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.     

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.     

Lack of Timely Follow-Up of Abnormal Imaging Results and Radiologists’ Recommendations

PurposeAbnormal imaging results may not always lead to timely follow-up. We tested whether certain aspects of communication in radiology reports influence the response of the referring providers, and hence follow-up on abnormal findings.MethodsWe focused on 2 communication-related items that we hypothesized could affect follow-up: expressions of doubt in the radiology report, and recommendations for further imaging. After institutional review board approval, we conducted a retrospective review of 250 outpatient radiology reports from a multispecialty ambulatory clinic of a tertiary-care Veterans Affairs facility. The selected studies included 92 cases confirmed to lack timely follow-up (ie, further tests or consultations, treatment, and/or communication to the patient within 4 weeks), as determined in a previous study. An additional 158 cases with documented timely follow-up served as controls. Doubt in the narrative was measured by the presence of key phrases (eg, “unable to exclude,” “cannot exclude,” “cannot rule out,” “possibly,” and “unlikely”), in the absence of which we used reviewer interpretation. A physician blinded to follow-up outcomes collected the data.ResultsPatients whose reports contained recommendations for further imaging were more likely to have been lost to follow-up at 4 weeks compared with patients without such recommendations (P = .01). Language in the report suggestive of doubt did not affect the timeliness of follow-up (P = .59).ConclusionsAbnormal imaging results with recommendations for additional imaging may be more vulnerable to lack of timely follow-up. Additional safeguards, such as tracking systems, should be developed to prevent failure to follow up on such results.     

Development of lumbar spine MRI referrals vetting models using machine learning and deep learning algorithms: Comparison models vs healthcare professionals

IntroductionReferrals vetting is a necessary daily task to ensure the appropriateness of radiology referrals. Vetting requires extensive clinical knowledge and may challenge those responsible. This study aims to develop AI models to automate the vetting process and to compare their performance with healthcare professionals.Methods1020 lumbar spine MRI referrals were collected retrospectively from two Irish hospitals. Three expert MRI radiographers classified the referrals into indicated or not indicated for scanning based on iRefer guidelines. The reference label for each referral was assigned based on the majority voting. The corpus was divided into two datasets, one for the models' development with 920 referrals, and one included 100 referrals used as a held-out for the final comparison of the AI models versus national and international MRI radiographers. Three traditional models were developed: SVM, LR, RF, and two deep neural models, including CNN and Bi-LSTM. For the traditional models, four vectorisation techniques applied: BoW, bigrams, trigrams, and TF-IDF. A textual data augmentation technique was applied to investigate the influence of data augmentation on the models' performances.ResultsRF with BoW achieved the highest AUC reaching 0.99. CNN model outperformed Bi-LSTM with AUC = 0.98. With the augmented dataset, the performance significantly improved with an increase in F1 scores ranging from 1% to 7%. All models outperformed the national and international radiographers when compared on the hold-out dataset.ConclusionThe models assigned the referrals' appropriateness with higher accuracies than the national and international radiographers. Applying data augmentation significantly improved the models' performances.Implications for practiceThe outcomes suggest that the use of AI for checking referrals' eligibility could serve as a supporting tool to improve the referrals' management in radiology departments.     

Use of Machine Learning to Identify Follow-Up Recommendations in Radiology Reports

Purpose

The aims of this study were to assess follow-up recommendations in radiology reports, develop and assess traditional machine learning (TML) and deep learning (DL) models in identifying follow-up, and benchmark them against a natural language processing (NLP) system.

A Standardized Radiology Template Improves Incidental Adrenal Mass Follow-Up: A Prospective Effectiveness and Implementation Study

