of right lower quadrant pain, followed by flank pain (19%). Chest pain and shortness of breath were the most common indications for CTs of the chest (315 [75%]) with 10% of these examinations for this indication positive for pulmonary embolism. Trauma was the most common indication for neck CTs (296 [73%]) and extremities (70 [69%]). Nil acute was the most common final interpretation in all categories (79% CT heads, 75% neck CTs, 38% abdominal CTs, 43% chest CTs).ConclusionsNil acute was the most common diagnosis; however, serious clinical outcomes were identified 40% of the time. Cross-sectional imaging remains an integral tool for triage and diagnosis in this environment as the cost of missing a diagnosis in this setting has a great impact on patient care.     

Natural Language Processing for Identification of Incidental Pulmonary Nodules in Radiology Reports

PurposeTo develop natural language processing (NLP) to identify incidental lung nodules (ILNs) in radiology reports for assessment of management recommendations.Methods and MaterialsWe searched the electronic health records for patients who underwent chest CT during 2014 and 2017, before and after implementation of a department-wide dictation macro of the Fleischner Society recommendations. We randomly selected 950 unstructured chest CT reports and reviewed manually for ILNs. An NLP tool was trained and validated against the manually reviewed set, for the task of automated detection of ILNs with exclusion of previously known or definitively benign nodules. For ILNs found in the training and validation sets, we assessed whether reported management recommendations agreed with Fleischner Society guidelines. The guideline concordance of management recommendations was compared between 2014 and 2017.ResultsThe NLP tool identified ILNs with sensitivity and specificity of 91.1% and 82.2%, respectively, in the validation set. Positive and negative predictive values were 59.7% and 97.0%. In reports of ILNs in the training and validation sets before versus after introduction of a Fleischner reporting macro, there was no difference in the proportion of reports with ILNs (108 of 500 [21.6%] versus 101 of 450 [22.4%]; P = .8), or in the proportion of reports with ILNs containing follow-up recommendations (75 of 108 [69.4%] versus 80 of 101 [79.2%]; P = .2]. Rates of recommendation guideline concordance were not significantly different before and after implementation of the standardized macro (52 of 75 [69.3%] versus 60 of 80 [75.0%]; P = .43).ConclusionNLP reliably automates identification of ILNs in unstructured reports, pertinent to quality improvement efforts for ILN management.     

An evaluation of the effect that the implementation of the NICE rules may have on a diagnostic imaging department for the early management of head injuries

IntroductionGuidelines by the National Institute of Clinical Excellence (NICE) for the early management of minor head injuries initiate the use of computed tomography (CT) for patients who may be at risk of developing intracranial haematoma. This retrospective study was designed to evaluate the effect the implementation of the NICE guidelines would have on the diagnostic imaging department of a local district general hospital. The main objective was to establish if there would be an increase in the number of CT head referrals for patients with minor head injuries. Secondly to assess how the implementation of these guidelines would affect the workload to the diagnostic imaging department in terms of cost and time, and to discuss the issue of radiation dose to patients.MethodA sample of 100 patients who were referred from the Accident and Emergency department (A&E) for plain skull radiographs, over a 4-month period were selected. The clinical information on each of these patients' was then extracted and a data collection sheet was to assess each patient according to the NICE criteria.Results and conclusionThe study found an 18% (n = 100) increase in the referral rate for CT heads for patients presenting with minor head injuries. It was also found that the use of these guidelines would mean a decrease in cost to the diagnostic imaging department of £324. Furthermore a saving of 10 h of radiographers' time was established, although the effective radiation dose to patients would be increased by 29 mSv.The NICE guidelines have proved efficient in identifying patients with intracranial damage although this coincides with an 18% (n = 100) increase in referral rates for CT and increased radiation dose to patients. However, the use of these guidelines would reduce workload to the diagnostic imaging department in terms of cost and time.     

