Report Turnaround Time Research Articles

Improving access to outpatient computed tomography

Demand for diagnostic imaging services in the United States continues to rise, posing challenges for health systems to maintain efficient scheduling processes. This study documents a quality improvement initiative undertaken at our institution in response to a surge in demand for outpatient imaging during 2022, which led to a notable scheduling backlog. By October 2022, the average scheduling interval, defined as the time from order placement to scheduled examination date, had increased from 2 weeks to 6 weeks. The objective of this initiative was to reduce the scheduling interval from 6 weeks to 10 days by January 2023. Utilizing feedback from schedulers, technologists, and radiologists, several interventions were implemented. The impact of each intervention was monitored with a control chart with weekly appointment delays tracked as a balancing measure. Initially, examination slots were double-booked for a period of 4 weeks to address the backlog, resulting in a reduction of the scheduling interval to 12 days (72 % decrease). Subsequently, examination slot duration was shorted from 20 to 15 min and contrast protocols were standardized across all sites. These adjustments further decreased the interval to 7 days (41 % reduction) over the following 9 weeks. While staffing shift adjustments had no impact on the scheduling interval, the introduction of an extra CT scanner reduced the interval to 3 days (57 % decrease). These interventions resulted in a notable increase in examination volume, from a weekly average of 722 to 860 examinations (19 % increase), approximately an additional $1,612,000 in annual revenue. Importantly, there was no change in the average appointment delay, which remained at 15 min over the study period. These improvements were sustained across the subsequent months and received favorable subjective feedback from staff. While the initiative successfully addressed scheduling inefficiencies across our health system, the rise in examination volumes has led to an increased turnaround time for completed reports. Future directions for enhancing the outpatient scheduling process include expanding online scheduling platforms, implementing systems to assess imaging appropriateness, and developing urgency stratification to prioritize time-sensitive examinations.

Prospective Evaluation of Artificial Intelligence Triage of Incidental Pulmonary Emboli on Contrast-Enhanced CT Examinations of the Chest or Abdomen.

BACKGROUND. Artificial intelligence (AI) algorithms improved detection of incidental pulmonary embolism (IPE) on contrast-enhanced CT (CECT) examinations in retrospective studies; however, prospective validation studies are lacking. OBJECTIVE. The purpose of this study was to assess the effect on radiologists' real-world diagnostic performance and report turnaround times of a radiology department's clinical implementation of an AI triage system for detecting IPE on CECT examinations of the chest or abdomen. METHODS. This prospective single-center study included consecutive adult patients who underwent CECT of the chest or abdomen for reasons other than pulmonary embolism (PE) detection from May 12, 2021, to June 30, 2021 (phase 1), or from September 30, 2021, to December 4, 2021 (phase 2). Before phase 1, the radiology department installed a commercially available AI triage algorithm for IPE detection that automatically processed CT examinations and notified radiologists of positive results through an interactive floating widget. In phase 1, the widget was inactive, and radiologists interpreted examinations without AI assistance. In phase 2, the widget was activated, and radiologists interpreted examinations with AI assistance. A review process involving a panel of radiologists was implemented to establish the reference standard for the presence of IPE. Diagnostic performance and report turnaround times were compared using the Pearson chi-square test and Wilcoxon rank sum test, respectively. RESULTS. Phase 1 included 1467 examinations in 1434 patients (mean age, 53.8 ± 18.5 [SD] years; 753 men, 681 women); phase 2 included 3182 examinations in 2886 patients (mean age, 55.4 ± 18.2 years; 1520 men, 1366 women). The frequency of IPE was 1.4% (20/1467) in phase 1 and 1.6% (52/3182) in phase 2. Radiologists without AI, in comparison to radiologists with AI, showed significantly lower sensitivity (80.0% vs 96.2%, respectively; p = .03), without a significant difference in specificity (99.9% vs 99.9%, p = .58), for the detection of IPE. The mean report turnaround time for IPE-positive examinations was not significantly different between radiologists without AI and radiologists with AI (78.3 vs 74.6 minutes, p = .26). CONCLUSION. An AI triage system improved radiologists' sensitivity for IPE detection on CECT examinations of the chest or abdomen without significant change in report turnaround times. CLINICAL IMPACT. This prospective real-world study supports the use of AI assistance for maximizing IPE detection.

Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations.

