RESUMEN

BACKGROUND. Examination protocoling is a noninterpretive task that increases radiologists' workload and can cause workflow inefficiencies. OBJECTIVE. The purpose of this study was to evaluate effects of an automated CT protocoling system on examination process times and protocol error rates. METHODS. This retrospective study included 317,597 CT examinations (mean age, 61.8 ± 18.1 [SD] years; male, 161,125; female, 156,447; unspecified sex, 25) from July 2020 to June 2022. A rules-based automated protocoling system was implemented institution-wide; the system evaluated all CT orders in the EHR and assigned a protocol or directed the order for manual radiologist protocoling. The study period comprised pilot (July 2020 to December 2020), implementation (January 2021 to December 2021), and postimplementation (January 2022 to June 2022) phases. Proportions of automatically protocoled examinations were summarized. Process times were recorded. Protocol error rates were assessed by counts of quality improvement (QI) reports and examination recalls and comparison with retrospectively assigned protocols in 450 randomly selected examinations. RESULTS. Frequency of automatic protocoling was 19,366/70,780 (27.4%), 68,875/163,068 (42.2%), and 54,045/83,749 (64.5%) in pilot, implementation, and postimplementation phases, respectively (p < .001). Mean (± SD) times from order entry to protocol assignment for automatically and manually protocoled examinations for emergency department examinations were 0.2 ± 18.2 and 2.1 ± 69.7 hours, respectively; mean inpatient examination times were 0.5 ± 50.0 and 3.5 ± 105.5 hours; and mean outpatient examination times were 361.7 ± 1165.5 and 1289.9 ± 2050.9 hours (all p < .001). Mean (± SD) times from order entry to examination completion for automatically and manually protocoled examinations for emergency department examinations were 2.6 ± 38.6 and 4.2 ± 73.0 hours, respectively (p < .001); for inpatient examinations were 6.3 ± 74.6 and 8.7 ± 109.3 hours (p = .001); and for outpatient examinations were 1367.2 ± 1795.8 and 1471.8 ± 2118.3 hours (p < .001). In the three phases, there were three, 19, and 25 QI reports and zero, one, and three recalls, respectively, for automatically protocoled examinations, versus nine, 19, and five QI reports and one, seven, and zero recalls for manually protocoled examinations. Retrospectively assigned protocols were concordant with 212/214 (99.1%) of automatically protocoled versus 233/236 (98.7%) of manually protocoled examinations. CONCLUSION. The automated protocoling system substantially reduced radiologists' protocoling workload and decreased times from order entry to protocol assignment and examination completion; protocol errors and recalls were infrequent. CLINICAL IMPACT. The system represents a solution for reducing radiologists' time spent performing noninterpretive tasks and improving care efficiency.

Asunto(s)

RESUMEN

PURPOSE: To 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. METHODS: A 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. RESULTS: A 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. CONCLUSION: The implementation of a semistructured electronic application for adverse contrast reaction reporting significantly increased radiologist documentation rate and completeness of the documentation.

Asunto(s)

RESUMEN

OBJECTIVE: To assess the impact of using a computer-assisted reporting and decision support (CAR/DS) tool at the radiologist point-of-care on ordering provider compliance with recommendations for adrenal incidentaloma workup. METHOD: Abdominal CT reports describing adrenal incidentalomas (2014 - 2016) were retrospectively extracted from the radiology database. Exclusion criteria were history of cancer, suspected functioning adrenal tumor, dominant nodule size < 1 cm or ≥ 4 cm, myelolipomas, cysts, and hematomas. Multivariable logistic regression models were employed to predict follow-up imaging (FUI) and hormonal screening orders as a function of patient age and sex, nodule size, and CAR/DS use. CAR/DS reports were compared to conventional reports regarding ordering provider compliance with, frequency, and completeness of, guideline-warranted recommendations for FUI and hormonal screening of adrenal incidentalomas using Chi-square test. RESULT: Of 174 patients (mean age 62.4; 51.1% women) with adrenal incidentalomas, 62% (108/174) received CAR/DS-based recommendations versus 38% (66/174) unassisted recommendations. CAR/DS use was an independent predictor of provider compliance both with FUI (Odds Ratio [OR]=2.47, p = 0.02) and hormonal screening (OR=2.38, p = 0.04). CAR/DS reports recommended FUI (97.2%,105/108) and hormonal screening (87.0%,94/108) more often than conventional reports (respectively, 69.7% [46/66], 3.0% [2/66], both p <0.0001). CAR/DS recommendations more frequently included instructions for FUI time, protocol, and modality than conventional reports (all p <0.001). CONCLUSION: Ordering providers were at least twice as likely to comply with report recommendations for FUI and hormonal evaluation of adrenal incidentalomas generated using CAR/DS versus unassisted reporting. CAR/DS-directed recommendations were more adherent to guidelines than those generated without.