Correlation of the Strength of Recommendations for Additional Imaging to Adherence Rate and Diagnostic Yield

PurposeThe aim of this study was to evaluate the association between the wording of radiologist recommendations for chest CT with the likelihood of recommendation adherence and the diagnostic yield of the recommended follow-up CT imaging.MethodsThis HIPAA-compliant retrospective study had institutional review board approval, including waiver of the requirement for patient consent. All outpatient chest radiographic (CXR) studies performed at a tertiary care academic medical center in 2008 (n = 29,138) were searched to identify examinations with recommendations for chest CT. The wording of chest CT recommendations was classified as conditional or absolute, on the basis of whether the recommendation stood independent of the clinical judgment of the ordering clinician. Using the radiology information system, patients who underwent chest CT within 90 days of the index CXR study containing the recommendation were determined, and the CT studies were evaluated to determine if there were abnormalities corresponding to the CXR abnormalities that prompted the recommendations. Corresponding abnormalities were categorized as clinically relevant or not, on the basis of whether further workup or treatment was warranted. Groups were compared using t tests and Fisher exact tests.ResultsRecommendations for chest CT appeared in 4.5% of outpatient CXR studies (1,316 of 29,138; 95% confidence interval [CI], 4.3%–4.8%); 39.4% (519 of 1,316; 95% CI, 36.8%–42.0%) were conditional and 60.6% (797 of 1,316; 95% CI, 58.0%–63.2%) were absolute. Patients with absolute recommendations were significantly more likely to undergo follow-up chest CT within 90 days than patients with conditional recommendations (67.8% vs 45.8%, respectively, P < .001). Despite this difference in provider adherence, there was no significant difference between the conditional and absolute recommendation groups with regard to the incidence of clinically relevant corresponding findings (P = .16) or malignancy (P = .08) on follow-up CT.ConclusionsConditional radiologist recommendations are associated with decreased provider adherence, though the likelihood of a clinically relevant finding on follow-up CT is no different than with absolute recommendations.     

Use of a Commercially Available Clinical Decision Support Tool to Expedite Prior Authorization in Partnership With a Private Payer

PurposeThe aim of this study was to determine if a clinical decision support (CDS) tool could be used in partnership with a private payer to successfully expedite the prior authorization process for advanced (ie, MRI, CT, PET, nuclear medicine) imaging requests.MethodsA single academic institution integrated a commercially available CDS tool utilizing the ACR Appropriateness Criteria into the ordering process for outpatient advanced imaging tests within the electronic health record. Ordering providers could elect to use the CDS tool or ignore the available technology. In partnership with a health care insurance company and a contracted radiology benefits management company, orders deemed as “usually indicated” by the CDS tool underwent expedited prior authorization in a pilot program from June 2018 to October 2019.ResultsProviders used the CDS tool for 15% (1,453 of 9,640) of outpatient advanced imaging orders. Of these orders with elective CDS scores, 69% (n = 997) qualified for an expedited prior authorization process.ConclusionsUnder specific circumstances, a commercially available CDS tool was used in partnership with a private payer and a radiology benefits management company to expedite prior authorization of outpatient advanced imaging examination orders deemed likely to be appropriate by multispecialty professional guidelines.     

Implementation of a Semistructured Clinical Event Documentation Tool for Acute Adverse Contrast Reactions

PurposeTo improve the efficiency and accuracy of clinicians documenting acute clinical events related to contrast agent administration using a web browser–based semistructured documentation support tool.MethodsA new tool called Contrast Incident Support and Reporting (CISaR) was developed to enable radiologists responding to contrast reactions to document inciting contrast class, type of event, severity of contrast reaction, and recommendation for future contrast use. Retrospective analysis was conducted of all CT and MRI examinations performed between February 2018 and December 2019 across our hospital system with associated contrast reaction documentation. Time periods were defined as before tool deployment, early adoption, and steady-state deployment. The primary outcome measure was the presence of event documentation by a radiologist. The secondary outcome measure was completeness of the documentation parameters.ResultsA total of 431 CT and MRI studies with reactions were included in the study, and 50% of studies had radiologist documentation during the pre-CISaR period. This increased to 66% during the early adoption period and 89% in the post-CISaR period. It took approximately 9 months from the introduction of CISaR to reach full adoption and become the main method for adverse contrast reaction documentation. The percentage of radiologist documentation that detailed provoking contrast agent class, severity of reaction, reaction type, and future contrast agent recommendation all significantly increased (P < .0001), with greater than 95% inclusion of each element.ConclusionThe implementation of a semistructured electronic application for adverse contrast reaction reporting significantly increased radiologist documentation rate and completeness of the documentation.     