PurposeIncidental adrenal masses (IAMs) are common but rarely evaluated. To improve this, we developed a standardized radiology report recommendation template and investigated its implementation and effectiveness.MethodsWe prospectively studied implementation of a standardized IAM reporting template as part of an ongoing quality improvement initiative, which also included primary care provider (PCP) notifications and a straightforward clinical algorithm. Data were obtained via medical record review and a survey of radiologists. Outcomes included template adoption rates and acceptability (implementation measures), as well as the proportion of patients evaluated and time to follow-up (effectiveness outcomes).ResultsOf 4,995 imaging studies, 200 (4.0%) detected a new IAM. The standardized template was used in 54 reports (27.0%). All radiologists surveyed were aware of the template, and 91% affirmed that standardized recommendations are useful. Patients whose reports included the template were more likely to have PCP follow-up after IAM discovery compared with those with no template (53.7% versus 36.3%, P = .03). After adjusting for sex, current or prior malignancy, and provider ordering the initial imaging (PCP, other outpatient provider, or emergency department or inpatient provider), odds of PCP follow-up remained 2.0 times higher (95% confidence interval 1.02-3.9). Patients whose reports included the template had a shorter time to PCP follow-up (log-rank P = .018). PCPs ultimately placed orders for biochemical testing (35.2% versus 18.5%, P = .01), follow-up imaging (40.7% versus 23.3%, P = .02), and specialist referral (22.2% versus 4.8%, P < .01) for a higher proportion of patients who received the template compared with those who did not.ConclusionsUse of a standardized template to communicate IAM recommendations was associated with improved IAM evaluation. Our template demonstrated high acceptability, but additional strategies are necessary to optimize adoption.     

Comparing Artificial Intelligence Approaches to Retrieve Clinical Reports Documenting Implantable Devices Posing MRI Safety Risks

ObjectiveAssess sensitivity, specificity, and accuracy of two approaches to identify patients with implantable devices that pose safety risks for MRI—an expert-derived approach and an ontology-derived natural language processing (NLP). Determine the proportion of clinical data that identify these implantable devices.MethodsThis Institutional Review Board–approved retrospective study was performed at a 793-bed academic hospital. The expert-derived approach used an open-source software with a list of curated terms to query for implantable devices posing high safety risk (“MRI-Red”) in patients undergoing MRI. The ontology-derived approach used an NLP system with terms mapped to Systematized Nomenclature of Medicine—Clinical Terms. Queries were performed in three clinical data types—25,000 radiology reports, 174,769 emergency department (ED) notes, and 41,085 other clinical reports (eg, cardiology, operating room, physician notes, radiology reports, pathology reports, patient letters). Sensitivity, specificity, and accuracy of both methods against manual review of a randomly sampled 465 reports were assessed and tested for significant differences between expert-derived and ontology-derived approaches using t test.ResultsAccuracy, sensitivity, and specificity of expert-versus ontology-derived approaches were similar (0.83 versus 0.91, P = .080; 0.88 versus 0.96, P = .178; 0.82 versus 0.92, P = .110). The proportion of radiology reports, ED notes, and other clinical reports retrieved containing implantable devices with high safety risks for MRI ranged from 1.47% to 1.88%.DiscussionArtificial intelligence approaches such as expert-driven NLP and ontology-driven NLP have similar accuracy in identifying patients with implantable devices that pose high safety risks for MRI.     

Asymptomatic Abdominal Aortic Aneurysm: Standardizing Reporting Recommendations at a Large Multistate Radiology Practice

ObjectiveAlthough often asymptomatic at initial diagnosis, abdominal aortic aneurysms (AAAs) require careful surveillance to prevent rupture, with rupture-associated mortality rates as high as 90%. The purpose of this study was to explore if a performance improvement initiative implemented across a large radiology practice successfully increased inclusion of best practice recommendations (BPRs) within the radiology report across the practice.MethodsAfter BPRs for asymptomatic AAA surveillance were developed, a structured reporting macro for follow-up recommendation was integrated into dictation software. Following a training period, inclusion of recommendations within the radiology report was monitored across 345 facilities within the practice. Performance was reported on scorecards distributed monthly. To measure practice improvement, inclusion of appropriate recommendation in radiology reports postimplementation was compared with pre-implementation data.ResultsDuring the period before AAA BPRs implementation, from 64,090 consecutive cross-sectional radiology reports reviewed during a 6-month period, 855 incidental AAAs (1.3%) were identified, with 783 aneurysms measuring 2.6 to 5.4 cm requiring imaging surveillance; only 17 (2.1%) included follow-up recommendations within the radiology report. Postimplementation, 2,641 of 148,807 cross-sectional imaging studies were positive for 2.6- to 5.4-cm AAAs requiring further management; 1,533 (58.0%) of these radiology reports included follow-up imaging recommendations (97.0% of which followed our AAA BPRs).DiscussionQuality improvement initiatives to develop BPRs for AAA surveillance and include these recommendations within the radiology report can be successfully implemented across large practices and are imperative to ensure imaging surveillance and avert AAA rupture.     