Asunto(s)

RESUMEN

The radiology reporting process is beginning to incorporate structured, semantically labeled data. Tools based on artificial intelligence technologies using a structured reporting context can assist with internal report consistency and longitudinal tracking. To-do lists of relevant issues could be assembled by artificial intelligence tools, incorporating components of the patient's history. Radiologists will review and select artificial intelligence-generated and other data to be transmitted to the electronic health record and generate feedback for ongoing improvement of artificial intelligence tools. These technologies should make reports more valuable by making reports more accessible and better able to integrate into care pathways.

Asunto(s)

Asunto(s)

Asunto(s)

RESUMEN

PURPOSE: During the COVID-19 pandemic, emergency department (ED) volumes have fluctuated. We hypothesized that natural language processing (NLP) models could quantify changes in detection of acute abdominal pathology (acute appendicitis (AA), acute diverticulitis (AD), or bowel obstruction (BO)) on CT reports. METHODS: This retrospective study included 22,182 radiology reports from CT abdomen/pelvis studies performed at an urban ED between January 1, 2018 to August 14, 2020. Using a subset of 2448 manually annotated reports, we trained random forest NLP models to classify the presence of AA, AD, and BO in report impressions. Performance was assessed using 5-fold cross validation. The NLP classifiers were then applied to all reports. RESULTS: The NLP classifiers for AA, AD, and BO demonstrated cross-validation classification accuracies between 0.97 and 0.99 and F1-scores between 0.86 and 0.91. When applied to all CT reports, the estimated numbers of AA, AD, and BO cases decreased 43-57% in April 2020 (first regional peak of COVID-19 cases) compared to 2018-2019. However, the number of abdominal pathologies detected rebounded in May-July 2020, with increases above historical averages for AD. The proportions of CT studies with these pathologies did not significantly increase during the pandemic period. CONCLUSION: Dramatic decreases in numbers of acute abdominal pathologies detected by ED CT studies were observed early on during the COVID-19 pandemic, though these numbers rapidly rebounded. The proportions of CT cases with these pathologies did not increase, which suggests patients deferred care during the first pandemic peak. NLP can help automatically track findings in ED radiology reporting.

Asunto(s)

RESUMEN

PURPOSE: Recent advances in structured reporting are providing an opportunity to enhance cancer imaging assessment to drive value-based care and improve patient safety. METHODS: The computer-assisted reporting and decision support (CAR/DS) framework has been developed to enable systematic ingestion of guidelines as clinical decision structured reporting tools embedded within the radiologist's workflow. RESULTS: CAR/DS tools can reduce the radiology reporting variability and increase compliance with clinical guidelines. The lung cancer use-case is used to describe various scenarios of a cancer imaging structured reporting pathway, including incidental findings, screening, staging, and restaging or continued care. Various aspects of these tools are also described using cancer-related examples for different imaging modalities and applications such as calculators. Such systems can leverage artificial intelligence (AI) algorithms to assist with the generation of structured reports and there are opportunities for new AI applications to be created using the structured data associated with CAR/DS tools. CONCLUSION: These AI-enabled systems are starting to allow information from multiple sources to be integrated and inserted into structured reports to drive improvements in clinical decision support and patient care.