Incidental findings in emergency imaging: frequency,recommendations, and compliance with consensus guidelines

The purpose of this study was to evaluate the frequency of incidental findings (IFs) in emergency department (ED) imaging reports and evaluate the adherence of imaging recommendations to consensus societal guidelines for IFs. A retrospective review of consecutive ED computed tomography (CT) and ultrasonography (US) reports from two university-affiliated EDs over a 2-month period was performed. Each imaging report was reviewed in its entirety, and incidental findings were documented along with recommendations for additional imaging. Imaging recommendations were compared to published societal guidelines from the American College of Radiology (ACR) and Fleischner Society. Three thousand one hundred thirty-one total cases consisting of 1967 CTs and 1164 US contained 514 incidental findings (16.4 %), with 329 CT IFs (64 %) and 185 US IFs (36 %). The ovary was the most common organ for an IF (n?=?214, 42 %). Of all IFs, 347 (67.5 %) recommendations were concordant with societal guidelines and 167 (32.5 %) were discordant. 39.8 % of CT recommendations were discordant, while 19.5 % of US recommendations were discordant (p?<?0.0001). Incidental findings are commonly encountered in the emergent setting. Variable adherence to societal guidelines is noted. Targeted radiologist education and technological solutions may decrease rates of discordance.     

CT Pulmonary Angiography: Using Decision Rules in the Emergency Department

PurposeThe aim of this study was to assess the appropriateness of utilization and diagnostic yields of CT pulmonary angiography (CTPA), comparing two commonly applied decision rules, the pulmonary embolism (PE) rule-out criteria (PERC) and the modified Wells criteria (mWells), in the emergency department (ED) setting.MethodsInstitutional review board approval was obtained for this HIPAA-compliant, prospective–cohort, academic single-center study. Six hundred two consecutive adult ED patients undergoing CTPA for suspected PE formed the study population. The outcome was positive or negative for PE by CTPA and at 6-month follow-up. PERC and mWells scores were calculated. A positive PERC score was defined as meeting one or more criteria and a positive mWells score as >4. The percentage of CT pulmonary angiographic examinations that could have been avoided and the diagnostic yield of CTPA using PERC, mWells, and PERC applied to a negative mWells score were calculated.ResultsThe diagnostic yield of CTPA was 10% (61 of 602). By applying PERC, mWells, and PERC to negative mWells score, 17.6% (106 of 602), 45% (273 of 602), and 17.1% (103 of 602) of CT pulmonary angiographic examinations, respectively, could have been avoided. The diagnostic yield in PERC-positive patients was higher than in mWells-positive patients (10% [59 of 602] vs 8% [49 of 602], P < .0001). Among PERC-negative and mWells-negative patients, the diagnostic yields for PE were 1.9% (2 of 106) and 4% (12 of 273), respectively (P = .004). The diagnostic yield of a negative PERC score applied to a negative mWells score was 1.9% (2 of 103).ConclusionsThe use of PERC in the ED has the potential to significantly reduce the utilization of CTPA and misses fewer cases of PE compared with mWells, and it is therefore a more efficient decision tool.     

Additional value of integrated PET-CT in the detection and characterization of lung metastases: correlation with CT alone and PET alone

The purpose was evaluating retrospectively the additional value of integrated positron emission tomography (PET) and computed tomography (CT) in the detection of pulmonary metastases in comparison with CT and PET alone. Fifty-six lung nodules, divided into three groups according their size, detected in 24 consecutive patients with a known primary tumor were retrospectively evaluated with integrated PET-CT, CT and PET. The nature of these nodules was determined by either histopathology or a follow-up of at least 6 months. The CT and PET images of the integrated PET-CT were evaluated separately by a radiologist and a nuclear medicine physician, the integrated PET-CT images were evaluated by a chest radiologist and nuclear medicine physician in consensus. The investigators were asked to search lung nodules and to determine whether these nodules were metastases or not. Sensitivity and accuracy for CT, PET and integrated PET-CT for characterization of all pulmonary nodules were, respectively: 100%, 90%, 100% and 57%, 55%, 55%. There was no significant difference in the characterization of pulmonary nodules between integrated PET-CT and CT alone (P=1.000) and PET alone (P=0.1306). An accurate evaluation is only possible for lesions larger than 1 cm.     