Background: Retrospective studies evaluating artificial intelligence (AI) algorithms for intracranial hemorrhage (ICH) detection on noncontrast CT (NCCT) have shown promising results but lack prospective validation. Objective: To evaluate the impact on radiologists' real-world aggregate performance for ICH detection and report turnaround times for ICH-positive examinations of a radiology department's implementation of an AI triage and notification system for ICH detection on head NCCT examinations. Methods: This prospective single-center study included adult patients who underwent head NCCT examinations from May 12, 2021 to June 30, 2021 (phase 1) or September 30, 2021 to December 4, 2021 (phase 2). Before phase 1, the radiology department implemented a commercial AI triage system for ICH detection that processed head NCCT examinations and notified radiologists of positive results through a widget with a floating pop-up display. Examinations were interpreted by neuroradiologists or emergency radiologists, who evaluated examinations without and with AI assistance in phase 1 and phase 2, respectively. A panel of radiologists conducted a review process for all examinations with discordance between the radiology report and AI and a subset of remaining examinations, to establish the reference standard. Diagnostic performance and report turnaround times were compared using Pearson chi-square test and Wilcoxon rank-sum test, respectively. Bonferroni correction was used to account for five diagnostic performance metrics (adjusted significance threshold, .01 [α=.05/5]). Results: A total of 9954 examinations from 7371 patients (mean age, 54.8±19.8 years; 3773 female, 3598 male) were included. In phases 1 and 2, 19.8% (735/3716) and 21.9% (1368/6238) of examinations, respectively, were positive for ICH (P=.01). Radiologists without versus with AI showed no significant difference in accuracy (99.5% vs 99.2%), sensitivity (98.6% vs 98.9%), PPV (99.0% vs 99.7%), or NPV (99.7% vs 99.7%) (all P>.01); specificity was higher for radiologists without than with AI (99.8% vs 99.3%, respectively, P=.004). Mean report turnaround time for ICH-positive examinations was 147.1 minutes without AI versus 149.9 minutes with AI (P=.11). Conclusion: An AI triage system for ICH detection did not improve radiologists' diagnostic performance or report turnaround times. Clinical Impact: This large prospective real-world study does not support use of AI assistance for ICH detection.

Effects of night-float shifts on cognitive function among radiology residents

BackgroundMany radiology programs utilize a night-float system to mitigate the effects of fatigue, improve patient care, and provide faster report turnaround times. Prior studies have demonstrated an increase in discrepancy rates during night-float shifts.ObjectivesThis study was performed to examine the effects of night-float shift work on radiology resident cognition. We hypothesized that there would be diminished cognitive function on testing following night-float shifts when compared to testing following day shifts.MethodsDiagnostic radiology residents in their second to fifth years of residency at a single institution were recruited to participate in this pilot study. Cognitive function was evaluated using the Lumosity Neurocognitive Performance Tests (NCPT), standardized performance tests that provide real-time, objective measurements of cognitive function. Study participants completed the NCPT in 5 sessions following 5 consecutive day shifts to evaluate their baseline cognitive function. The tests were re-administered at the end of consecutive night-float shifts to assess for any changes. Sleep was objectively monitored using actigraphy devices worn around the wrist during all study weeks. Descriptive and summary statistics were performed.Results23 prospectively recruited diagnostic radiology residents working night-float shifts took a mean 13.6 (± 5.1) neurocognitive performance tests during the study period. There was a statistically significant decline in 2 of the 6 cognitive tests administered, signifying a decrease in attention, speed, and complex reasoning ability. Night-float shifts were significantly longer than the day shifts and associated with a significantly higher study volume and cross-sectional study volume. Fitbit data demonstrated that there were no significant differences in level of activity while awake. However, participants slept significantly longer during day shifts.ConclusionsA sample of 23 radiology residents working night-float shifts demonstrated declines in attention, speed, and complex reasoning ability following sequential administration of standardized neurocognitive performance tests. While the sample size is small, these findings demonstrate the potential deleterious effects of night-float shift work and provide evidence to support further inquiry into this phenomenon.

Abbreviated MRI in the evaluation of dizziness: report turnaround times and impact on length of stay compared to CT, CTA, and conventional MRI.

Neuroimaging is often used in the emergency department (ED) to evaluate for posterior circulation strokes in patients with dizziness, commonly with CT/CTA due to speed and availability. Although MRI offers more sensitive evaluation, it is less commonly used, in part due to slower turnaround times. We assess the potential for abbreviated MRI to improve reporting times and impact on length of stay (LOS) compared to conventional MRI (as well as CT/CTA) in the evaluation of acute dizziness. We performed a retrospective analysis of length of stay via LASSO regression for patients presenting to the ED with dizziness and discharged directly from the ED over 4 years (1/1/2018-12/31/2021), controlling for numerous patient-level and logistical factors. We additionally assessed turnaround time between order and final report for various imaging modalities. 14,204 patients were included in our analysis. Turnaround time for abbreviated MRI was significantly lower than for conventional MRI (4.40h vs. 6.14h, p < 0.001) with decreased impact on LOS (0.58h vs. 2.02h). Abbreviated MRI studies had longer turnaround time (4.40h vs. 1.41h, p < 0.001) and was associated with greater impact on ED LOS than non-contrast CT head (0.58h vs. 0.00h), however there was no significant difference in turnaround time compared to CTA head and neck (4.40h vs. 3.86h, p = 0.06) with similar effect on LOS (0.58h vs. 0.53h). Ordering both CTA and conventional MRI was associated with a greater-than-linear increase in LOS (additional 0.37h); the same trend was not seen combining CTA and abbreviated MRI (additional 0.00h). In the acute settings where MRI is available, abbreviated MRI protocols may improve turnaround times and LOS compared to conventional MRI protocols. Since recent guidelines recommend MRI over CT in the evaluation of dizziness, implementation of abbreviated MRI protocols has the potential to facilitate rapid access to preferred imaging, while minimizing impact on ED workflows.