Asunto(s)

RESUMEN

RATIONALE AND OBJECTIVES: Radiographic findings of COVID-19 pneumonia can be used for patient risk stratification; however, radiologist reporting of disease severity is inconsistent on chest radiographs (CXRs). We aimed to see if an artificial intelligence (AI) system could help improve radiologist interrater agreement. MATERIALS AND METHODS: We performed a retrospective multi-radiologist user study to evaluate the impact of an AI system, the PXS score model, on the grading of categorical COVID-19 lung disease severity on 154 chest radiographs into four ordinal grades (normal/minimal, mild, moderate, and severe). Four radiologists (two thoracic and two emergency radiologists) independently interpreted 154 CXRs from 154 unique patients with COVID-19 hospitalized at a large academic center, before and after using the AI system (median washout time interval was 16 days). Three different thoracic radiologists assessed the same 154 CXRs using an updated version of the AI system trained on more imaging data. Radiologist interrater agreement was evaluated using Cohen and Fleiss kappa where appropriate. The lung disease severity categories were associated with clinical outcomes using a previously published outcomes dataset using Fisher's exact test and Chi-square test for trend. RESULTS: Use of the AI system improved radiologist interrater agreement (Fleiss κ = 0.40 to 0.66, before and after use of the system). The Fleiss κ for three radiologists using the updated AI system was 0.74. Severity categories were significantly associated with subsequent intubation or death within 3 days. CONCLUSION: An AI system used at the time of CXR study interpretation can improve the interrater agreement of radiologists.

Asunto(s)

RESUMEN

Recent advances in artificial intelligence (AI) are providing an opportunity to enhance existing clinical decision support (CDS) tools to improve patient safety and drive value-based imaging. We discuss the advantages and potential applications that may be realized with the synergy between AI and CDS systems. From the perspective of both radiologist and ordering provider, CDS could be significantly empowered using AI. CDS enhanced by AI could reduce friction in radiology workflows and can aid AI developers to identify relevant imaging features their tools should be seeking to extract from images. Furthermore, these systems can generate structured data to be used as input to develop machine learning algorithms, which can drive downstream care pathways. For referring providers, an AI-enabled CDS solution could enable an evolution from existing imaging-centric CDS toward decision support that takes into account a holistic patient perspective. More intelligent CDS could suggest imaging examinations in highly complex clinical scenarios, assist on the identification of appropriate imaging opportunities at the health system level, suggest appropriate individualized screening, or aid health care providers to ensure continuity of care. AI has the potential to enable the next generation of CDS, improving patient care and enhancing providers' and radiologists' experience.

Asunto(s)

RESUMEN

Advances in machine learning in medical imaging are occurring at a rapid pace in research laboratories both at academic institutions and in industry. Important artificial intelligence (AI) tools for diagnostic imaging include algorithms for disease detection and classification, image optimization, radiation reduction, and workflow enhancement. Although advances in foundational research are occurring rapidly, translation to routine clinical practice has been slower. In August 2018, the National Institutes of Health assembled multiple relevant stakeholders at a public meeting to discuss the current state of knowledge, infrastructure gaps, and challenges to wider implementation. The conclusions of that meeting are summarized in two publications that identify and prioritize initiatives to accelerate foundational and translational research in AI for medical imaging. This publication summarizes key priorities for translational research developed at the workshop including: (1) creating structured AI use cases, defining and highlighting clinical challenges potentially solvable by AI; (2) establishing methods to encourage data sharing for training and testing AI algorithms to promote generalizability to widespread clinical practice and mitigate unintended bias; (3) establishing tools for validation and performance monitoring of AI algorithms to facilitate regulatory approval; and (4) developing standards and common data elements for seamless integration of AI tools into existing clinical workflows. An important goal of the resulting road map is to grow an ecosystem, facilitated by professional societies, industry, and government agencies, that will allow robust collaborations between practicing clinicians and AI researchers to advance foundational and translational research relevant to medical imaging.