Impact on Quality When Pediatric Urgent Care Centers Are Staffed With Radiology Technologists

PurposeThe proliferation of pediatric urgent care centers has increased the need for diagnostic imaging support, but the impact of employing radiology technologists at these centers is not known. The purpose of this study was to evaluate radiographic impact and quality at urgent care centers with and without radiology technologists.MethodsA retrospective case-control study was conducted comparing 235 radiographic examinations (study) performed without and 83 examinations (control) performed with a radiology technologist at the authors’ pediatric urgent care centers. Studies were evaluated for quality using a five-point, Likert-type scale (1 = poor, 5 = best) regarding field of view, presentation, and orthogonal view orientation. Studies were also evaluated for the incidence of positive results, need for repeat imaging, and discrepancies between initial study and follow-up.ResultsImaging quality comparisons between study and control groups were statistically different for field of view (3.98 versus 4.29, P = .014), presentation (4.39 versus 4.51, P = .045), and orthogonal view orientation (4.45 versus 4.69, P = .033). The incidence of repeat imaging was similar (4.7% versus 2.4%, P = 0.526), as well as the discrepancy rates (3.4 versus 2.4%, P = 1.00). The incidence of abnormal radiographic findings for the study and control groups was similar (40.9% versus 34.9%, P = .363).ConclusionsRadiography is an important triage tool at pediatric urgent care centers. It is imperative to have optimal radiographic imaging for accurate diagnosis, and imaging quality is improved when radiology technologists are available. If not feasible or cost prohibitive, it is important that physicians be given training opportunities to bridge the quality gap when using radiographic equipment and exposing children to radiation.     

Comparing Breast and Abdominal Subspecialists’ Follow-Up Recommendations for Incidental Liver Lesions on Breast MRI

PurposeThe aim of this study was to compare breast imaging subspecialists’ follow-up recommendations for incidental liver lesions (ILLs) on breast MRI with abdominal subspecialty radiologists’ opinions informed by best-practice recommendations.MethodsIn this retrospective study at an academic medical center, natural language processing identified reports with ILLs among 2,181 breast MRI studies completed in 2015. Electronic health record and radiology report reviews abstracted malignancy presence or absence, prior imaging, and breast subspecialists’ recommendations regarding ILLs for random sets of 30 patients: ILLs with follow-up recommendations, ILLs without recommendations, and without ILLs. Two abdominal radiologists evaluated MRI liver findings and offered follow-up recommendations in consensus. The primary outcome was agreement between breast and abdominal subspecialists in patients with ILL follow-up recommendations compared with those without (χ² analysis). Secondary outcomes were agreement between subspecialists when ILLs were reported and referring clinicians’ adherence to follow-up recommendations.ResultsILLs were identified in 11.3% of breast MRI reports (247 of 2,181); breast subspecialists made follow-up recommendations in 12% of them (30 of 247). Abdominal subspecialists agreed with breast subspecialists when ILLs required no follow-up (29 of 30 cases) but disagreed with 28 of 30 breast subspecialists’ follow-up recommendations (agreement proportion 29 of 30 versus 2 of 30, P < .0001). Subspecialists agreed in 93% of cases (28 of 30) when breast imagers reported no ILLs. Overall, 16 of 30 breast subspecialists’ follow-up recommendations were performed; ILLs were benign in 15.ConclusionsAbdominal subspecialists disagreed frequently with breast subspecialists regarding follow-up recommendations for ILLs on breast MRI. Abdominal subspecialty consultation or embedding liver imaging decision support in breast imaging reporting workflow may reduce unnecessary imaging and improve care. Improvement opportunities may exist in other cross-subspecialty interpretation workflows.     