Laboratory testing consolidation and total laboratory automation improves service efficiency and effectiveness: a study of a medical center in Taiwan.

Test consolidation and total laboratory automation (TLA) were implemented in a core laboratory with a high volume of specimens in a medical center in Taiwan to reduce the costs of laboratory services and improve laboratory workflow and performance. Using a retrospective research approach, 5 stat and 7 routine tests were used to analyze the in-laboratory to report turnaround time (IR-TAT). Mean, SD, medium, 90th percentile, outlier percentage of IR-TAT, full-time equivalents, productivity, tube touch moment (TTM), and financial impact were determined and compared pre- and post-TLA. The mean IR-TAT of overall stat chemical tests for inpatient and outpatient were 32.8% and 11.9% reductions, respectively. The productivity of each medical technologist increased by 32.4% per month, and there was a reduction of 5 medical technologists compared with the number required to complete the same tests before consolidation. The TTM of staff per year post-TLA decreased by 74.1% tube touches. The efficiency of laboratory services was improved by consolidation to the core laboratory along with TLA implementation coupled with logic rules such as delta-check and autoverification. Effectiveness was improved as measured by an increase in productivity, labor reduction, staff safety, and cost reduction.

Abstract 5177: Ex vivo assessment of cellular mass response predicts clinical efficacy in solid tumors

Abstract Introduction: Identifying personalized, efficacious therapies for cancer remains an urgent unmet need in oncology. While genomics-based biomarkers have demonstrated significant progress, they are not universally applicable, with most patients still treated using clinical guidelines. Experimental procedures: We have previously demonstrated broad clinical applicability of a functional precision medicine (FPM) workflow that incorporates high-resolution measurements of single-cell mass changes in response to drugs. As a highly integrative biomarker of cellular state, mass change serves as a rapid and mechanism agnostic readout of drug response, demonstrating an ability to detect signal from over 100 different cytotoxic and targeted therapies within 24 hours of treatment ex vivo. As a single-cell assay that requires as few as 10,000 cells to assess drug response, this method does not require any ex vivo culture for cell expansion and is compatible with a range of clinically relevant tissue specimen formats. Together, these features have enabled this mass response framework to be implemented in a CLIA-certified laboratory with a reporting turnaround time of just two days. Summary of the new, unpublished data: Having previously shown that mass response testing is compatible with various solid tumor specimen formats such as malignant fluids, core biopsies and fine needle aspirates, here we present preliminary results that demonstrate compatibility with surgically resected tissue specimens. Specifically, we demonstrate that mass response testing results correlate with clinical response across of broad array of solid tumors. In our cohort of 24 patients, we found that mass response measurements correlated with clinical response to therapy with an accuracy of 83% (OR=19.66, P=0.003). Within this group, we also found clear examples of how mass response testing can serve as a valuable complement to existing genomic approaches to guide therapy. Importantly, we demonstrate both concordant and discrepant results using small molecule inhibitors in the setting of known biomarkers of response, highlighting the need for functional testing in precision cancer medicine. Conclusions: These results support that mass response testing is feasible and broadly applicable to solid tumor malignancies and may serve as a valuable complementary readout for informing therapeutic selection for cancer patients. Citation Format: Robert Kimmerling, Mark Stevens, Selim Olcum, Madeleine Vacha, Rachel LaBella, Katie Katsis, Reginald Aikens, Cathleen Hannah, Audrey Guo, Juanita Fujii, Zayna Shaheen, Srividya Sundaresan, Ashley Rainey, Andrew M. Blakely, Jonathan Hernandez, Anobel Tamrazi, Clifford Reid. Ex vivo assessment of cellular mass response predicts clinical efficacy in solid tumors [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 5177.