Asunto(s)

RESUMEN

PURPOSE: To evaluate a new system for processing and performing inpatient STAT diagnostic imaging with respect to utilization and time-based performance metrics. MATERIALS AND METHODS: This HIPAA-compliant study had institutional review board approval; informed consent was not required. The radiology information system of a large academic medical center was queried for all inpatient diagnostic imaging exams performed and interpreted from August 1, 2010, to October 31, 2012. Using customized software, data were evaluated based on order priority (non-STAT or STAT) and exam modality with respect to exam volume and time-based performance metrics (time-to-performance and preliminary interpretation time). Data were compared over 3 periods: August 1, 2010, to October 31, 2010 (preimplementation period); November 1, 2010, to October 31, 2011 (year 1 postimplementation); and November 1, 2011, to October 31, 2012 (year 2 postimplementation). RESULTS: In the first year after implementation of the new STAT policy, the percentage of inpatient exams ordered STAT significantly decreased from 22.1% to 5.4% (P < 0.001). This represented a proportional decrease of 26% (CT), 16% (MRI), 20% (US), and 24% (radiographs) relative to pre-STAT policy levels. The median time-to-performance and median preliminary interpretation time significantly decreased for all modalities after implementation of the policy (P < 0.05 for all modalities), decreasing by an average of 104 and 162 minutes, respectively. These changes persisted throughout year 2 postimplementation. CONCLUSION: A new institutional system for handling inpatient STAT diagnostic imaging results in a decreased number of STAT exams ordered and improved time-based performance metrics, thereby increasing workflow efficiency.

Asunto(s)

RESUMEN

BACKGROUND: Lumbar spine magnetic resonance imaging is frequently said to be "overused" in the evaluation of low back pain, yet data concerning the extent of overuse and the potential harmful effects are lacking. PURPOSE: The objective of this study was to determine the proportion of examinations with a detectable impact on patient care (actionable outcomes). STUDY DESIGN: This is a retrospective cohort study. PATIENT SAMPLE: A total of 5,365 outpatient lumbar spine magnetic resonance (MR) examinations were conducted. OUTCOME MEASURES: Actionable outcomes included (1) findings leading to an intervention making use of anatomical information such as surgery; (2) new diagnoses of cancer, infection, or fracture; or (3) following known lumbar spine pathology. Potential harm was assessed by identifying examinations where suspicion of cancer or infection was raised but no positive diagnosis made. METHODS: A medical record aggregation/search system was used to identify lumbar spine MR examinations with positive outcome measures. Patient notes were examined to verify outcomes. A random sample was manually inspected to identify missed positive outcomes. RESULTS: The proportion of actionable lumbar spine magnetic resonance imaging was 13%, although 93% were appropriate according to the American College of Radiology guidelines. Of 36 suspected cases of cancer or infection, 81% were false positives. Further investigations were ordered on 59% of suspicious examinations, 86% of which were false positives. CONCLUSIONS: The proportion of lumbar spine MR examinations that inform management is small. The false-positive rate and the proportion of false positives involving further investigation are high. Further study to improve the efficiency of imaging is warranted.

Asunto(s)

RESUMEN

Radiology practice will be altered by the coming of artificial intelligence, and the process of learning in radiology will be similarly affected. In the short term, radiologists will need to understand the first wave of artificially intelligent tools, how they can help them improve their practice, and be able to effectively supervise their use. Radiology training programs will need to develop curricula to help trainees acquire the knowledge to carry out this new supervisory duty of radiologists. In the longer term, artificially intelligent software assistants could have a transformative effect on the training of residents and fellows, and offer new opportunities to bring learning into the ongoing practice of attending radiologists.