Longitudinal Resilience and Burnout in Radiology Residents

PurposeThe aims of this study were to determine resilience levels of radiology residents at the start of radiology residency, investigate changes in resilience and burnout during residency, and assess the relationship between resilience and burnout among radiology residents.MethodsDiagnostic radiology residents were invited to participate in online surveys from 2016 to 2019. Resilience was assessed using the Connor–Davidson Resilience Scale. Burnout was assessed using the Maslach Burnout Inventory–Human Services Survey. For each data set, genders’ scores were compared using either analysis of variance or Kruskal–Wallis tests. Pearson correlation coefficients were calculated to explore the correlations between resilience and burnout.ResultsWomen and men had no statistically significant difference among baseline resilience scores (P = .78). However, there was a statistically significant overall decrease in resilience scores among women (P = .002). Baseline Maslach Burnout Inventory–Human Services Survey scores indicated that residents began residency without frequent symptoms of burnout. There was no statistically significant temporal change across subjects among burnout scores in any scale (P ≥ .09 for all) or between women and men (P ≥ .37 for all interactions). However, among women, there was a statistically significant difference in depersonalization scores during training (P = .009). Additionally, higher resilience scores were associated with a greater sense of personal achievement (r = .52) and less emotional exhaustion (r = −.56) and depersonalization (r = −.59).ConclusionsThe results of this study demonstrate that gender differences in resilience and burnout occur during radiology residency and that resilience has a protective effect against experiencing symptoms of burnout. Radiology residency programs should consider building longitudinal resilience for all trainees, especially women.     

Citation Impact of Collaboration in Radiology Research

PurposeTeam science involving multidisciplinary and multi-institutional collaboration is increasingly recognized as a means of strengthening the quality of scientific research. The aim of this study was to assess associations between various forms of collaboration and the citation impact of published radiology research.MethodsIn 2010, 876 original research articles published in Academic Radiology, the American Journal of Roentgenology, JACR, and Radiology were identified with at least one radiology-affiliated author. All articles were manually reviewed to extract features related to all authors’ disciplines and institutions. Citations to these articles through September 2016 were extracted from Thomson Reuters Web of Science.ResultsSubsequent journal article citation counts were significantly higher (P < .05) for original research articles with at least seven versus six or fewer authors (26.2 ± 30.8 versus 20.3 ± 23.1, respectively), with authors from multiple countries versus from a single country (32.3 ± 39.2 versus 22.0 ± 25.0, respectively), with rather than without a nonuniversity collaborator (28.7 ± 38.6 versus 22.4 ± 24.9, respectively), and with rather than without a nonclinical collaborator (26.5 ± 33.1 versus 21.9 ± 24.4, respectively). On multivariate regression analysis, the strongest independent predictors of the number of citations were authors from multiple countries (β = 9.14, P = .002), a nonuniversity collaborator (β = 4.80, P = .082), and at least seven authors (β = 4.11, P = .038).ConclusionsWith respect to subsequent journal article citations, various forms of collaboration are associated with greater scholarly impact of published radiology research. To enhance the relevance of their research, radiology investigators are encouraged to pursue collaboration across traditional disciplinary, institutional, and geographic boundaries.     

Radiofrequency Ablation,Cryoablation, and Microwave Ablation for T1a Renal Cell Carcinoma: A Comparative Evaluation of Therapeutic and Renal Function Outcomes

PurposeTo compare the therapeutic and renal function outcomes of radiofrequency (RF) ablation, cryoablation, and microwave (MW) ablation for treatment of T1a renal cell carcinoma (RCC).Materials and MethodsA retrospective assessment of 297 patients (mean age 72 years range 24–90 years) with biopsy-proven RCC treated with image-guided percutaneous thermal ablation was performed between October 2006 and December 2016. Mean tumor size was 2.4 cm; mean radius, exophytic/endophytic properties, nearness of tumor to collecting system or sinus, anterior/posterior, hilar tumor touching the main renal artery or vein, and location relative to polar lines; Preoperative Aspects and Dimensions Used for an Anatomical; and c-centrality scores were 6.0, 7.0, and 2.8, respectively. Assessments of adverse events, treatment efficacy, and therapeutic outcomes were performed among RF ablation, cryoablation, and MW ablation. The 2-year disease-free, metastatic-free, and cancer-specific survival rates were tabulated. Estimated glomerular filtration rate was used to assess for treatment related changes in renal function.ResultsA total of 297 T1aN0M0 biopsy-proven RCCs measuring 1.2–3.9 cm were treated with computed tomography–guided RF ablation (n = 244, 82%), cryoablation (n = 26, 9%), and MW ablation (n = 27, 9%). There were no significant differences in patient demographics among the 3 groups (P = .09). Technical success rates were similar among the 3 treatments (P = .33). Primary efficacy at 1 month postablation was more likely to be achieved with RF ablation and MW ablation than with cryoablation. At 2 years’ follow-up, there was no local recurrence, metastatic progression, or RCC-related death observed in the 3 groups. There was no significant change in estimated glomerular filtration rate among the 3 ablation groups compared with baseline at 2-year follow-up (P = .71).ConclusionRF ablation, cryoablation, and MW ablation are equivalent at 2 years for treatment of T1a RCC for therapeutic outcome, stability of renal function, and low adverse event rate.     