Adoption, orchestration, and deployment of artificial intelligence within the National Health Service—facilitators and barriers: an expert roundtable discussion

Abstract Clinical care, workflow, and patient outcomes within National Health Service (NHS) radiology services will potentially benefit significantly in coming years with the integration of artificial intelligence (AI) into various specialty areas. This article summarizes an expert roundtable discussion, convened by the British Institute of Radiology, comprised experts from clinical, NHS management and industry backgrounds. Facilitators and barriers to both implementation and integration of AI platforms into daily practice are discussed alongside examples including AI in emergency care and breast screening. Issues addressed include the need to generate more real-world evidence that helps developers and service providers to determine the optimal way for patients to reap the benefits of AI with faster reporting turnaround time, faster diagnoses, and treatment times, for example. To ensure the effective and timely wide-scale implementation, adoption requires a national policy drive and national level coordination but specific, local needs of NHS Trusts and any particular service within Trusts will also need to be met. By embedding AI-capabilities into scanners, ultrasound-devices, X-ray equipment, and Picture archiving and communication system (PACS), local services will benefit, while AI applications can streamline workflows across and between departments and potentially Trusts. AI predictive analytics and systems engineering can be used to better manage patient volume and movement. In the short term, education, training, and confidence in adapting and adopting AI in radiology require dedicated local, national, and governmental effort but the future benefits promise to justify the means.

Comparative effectiveness of standard vs. AI-assisted PET/CT reading workflow for pre-treatment lymphoma staging: a multi-institutional reader study evaluation.

Fluorine-18 fluorodeoxyglucose (FDG)-positron emission tomography/computed tomography (PET/CT) is widely used for staging high-grade lymphoma, with the time to evaluate such studies varying depending on the complexity of the case. Integrating artificial intelligence (AI) within the reporting workflow has the potential to improve quality and efficiency. The aims of the present study were to evaluate the influence of an integrated research prototype segmentation tool implemented within diagnostic PET/CT reading software on the speed and quality of reporting with variable levels of experience, and to assess the effect of the AI-assisted workflow on reader confidence and whether this tool influenced reporting behaviour. Nine blinded reporters (three trainees, three junior consultants and three senior consultants) from three UK centres participated in a two-part reader study. A total of 15 lymphoma staging PET/CT scans were evaluated twice: first, using a standard PET/CT reporting workflow; then, after a 6-week gap, with AI assistance incorporating pre-segmentation of disease sites within the reading software. An even split of PET/CT segmentations with gold standard (GS), false-positive (FP) over-contour or false-negative (FN) under-contour were provided. The read duration was calculated using file logs, while the report quality was independently assessed by two radiologists with >15 years of experience. Confidence in AI assistance and identification of disease was assessed via online questionnaires for each case. There was a significant decrease in time between non-AI and AI-assisted reads (median 15.0 vs. 13.3 min, p < 0.001). Sub-analysis confirmed this was true for both junior (14.5 vs. 12.7 min, p = 0.03) and senior consultants (15.1 vs. 12.2 min, p = 0.03) but not for trainees (18.1 vs. 18.0 min, p = 0.2). There was no significant difference between report quality between reads. AI assistance provided a significant increase in confidence of disease identification (p < 0.001). This held true when splitting the data into FN, GS and FP. In 19/88 cases, participants did not identify either FP (31.8%) or FN (11.4%) segmentations. This was significantly greater for trainees (13/30, 43.3%) than for junior (3/28, 10.7%, p = 0.05) and senior consultants (3/30, 10.0%, p = 0.05). The study findings indicate that an AI-assisted workflow achieves comparable performance to humans, demonstrating a marginal enhancement in reporting speed. Less experienced readers were more influenced by segmentation errors. An AI-assisted PET/CT reading workflow has the potential to increase reporting efficiency without adversely affecting quality, which could reduce costs and report turnaround times. These preliminary findings need to be confirmed in larger studies.

Improving the process for expediting reporting in a radiology service, to deliver faster and more reliable report turnaround time where necessary

Improving the process for expediting reporting in a radiology service, to deliver faster and more reliable report turnaround time where necessary

Clinical Evaluation of a Functional Combinatorial Precision Medicine Platform to Predict Patient-Specific Treatment Outcomes in Acute Myeloid Leukemia