Asunto(s)

RESUMEN

PURPOSE: The aim of this study was to assess differences in interreader variability among radiologists after the implementation of a computer-assisted reporting (CAR) tool for the interpretation of degenerative disc disease on lumbar spine MRI. METHODS: Thirty lumbar spine MRI examinations were selected from the radiology database. Five fellowship-trained musculoskeletal radiologists evaluated each L4-L5 disc in a blinded fashion and reported the findings using a traditional free dictation approach. One month later, they reinterpreted the same discs using a web browser-based CAR tool in the same blinded fashion. The degrees of central canal stenosis, neural foraminal stenosis, and facet joint osteoarthritis; presence or absence of lateral recess stenosis; types of disc bulge or herniation; and herniation location using both methods were recorded. Percentage disagreement among the radiologists for each variable was calculated and compared using the Wilcoxon signed rank test. RESULTS: There was a statistically significant decrease among the five radiologists in percentage disagreement for neural foraminal stenosis (46% versus 35%, P = .0146) and facet joint osteoarthritis (45% and 22%, P < .0001) for reports created by free dictation compared with those created using the CAR tool. There was no statistically significant difference in interreader variability for the assessment of central canal stenosis, lateral recess effacement, disc herniation, disc bulge, or herniation location. CONCLUSIONS: Implementation of a CAR tool for the interpretation of degenerative changes on lumbar spine MRI decreases interreader variability in the assessment of neural foraminal stenosis and facet joint osteoarthritis.

Asunto(s)

RESUMEN

Decreasing unnecessary variation in radiology reporting and producing guideline-concordant reports is fundamental to radiology's success in value-based payment models and good for patient care. In this article, we present an open authoring system for point-of-care clinical decision support tools integrated into the radiologist reporting environment referred to as the computer-assisted reporting and decision support (CAR/DS) framework. The CAR/DS authoring system, described herein, includes: (1) a definition format for representing radiology clinical guidelines as structured, machine-readable Extensible Markup Language documents and (2) a user-friendly reference implementation to test the fidelity of the created definition files with the clinical guideline. The proposed definition format and reference implementation will enable content creators to develop CAR/DS tools that voice recognition software (VRS) vendors can use to extend the commercial tools currently in use. In making the definition format and reference implementation software freely available, we hope to empower individual radiologists, expert groups such as the ACR, and VRS vendors to develop a robust ecosystem of CAR/DS tools that can further improve the quality and efficiency of the patient care that our field provides. We hope that this initial effort can serve as the basis for a community-owned open standard for guideline definition that the imaging informatics and VRS vendor communities will embrace and strengthen. To this end, the ACR Assist™ initiative is intended to make the College's clinical content, including the Incidental Findings Committee White Papers, available for decision support tool creation based upon the herein described CAR/DS framework.

Asunto(s)

RESUMEN

Skeletal maturity progresses through discrete phases, a fact that is used routinely in pediatrics where bone age assessments (BAAs) are compared to chronological age in the evaluation of endocrine and metabolic disorders. While central to many disease evaluations, little has changed to improve the tedious process since its introduction in 1950. In this study, we propose a fully automated deep learning pipeline to segment a region of interest, standardize and preprocess input radiographs, and perform BAA. Our models use an ImageNet pretrained, fine-tuned convolutional neural network (CNN) to achieve 57.32 and 61.40% accuracies for the female and male cohorts on our held-out test images. Female test radiographs were assigned a BAA within 1 year 90.39% and within 2 years 98.11% of the time. Male test radiographs were assigned 94.18% within 1 year and 99.00% within 2 years. Using the input occlusion method, attention maps were created which reveal what features the trained model uses to perform BAA. These correspond to what human experts look at when manually performing BAA. Finally, the fully automated BAA system was deployed in the clinical environment as a decision supporting system for more accurate and efficient BAAs at much faster interpretation time (<2 s) than the conventional method.