Factors Affecting Adherence to Recommendations for Additional Imaging of Incidental Findings in Radiology Reports

ObjectiveTo determine the rate at which recommendations for additional imaging (RAIs) of incidental findings on CT are adhered to at a tertiary-care medical center and what factors influence adherence.MethodsWe used a radiology clinical informatics tool (mPower, Nuance Communications Inc, Burlington, Massachusetts) to identify RAIs in reports from all CT examinations performed at a tertiary-care medical center during a 6-month period. For those studies in which the RAI was for incidental findings, we reviewed the patients’ charts to determine if there was appropriate follow-up of the lesion in question.ResultsThe overall rate of adherence to RAIs was 39.1%, and in patients with a same-institution primary care provider (PCP), 56.8% (P < .0001). Adherence was higher in studies ordered in the outpatient setting (P < .0001) and in patients with a same-institution PCP (P < .0001). Among patients with a same-institution PCP, adherence was highest for outpatients (66.7%), followed by patients seen in the emergency department (46.0%) and inpatients (36.0%). Among outpatients, adherence was highest with PCPs (67%) followed by internal medicine subspecialties (50%) and surgery (38%).DiscussionThe rate of adherence to recommendations for additional imaging of incidental findings was 39.1% in this study and higher for patients with a same-institution PCP, studies ordered in the outpatient setting, and in studies ordered by PCPs.     

Does Direct Radiologist-Patient Verbal Communication Affect Follow-Up Compliance of Probably Benign Assessments?

PurposeThe aim of this study was to determine whether direct verbal communication of results by a radiologist affected follow-up compliance rates for probably benign breast imaging findings.MethodsThis study was institutional review board approved and HIPAA compliant. A retrospective search identified all patients from January 1, 2010 to December 31, 2010 who had breast findings newly assessed as probably benign (BI-RADS category 3). Patients were categorized by whether the radiologist or the technologist verbally communicated the result and follow-up recommendation. Patient adherence to 6-, 12-, and 24-month follow-up imaging recommendations was recorded.ResultsCompliance data were available for 770 of 819 patients in the study. Overall compliance was 83.0% (639 of 770) for 6-month examinations, 68.1% (524 of 770) for 6- and 12-month examinations, and 57.4% (442 of 770) for 6-, 12-, and 24-month examinations. For patients who initially underwent diagnostic mammography alone, there was no significant difference in compliance between those who had and those who did not have radiologist-patient communication (6 months, 81.9% vs 80.8% [P = .83]; 6 and 12 months, 70.8% vs 67.3% [P = .58]; 6, 12, and 24 months, 54.2% vs 58.4% [P = .53]). For patients who initially underwent diagnostic mammography alone versus ultrasound with or without diagnostic mammography, there was no significant difference in compliance (6 months, 81.1% vs 84.3% [P = .24]; 6 and 12 months, 68.1% vs 68.0% [P = .96]; 6, 12, and 24 months, 57.4% vs 57.4% [P = .00]).ConclusionsHigh initial compliance was achieved by radiologist or technologist verbal communication of findings and recommendations. Direct communication by the radiologist did not increase compliance compared with communication by a technologist.     

Qualitative Study to Understand Ordering of CT Angiography to Diagnose Pulmonary Embolism in the Emergency Room Setting