Introduction: Acute myeloid leukemia (AML) is an aggressive form a leukemia that remains difficult to treat, often with rapid and frequent disease relapse due to drug-resistant clonal selection. A range of combination therapies have been designed to overcome this hurdle, however, identifying the most appropriate combination therapy at each line of treatment remains a challenge. Functional precision medicine platforms that use ex vivo drug sensitivity data from primary patient samples have shown potential to guide treatments in a range of cancers. We have recently developed an ex vivo combinatorial drug sensitivity platform, quadratic phenotypic optimization platform (QPOP), that analyses a predesigned array of 155 test combinations performed on a primary patient sample to rank and compare all possible therapeutic combinations from a 12-drug set. In this study, we evaluated the use of QPOP to predict treatment outcomes in an AML cohort treated with a variety of combination therapies. Furthermore, we also explored QPOP's combination therapy ranking function to identify novel or under-utilized combinations that may benefit larger groups of AML patients when appropriately guided. Methods: Prospective clinical feasibility study of QPOP in AML was performed at National University Hospital (NUH) in Singapore. Peripheral blood or bone marrow aspirations were collected from AML patients, recruited between 26 th November 2019 and June 15 th 2023. Following CD34+ cell selection, the enriched malignant blast population was subjected to an array of 155 test combinations derived from an orthogonal array composite design. Phenotypic cell viability data from this test was subsequently used by QPOP to derive drug combination scores and rankings for all possible combinations. Median turnaround time for QPOP patient-specific reports was 8 (±2.1) days. Patients were treated with current standard of care options as guided by the clinician. The primary outcomes of this study were to determine the concordance between treatment outcomes as guided by clinicians and QPOP drug combination scores and rankings. Secondary outcomes of this study were to identify high-ranking, potentially effective combinations that may be nover or under-utilized for future studies. Results: 40 patients were recruited to the study with 49 samples analyzed by QPOP. Samples collected until 21 January 2022 were also used to refined ex vivo drug dosing levels for 12-drug, 3-level test combination arrays. Excluding patients diagnosed as non-AML and patient without available clinical concordance data, QPOP response concordance was evaluable for 19 patients. A 75% positive predictive value (PPV) and a 72.7% negative predictive value (NPV) was determined for a QPOP normalized cell viability (NCV) cutoff of 0.65. The area under the curve of the receiver operator curve, AUC = 0.75, suggesting acceptable predictivity. Concordance analysis of with samples (n = 10) collected after 21January 2022 demonstrated an 80% PPV, 80% NPV, AUC = 0.80 for an NCV cutoff of 0.62, suggesting that current ex vivo dosage settings for test array can further improve test accuracy. Combination therapy with the BCL2 inhibitor venetoclax and hypomethylating agent azacytidine is standard-of-care for AML. QPOP NCV cutoff of 0.62 also exhibited 100% concordance (5/5) with venetoclax+azacytidine treatment further demonstrating the accuracy of QPOP to predict treatment outcomes in AML. Amongst top ranked QPOP-derived combinations, venetoclax/fludarabine was amongst the most frequently reoccurring top-ranked combinations. With appropriate functional combinatorial precision medicine testing, patients who may benefit from addition of venetoclax to fludarabine-based chemotherapy regimens, such as fludarabine/busulfan reduced-intensity conditioning chemotherapy, may be accurately identified. Conclusions: This clinical study demonstrates the feasibility of QPOP to predict treatment outcomes and accurately identify both response and resistance to combination therapy. Following platform workflow optimization, initial concordance analysis suggests excellent predictivity. Expansion of this clinical study is needed to confirm these results. This study also suggests that underutilized combinations may be effective across a larger population of AML patients with appropriate ex vivo drug testing and deserve further clinical interrogation.

A vendor-agnostic, PACS integrated, and DICOM-compatible software-server pipeline for testing segmentation algorithms within the clinical radiology workflow.

Reproducible approaches are needed to bring AI/ML for medical image analysis closer to the bedside. Investigators wishing to shadow test cross-sectional medical imaging segmentation algorithms on new studies in real-time will benefit from simple tools that integrate PACS with on-premises image processing, allowing visualization of DICOM-compatible segmentation results and volumetric data at the radiology workstation. In this work, we develop and release a simple containerized and easily deployable pipeline for shadow testing of segmentation algorithms within the clinical workflow. Our end-to-end automated pipeline has two major components- 1. A router/listener and anonymizer and an OHIF web viewer backstopped by a DCM4CHEE DICOM query/retrieve archive deployed in the virtual infrastructure of our secure hospital intranet, and 2. An on-premises single GPU workstation host for DICOM/NIfTI conversion steps, and image processing. DICOM images are visualized in OHIF along with their segmentation masks and associated volumetry measurements (in mL) using DICOM SEG and structured report (SR) elements. Since nnU-net has emerged as a widely-used out-of-the-box method for training segmentation models with state-of-the-art performance, feasibility of our pipleine is demonstrated by recording clock times for a traumatic pelvic hematoma nnU-net model. Mean total clock time from PACS send by user to completion of transfer to the DCM4CHEE query/retrieve archive was 5 min 32 s (± SD of 1 min 26 s). This compares favorably to the report turnaround times for whole-body CT exams, which often exceed 30 min, and illustrates feasibility in the clinical setting where quantitative results would be expected prior to report sign-off. Inference times accounted for most of the total clock time, ranging from 2 min 41 s to 8 min 27 s. All other virtual and on-premises host steps combined ranged from a minimum of 34 s to a maximum of 48 s. The software worked seamlessly with an existing PACS and could be used for deployment of DL models within the radiology workflow for prospective testing on newly scanned patients. Once configured, the pipeline is executed through one command using a single shell script. The code is made publicly available through an open-source license at "https://github.com/vastc/," and includes a readme file providing pipeline config instructions for host names, series filter, other parameters, and citation instructions for this work.

Synoptic Reporting for Pretreatment CT Examination in Patients With Advanced Ovarian Cancer: Impact on Documentation of Disease Sites and Physician Satisfaction.