Asunto(s)

RESUMEN

PURPOSE: We evaluated all PET/CTs acquired for patients without a primary diagnosis of colorectal cancer, and compared results for those who had subsequent colonoscopy within 6 months, to assess the accuracy of FDG PET/CT for detection of incidental pre-malignant polyps and malignant colon cancers. MATERIALS AND METHODS: Medical records of 9,545 patients who underwent F-18 FDG PET/CT studies over 3.5 years were retrospectively reviewed. Due to pre-existing diagnosis of colorectal cancer, 818 patients were excluded. Of the remainder, 157 patients had colonoscopy within 6 months (79 males; mean age 61). We divided the colon into 4 regions and compared PET/CT results for each region with colonoscopy and histopathologic findings. True positive lesions included colorectal cancer, villous adenoma, tubulovillous adenoma, tubular adenoma and serrated hyperplastic polyp/hyperplastic polyposis. RESULTS: Of 157 patients, 44 had incidental colonic uptake on PET/CT (28%). Of those, 25 had true positive (TP) uptake, yielding a 48% positive predictive value (PPV); 9% (4/44) were adenocarcinoma. There were 23 false positive (FP) lesions of which 4 were hyperplastic polyps, one was a juvenile polyp and 7 were explained by diverticulitis. Fifty eight patients had false negative PET scans but colonoscopy revealed true pre-malignant and malignant pathology, yielding 23% sensitivity. The specificity, negative predictive value (NPV) and accuracy were 96%, 90% and 87%, respectively. The average SUVmax values of TP, FP and FN lesions were 7.25, 6.11 and 2.76, respectively. There were no significant difference between SUVmax of TP lesions and FP lesions (p>0.95) but significantly higher than in FN lesions (p<0.001). The average size (by histopathology and colonoscopy) of TP lesions was 18.1 mm, statistically different from that of FN lesions which was 5.9 mm (p<0.001). Fifty-one percent of FN lesions were smaller than 5 mm (29/57) and 88% smaller than 10 mm (50/57). CONCLUSIONS: The high positive predictive value of incidental focal colonic FDG uptake of 48% for colonic neoplasia suggests that colonoscopy follow-up is warranted with this finding. We observed a low sensitivity of standardly acquired FDG-PET/CT for detecting small polyps, especially those less than 5 mm. Clinicians and radiologists should be aware of the high PPV of focal colonic uptake reflecting pre-malignant and malignant lesions, and the need for appropriate follow up.

Asunto(s)

RESUMEN

PURPOSE: The objective of this study was to evaluate the feasibility of the consensus-oriented group review (COGR) method of radiologist peer review within a large subspecialty imaging department. METHODS: This study was institutional review board approved and HIPAA compliant. Radiologist interpretations of CT, MRI, and ultrasound examinations at a large academic radiology department were subject to peer review using the COGR method from October 2011 through September 2013. Discordance rates and sources of discordance were evaluated on the basis of modality and division, with group differences compared using a χ(2) test. Potential associations between peer review outcomes and the time after the initiation of peer review or the number of radiologists participating in peer review were tested by linear regression analysis and the t test, respectively. RESULTS: A total of 11,222 studies reported by 83 radiologists were peer reviewed using COGR during the two-year study period. The average radiologist participated in 112 peer review conferences and had 3.3% of his or her available CT, MRI and ultrasound studies peer reviewed. The rate of discordance was 2.7% (95% confidence interval [CI], 2.4%-3.0%), with significant differences in discordance rates on the basis of division and modality. Discordance rates were highest for MR (3.4%; 95% CI, 2.8%-4.1%), followed by ultrasound (2.7%; 95% CI, 2.0%-3.4%) and CT (2.4%; 95% CI, 2.0%-2.8%). Missed findings were the most common overall cause for discordance (43.8%; 95% CI, 38.2%-49.4%), followed by interpretive errors (23.5%; 95% CI, 18.8%-28.3%), dictation errors (19.0%; 95% CI, 14.6%-23.4%), and recommendation (10.8%; 95% CI, 7.3%-14.3%). Discordant cases, compared with concordant cases, were associated with a significantly greater number of radiologists participating in the peer review process (5.9 vs 4.7 participating radiologists, P < .001) and were significantly more likely to lead to an addendum (62.9% vs 2.7%, P < .0001). CONCLUSIONS: COGR permits departments to collect highly contextualized peer review data to better elucidate sources of error in diagnostic imaging reports, while reviewing a sufficient case volume to comply with external standards for ongoing performance review.

Asunto(s)