PurposeTo better understand the decision making behind the ordering of CT pulmonary angiography (CTPA) for the diagnosis of pulmonary embolism (PE) in the emergency department.MethodsWe conducted semistructured interviews with our institution’s emergency medicine (EM) providers and radiologists who read CTPAs performed in the emergency department. We employed the Theoretical Domains Framework—a formal, structured approach used to better understand the motivations and beliefs of physicians surrounding a complex medical decision making—to categorize the themes that arose from our interviews.ResultsEM providers were identified as the main drivers of CTPA ordering. Both EM and radiologist groups perceived the radiologist’s role as more limited. Experience- and gestalt-based heuristics were the most important factors driving this decision and more important, in many cases, than established algorithms for CTPA ordering. There were contrasting views on the value of d-dimer in the suspected PE workup, with EM providers finding this test less useful than radiologists. EM provider and radiologist suggestions for improving the appropriateness of CTPA ordering consisted of making this process more arduous and incorporating d-dimer tests and prediction rules into a decision support tool.ConclusionEM providers were the main drivers of CTPA ordering, and there was a marginalized role for the radiologist. Experience- and gestalt-based heuristics were the main influencers of CTPA ordering. Our findings suggest that a more nuanced intervention than simply including a d-dimer and a prediction score in each preimaging workup may be necessary to curb overordering of CTPA in patients suspected of PE.     

Diagnostic Performance of Deep Learning-Based Lesion Detection Algorithm in CT for Detecting Hepatic Metastasis from Colorectal Cancer

ObjectiveTo compare the performance of the deep learning-based lesion detection algorithm (DLLD) in detecting liver metastasis with that of radiologists.Materials and MethodsThis clinical retrospective study used 4386-slice computed tomography (CT) images and labels from a training cohort (502 patients with colorectal cancer [CRC] from November 2005 to December 2010) to train the DLLD for detecting liver metastasis, and used CT images of a validation cohort (40 patients with 99 liver metastatic lesions and 45 patients without liver metastasis from January 2011 to December 2011) for comparing the performance of the DLLD with that of readers (three abdominal radiologists and three radiology residents). For per-lesion binary classification, the sensitivity and false positives per patient were measured.ResultsA total of 85 patients with CRC were included in the validation cohort. In the comparison based on per-lesion binary classification, the sensitivity of DLLD (81.82%, [81/99]) was comparable to that of abdominal radiologists (80.81%, p = 0.80) and radiology residents (79.46%, p = 0.57). However, the false positives per patient with DLLD (1.330) was higher than that of abdominal radiologists (0.357, p < 0.001) and radiology residents (0.667, p < 0.001).ConclusionDLLD showed a sensitivity comparable to that of radiologists when detecting liver metastasis in patients initially diagnosed with CRC. However, the false positives of DLLD were higher than those of radiologists. Therefore, DLLD could serve as an assistant tool for detecting liver metastasis instead of a standalone diagnostic tool.     

Variation in Radiologists’ Follow-Up Imaging Recommendations for Small Cystic Pancreatic Lesions

ObjectiveThis study aimed to determine the incidence, identify imaging and patient factors, and measure individual radiologist variation associated with follow-up recommendations for small focal cystic pancreatic lesions (FCPLs), a common incidental imaging finding.MethodsThis institutional review board–approved retrospective study analyzed 146,709 reports from abdominal CTs and MRIs performed in a large academic hospital from July 1, 2016, to June 30, 2018. A trained natural language processing tool identified 4,345 reports with FCPLs, which were manually reviewed to identify those containing one or more <1.5-cm pancreatic cysts. For these patients, patient, lesion, and radiologist features and follow-up recommendations for FCPL were extracted. A nonlinear random-effects model estimated degree of variation in follow-up recommendations across radiologists at department and division levels.ResultsOf 2,872 reports with FCPLs < 1.5 cm, 708 (24.7%) had FCPL-related follow-up recommendations. Average patient age was 67 years (SD ± 11). In all, 1,721 (60.0%) reports were for female patients; 59.3% of patients had only one cyst. In multivariable analysis, older patients had slightly lower follow-up recommendation rates (odds ratio [OR]: 0.98 [0.98-1.00] per additional year), and lesions associated with main duct dilatation and septation were more likely to have a follow-up recommendation (ORs: 1.93 [1.11-3.36] and 2.88 [1.89-4.38], respectively). Radiologist years in practice (P = .51), trainee presence (P = .21), and radiologist gender (P = .52) were not associated with increased follow-up recommendations. There was significant interradiologist variation in the Abdominal Imaging Division (P = .04), but not in Emergency Radiology (P = .31) or Cancer Imaging Divisions (P = .29).DiscussionInterradiologist variation significantly contributes to variability in follow-up imaging recommendations for FCPLs.