BACKGROUND. Imaging reports that consistently document all disease sites with a potential to increase surgical complexity or morbidity can facilitate ovarian cancer treatment planning. OBJECTIVE. The aims of this study were to compare simple structured reports and synoptic reports from pretreatment CT examinations in patients with advanced ovarian cancer in terms of completeness of documenting involvement of clinically relevant anatomic sites as well as to evaluate physician satisfaction with synoptic reports. METHODS. This retrospective study included 205 patients (median age, 65 years) who underwent contrast-enhanced abdominopelvic CT before primary treatment of advanced ovarian cancer from June 1, 2018, to January 31, 2022. A total of 128 reports generated on or before March 31, 2020, used a simple structured report (free text organized into sections); 77 reports generated on or after April 1, 2020, used a synoptic report (a list of 45 anatomic sites relevant to ovarian cancer management, each of which was classified in terms of disease absence versus presence). Reports were reviewed for completeness of documentation of involvement of the 45 sites. For patients who underwent neoadjuvant chemotherapy based on diagnostic laparoscopy findings or underwent primary debulking surgery with suboptimal resection, the EMR was reviewed to identify surgically established sites of disease that were unresectable or challenging to resect. Gynecologic oncology surgeons were electronically surveyed. RESULTS. The mean report turnaround time was 29.8 minutes for simple structured reports versus 54.5 minutes for synoptic reports (p < .001). A mean of 17.6 of 45 sites (range, four to 43 sites) were mentioned by simple structured reports versus 44.5 of 45 sites (range, 39-45) for synoptic reports (p < .001). Forty-three patients had surgically established unresectable or challenging-to-resect disease; involvement of anatomic site(s) with such disease was mentioned in 37% (11/30) of simple structured reports versus 100% (13/13) of synoptic reports (p < .001). All eight surveyed gynecologic oncology surgeons completed the survey. CONCLUSION. A synoptic report improved completeness of pretreatment CT reports in patients with advanced ovarian cancer, including for established sites of unresectable or challenging-to-resect disease. CLINICAL IMPACT. The findings indicate the role of disease-specific synoptic reports in facilitating referrer communication and potentially guiding clinical decision-making.

Prospective Evaluation of AI Triage of Pulmonary Emboli on CT Pulmonary Angiograms.

Background Artificial intelligence (AI) algorithms have shown high accuracy for detection of pulmonary embolism (PE) on CT pulmonary angiography (CTPA) studies in academic studies. Purpose To determine whether use of an AI triage system to detect PE on CTPA studies improves radiologist performance or examination and report turnaround times in a clinical setting. Materials and Methods This prospective single-center study included adult participants who underwent CTPA for suspected PE in a clinical practice setting. Consecutive CTPA studies were evaluated in two phases, first by radiologists alone (n = 31) (May 2021 to June 2021) and then by radiologists aided by a commercially available AI triage system (n = 37) (September 2021 to December 2021). Sixty-two percent of radiologists (26 of 42 radiologists) interpreted studies in both phases. The reference standard was determined by an independent re-review of studies by thoracic radiologists and was used to calculate performance metrics. Diagnostic accuracy and turnaround times were compared using Pearson χ2 and Wilcoxon rank sum tests. Results Phases 1 and 2 included 503 studies (participant mean age, 54.0 years ± 17.8 [SD]; 275 female, 228 male) and 1023 studies (participant mean age, 55.1 years ± 17.5; 583 female, 440 male), respectively. In phases 1 and 2, 14.5% (73 of 503) and 15.9% (163 of 1023) of CTPA studies were positive for PE (P = .47). Mean wait time for positive PE studies decreased from 21.5 minutes without AI to 11.3 minutes with AI (P < .001). The accuracy and miss rate, respectively, for radiologist detection of any PE on CTPA studies was 97.6% and 12.3% without AI and 98.6% and 6.1% with AI, which was not significantly different (P = .15 and P = .11, respectively). Conclusion The use of an AI triage system to detect any PE on CTPA studies improved wait times but did not improve radiologist accuracy, miss rate, or examination and report turnaround times. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Murphy and Tee in this issue.

Implementation of Medical Students as Radiology Reading Room Coordinators

ObjectiveEffort has been made to minimize the burden of non-interpretive tasks (NITs), in particular by hiring and training non-radiologist support staff as reading room coordinators (RRCs). Our medical center recruited and trained senior medical students from our affiliated school of medicine to work alongside on-call radiology residents as RRCs. MethodsA 12-month Malpractice Carrier monetary grant was acquired to fund medical students at with the aim to reduce malpractice risk. After the first year, residents were surveyed regarding the impact of the RRCs on perceived on-call efficiency and morale. Furthermore, report turnaround times (TAT) on call shifts that were and were not accompanied by a RRC were compared. Results89 % of residents strongly agreed that the RRC improved workflow efficiency, decreased distractions, and felt less stressed during the call shift when the RRC was on duty. 78 % strongly agreed to be more likely to contact a referring clinician when the RRC was able to help coordinate. The mean TAT in the presence of a RRC was 36.8 min, and the mean TAT in the absence of a RRC was 36.9 min DiscussionAfter hiring medical students to assist on-call radiology residents with noninterpretive tasks, residents reported subjective indicators of program success, but average report turnaround time was unaffected. Nevertheless, we predict that this type of program will continue to grow among academic radiology departments, though additional research is required to evaluate national trends and impacts on radiologist productivity and well-being.