The energetic cost of gait retraining: A pilot study of the acute effect

ObjectiveTo investigate the acute effect of gait retraining aimed at reducing tibial peak positive acceleration (PPA) on energetic cost (VO₂).DesignIntervention with a pre/post-test design.SettingUniversity biomechanics laboratory.Participants12 healthy male runners (23.4 ± 5.3 years, 179.7 ± 4.3 cm, 75.6 ± 9.2 kg).Main outcome measuresTibial PPA and oxygen consumption (VO₂) were measured after a five minute baseline run and at the end of a gait retraining session aimed at minimizing tibial PPA.ResultsTibial PPA significantly decreased between baseline and after gait retraining (32.6%, p = 0.007). VO₂ significantly increased between the two time periods (9.3%, p = 0.008). There was no correlation between change in tibial PPA and change in VO₂ (p = 0.956, r = 0.018).ConclusionPractitioners who aim to reduce injury risk by minimizing tibial PPA in runners need to consider the possible acute effect on performance as a result of changes in VO₂. Further investigation is warranted to understand the energetic cost of different kinematic strategies used by individuals.     

Follow-up Recommendation Rates Associated With Spectral Detector Dual-Energy CT of the Abdomen and Pelvis: A Retrospective Comparison to Single-Energy CT

BackgroundDual-energy CT image sets have many applications in abdominopelvic imaging but no demonstrated clinical effect.PurposeTo determine the effect of dual-energy CT iodine maps on abdominopelvic imaging follow-up recommendation rates.Materials and MethodsRetrospective study of abdominopelvic CTs acquired from April 2017 through June 2018. CT reports were analyzed for radiologic follow-up recommendation and follow-up recommendation reason. Follow-up MRI reports were analyzed for benign or nonbenign diagnosis. CT scans with iodine maps (CTIMs) and conventional CT scans (CCTs) subgroups were compared using χ² testing.ResultsIn all, 3,221 abdominopelvic CT scans of 2,401 patients (1,326 men, 1,075 women, mean age 54.1 years) were analyzed; 1,423 were CTIMs and 1,798 were CCTs. Follow-up recommendation rates were not significantly different for CTIMs and CCTs (19.5% and 21.4%, respectively, P = .19). Follow-up recommendations because of incomplete diagnosis were significantly lower in CTIMs (9.1%) than in CCTs (11.9%, P = .01). Follow-up recommendations for MRI and PET/CT were significantly lower in CTIMs (9.6%) than CCTs (13.0%, P = .003). Follow-up MRI outcomes (n = 111) were not different between CTIMs (61.2% benign) and CCTs (59.6%, P = .87).ConclusionDual-energy CT iodine maps are associated with decreased follow-up examinations because of incomplete diagnosis and decreased recommendations for follow-up MRI, suggesting that abdominopelvic iodine maps may benefit patient care and decrease institutional cost.     

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.     

Endovascular Venous Stenosis and Thrombosis Large Animal Model: Angiographic,Histological, and Biomechanical Characterizations