Imaging Analytics using Artificial Intelligence in Oncology: A Comprehensive Review

The present era has seen a surge in artificial intelligence-related research in oncology, mainly using deep learning, because of powerful computer hardware, improved algorithms and the availability of large amounts of data from open-source domains and the use of transfer learning. Here we discuss the multifaceted role of deep learning in cancer care, ranging from risk stratification, the screening and diagnosis of cancer, to the prediction of genomic mutations, treatment response and survival outcome prediction, through the use of convolutional neural networks. Another role of artificial intelligence is in the generation of automated radiology reports, which is a boon in high-volume centres to minimise report turnaround time. Although a validated and deployable deep-learning model for clinical use is still in its infancy, there is ongoing research to overcome the barriers for its universal implementation and we also delve into this aspect. We also briefly describe the role of radiomics in oncoimaging. Artificial intelligence can provide answers pertaining to cancer management at baseline imaging, saving cost and time. Imaging biobanks, which are repositories of anonymised images, are also briefly described. We also discuss the commercialisation and ethical issues pertaining to artificial intelligence. The latest generation generalist artificial intelligence model is also briefly described at the end of the article. We believe this article will not only enrich knowledge, but also promote research acumen in the minds of readers to take oncoimaging to another level using artificial intelligence and also work towards clinical translation of such research.

Radiologist Worklist Reprioritization Using Artificial Intelligence: Impact on Report Turnaround Times for CTPA Examinations Positive for Acute Pulmonary Embolism.

BACKGROUND. In patients with acute pulmonary embolism (PE), timely intervention (e.g., initiation of anticoagulation) is critical for optimizing clinical outcomes. OBJECTIVE. The purpose of this study was to evaluate the effect of artificial intelligence (AI)-based radiologist worklist reprioritization on report turnaround times for pulmonary CTA (CTPA) examinations positive for acute PE. METHODS. This retrospective single-center study included patients who underwent CTPA before (October 1, 2018-March 31, 2019 [pre-AI period]) and after (October 1, 2019-March 31, 2020 [post-AI period]) implementation of an AI tool that reprioritized CTPA examinations to the top of radiologists' reading worklists if acute PE was detected. EMR and dictation system timestamps were used to determine the wait time (time from examination completion to report initiation), read time (time from report initiation to report availability), and report turnaround time (sum of wait and read times) for the examinations. Times for reports positive for PE, with final radiology reports as reference, were compared between periods. RESULTS. The study included 2501 examinations of 2197 patients (1307 women, 890 men; mean age, 57.4 ± 17.0 [SD] years), including 1335 examinations from the pre-AI period and 1166 from the post-AI period. The frequency of acute PE, based on radiology reports, was 15.1% (201/1335) during the pre-AI period and 12.3% (144/1166) during the post-AI period. During the post-AI period, the AI tool reprioritized 12.7% (148/1166) of examinations. For PE-positive examinations, the post-AI period, compared with the pre-AI period, had significantly shorter mean report turnaround time (47.6 vs 59.9 minutes; mean difference, 12.3 minutes [95% CI, 0.6-26.0 minutes]) and mean wait time (21.4 vs 33.4 minutes; mean difference, 12.0 minutes [95% CI, 0.9-25.3 minutes]) but no significant difference in mean read time (26.3 vs 26.5 minutes; mean difference, 0.2 minutes [95% CI, -2.8 to 3.2 minutes]). During regular operational hours, wait time was significantly shorter in the post-AI than in the pre-AI period for routine-priority examinations (15.3 vs 43.7 minutes; mean difference, 28.4 minutes [95% CI, 2.2-64.7 minutes]) but not for stat- or urgent-priority examinations. CONCLUSION. AI-driven worklist reprioritization yielded reductions in report turnaround time and wait time for PE-positive CTPA examinations. CLINICAL IMPACT. By assisting radiologists in providing rapid diagnoses, the AI tool has potential for enabling earlier interventions for acute PE.

A Teleradiology System for Early Ischemic and Hemorrhagic Stroke Evaluation and Management

Abstract Purpose Stroke is a cardinal cause of death and disability globally. It is an emergency condition where the rapidity of diagnosis is directly linked to the outcome. “Imaging is Brain” is, therefore, an important concept. The early diagnosis of stroke is crucial not only in guiding its effective treatment but also in estimating prognosis. This study aims to provide perspective on the implementation of international teleradiology in stroke evaluation, management, and care. Methods A dedicated international teleradiology stroke network has been evaluated in our study between March 2019 and July 2022 where the interpretation and analysis of the computed tomography (CT) scans of the patients from distant hospitals in United States were performed by teleradiologists via high-quality Digital Imaging and Communications in Medicine (DICOM)-image transfer through a cloud-based radiology information system/picture archival and communication system platform RADspa. Results Over a period of three and a half years, starting from March 2019, a total of 30,406 CT scans of 19,342 patients from 96 hospitals of 15 states in the United States were interpreted and reported by board-certified radiologists empaneled by Teleradiology Solutions. The mean report turnaround time for all noncontrast CT studies was 9.97 minutes at 95% confidence interval (CI: 9.89–10.05); for CT angiogram studies, it was 20.57 minutes 95% CI (20.38–20.77); and for CT perfusion studies, it was 13.72 minutes 95% CI (13.42–14.03). Conclusion A dedicated international teleradiology stroke network designed in our study allowed for transmission, prioritization, evaluation, and management of CT cases performed in the setting of acute stroke in the study population. The results of our investigation indicate that teleradiology provides an effective solution for early diagnosis/interpretation of CT examinations performed internationally in the setting of acute stroke. This may further be used as a model or template for the development of a nationwide stroke network within our own country.

An initiative to promote value-based stress test selection in primary care and cardiology clinics: A mixed methods evaluation.

Exercise stress echocardiograms (stress echos) are overused, whereas exercise stress electrocardiograms (stress ECGs) can be an appropriate, lower-cost substitute. In this post hoc, mixed methods evaluation, we assessed an initiative promoting value-based, guideline-concordant ordering practices in primary care (PC) and cardiology clinics. Change in percent of stress ECGs ordered of all exercise stress tests (stress ECGs and echos) was calculated between three periods: baseline (January 2019-February 2020); Period 1 with reduced stress ECG report turnaround time + PC-targeted education (began June 2020); and Period 2 with the addition of electronic health record-based alternative alert (AA) providing point-of-care clinical decision support. The AA was deployed in two of five PC clinics in July 2020, two additional PC clinics in January 2021, and one of four cardiology clinics in February 2021. Nineteen primary care providers (PCPs) and five cardiologists were interviewed in Period 2. Clinicians reported reducing ECG report turnaround time was crucial for adoption. PCPs specifically reported that value-based education helped change their practice. In PC, the percent of stress ECGs ordered increased by 38% ± 6% (SE) (p < 0.0001) from baseline to Period 1. Most PCPs identified the AA as the most impactful initiative, yet stress ECG ordering did not change (6% ± 6%; p = 0.34) between Periods 1 and 2. In contrast, cardiologists reportedly relied on their expertise rather than AAs, yet their stress ECGs orders increased from Period 1 to 2 to a larger degree in the cardiology clinic with the AA (12% ± 5%; p = 0.01) than clinics without the AA (6% ± 2%; p = 0.01). The percent of stress ECGs ordered was higher in Period 2 than baseline for both specialties (both p < 0.0001). This initiative influenced ordering behaviour in PC and cardiology clinics. However, clinicians' perceptions of the initiative varied between specialties and did not always align with the observed behaviour change.

Feasibility and Cost Analysis of Portable MRI Implementation in a Remote Setting in Canada.

To conduct feasibility and cost analysis of portable MRI implementation in a remote setting where MRI access is otherwise unavailable. Portable MRI (ultra-low field, 0.064T) was installed in Weeneebayko General Hospital, Moose Factory, Ontario. Adult patients, presenting with any indication for neuroimaging, were eligible for study inclusion. Scanning period was from November 14, 2021, to September 6, 2022. Images were sent via a secure PACS network for Neuroradiologist interpretation, available 24/7. Clinical indications, image quality, and report turnaround time were recorded. A cost analysis was conducted from a healthcare system's perspective in 2022 Canadian dollars, comparing cost of portable MRI implementation to transporting patients to a center with fixed MRI. Portable MRI was successfully implemented in a remote Canadian location. Twenty-five patients received a portable MRI scan. All studies were of diagnostic quality. No clinically significant pathologies were identified on any of the studies. However, based on clinical presentation and limitations of portable MRI resolution, it is estimated that 11 (44%) of patients would require transfer to a center with fixed MRI for further imaging workup. Cost savings were $854,841 based on 50 patients receiving portable MRI over 1 year. Five-year budget impact analysis showed nearly $8 million dollars saved. Portable MRI implementation in a remote setting is feasible, with significant cost savings compared to fixed MRI. This study may serve as a model to democratize MRI access, offer timely care and improved triaging in remote areas where conventional MRI is unavailable.