PurposeTo characterize an ovine endovascular radiofrequency (RF) ablation-based venous stenosis and thrombosis model for studying venous biomechanics and response to intervention.Materials and MethodsUnilateral short-segment (n = 2) or long-segment (n = 6) iliac vein stenoses were created in 8 adult sheep using an endovenous RF ablation technique. Angiographic assessment was performed at baseline, immediately after venous stenosis creation, and after 2-week (n = 6) or 3-month (n = 2) survival. Stenosed iliac veins and the contralateral healthy controls were harvested for histological and biomechanical assessment.ResultsAt follow-up, the short-segment RF ablation group showed stable stenosis without occlusion. The long-segment group showed complete venous occlusion/thrombosis with the formation of collateral veins. Stenosed veins showed significant wall thickening (0.28 vs 0.16 mm, P = .0175) and confluent collagen deposition compared with the healthy controls. Subacute nonadherent thrombi were apparent at 2 weeks, which were replaced by fibrous luminal obliteration with channels of recanalization at 3 months. Stenosed veins demonstrated increased longitudinal stiffness (448.5 ± 5.4 vs 314.6 ± 1.5 kPa, P < .0001) and decreased circumferential stiffness (140.8 ± 2.6 vs 246.0 ± 1.6 kPa, P < .0001) compared with the healthy controls.ConclusionEndovenous RF ablation is a reliable technique for creating venous stenosis and thrombosis in a large animal model with histological and biomechanical attributes similar to those seen in humans. This platform can facilitate understanding of venous biomechanics and testing of venous-specific devices and interventions.     

Implementation and Impact of a Comprehensive Radiology Report Categorization System on Communication of Important Results

PurposeEffective communication of important imaging results is critical to patient care but difficult to accomplish efficiently. To improve communication at their institution, the authors introduced a radiology report categorization system (RADCAT) that organizes diagnostic imaging reports and uses automated communication systems. The study objectives were to (1) describe RADCAT’s design, (2) evaluate its implementation for appropriate imaging, and (3) evaluate the communication of important, nonurgent results with recommended follow-up.MethodsThis retrospective study was performed in a multihospital adult and pediatric tertiary referral academic health system. The intervention, a radiology report categorization system with five levels of acuity and IT-supported communication workflows, was globally implemented in November 2017. The primary outcomes were the successful implementation of RADCAT to appropriate diagnostic imaging reports and the successful communication of important, nonurgent results with recommended follow-up to ordering providers and patients by the radiology quality assurance team.ResultsOver 18 months after implementation, 740,625 radiology reports were categorized under the RADCAT system, with 42%, 28%, and 30% from the emergency department, inpatient, and outpatient settings, respectively. A random selection of 100 studies from the 23,718 total reports without RADCAT categorization identified 4 diagnostic radiology reports that erroneously lacked RADCAT grading. In 2019, of the 38,701 studies with nonurgent imaging follow-up recommendations, 38,692 (nearly 100.0%) were successfully communicated to providers or patients on the basis of quality assurance data.ConclusionsA comprehensive radiology report categorization system was successfully implemented across a multihospital adult and pediatric health system, demonstrating reliable communication of imaging results with recommendations for nonacute imaging follow-up.     

Patient and Provider Feedback for Radiology Reports: Implementation of a Quality Improvement Project in a Multi-Institutional Setting

BackgroundRadiology does not routinely solicit feedback on radiology reports. The aim of the study is to report the feasibility and initial results of a multi-institutional quality improvement project implementing patient and provider feedback for radiology reports.MethodsA HIPAA-compliant, institutional review board–waived quality improvement effort at two institutions obtaining patient and provider feedback for radiology reports was implemented from January 2018 to May 2020.InterventionA two-question survey (quantitative review and open text box feedback) was embedded into the electronic health records for patients and providers. Text-based feedback was evaluated, and patterns of feedback were categorized: thoroughness of reports, error in reports, timeliness of reports, access to reports, desire for patient summary, and desire for key images. We performed the χ² test for categorical variables. P < .05 was considered significant.ResultsOf 367 responses, patients provided 219 of 367 (60%), and providers provided 148 of 367 (40%) of the feedback. A higher proportion of patients reported satisfaction with reports (76% versus 65%, P = .023) and provided more feedback compared with providers (71% versus 50%, P < .0001). Both patients and providers commented on the thoroughness of reports (12% of patients versus 9% of providers) and errors in reports (8% of patients and 9% of providers). Patients disproportionately commented on timeliness of reports (11%) and access to the reports (6%) compared with providers (3% each). In addition, 7% of patients expressed a desire for patient summaries.ConclusionReport-specific patient and provider feedback demonstrate the feasibility of embedding surveys into electronic medical records. Up to 9% of the feedback addressed an error in reports.