Smart chest X-ray worklist prioritization using artificial intelligence: a clinical workflow simulation

Objective The aim is to evaluate whether smart worklist prioritization by artificial intelligence (AI) can optimize the radiology workflow and reduce report turnaround times (RTATs) for critical findings in chest radiographs (CXRs). Furthermore, we investigate a method to counteract the effect of false negative predictions by AI—resulting in an extremely and dangerously long RTAT, as CXRs are sorted to the end of the worklist. Methods We developed a simulation framework that models the current workflow at a university hospital by incorporating hospital-specific CXR generation rates and reporting rates and pathology distribution. Using this, we simulated the standard worklist processing “first-in, first-out” (FIFO) and compared it with a worklist prioritization based on urgency. Examination prioritization was performed by the AI, classifying eight different pathological findings ranked in descending order of urgency: pneumothorax, pleural effusion, infiltrate, congestion, atelectasis, cardiomegaly, mass, and foreign object. Furthermore, we introduced an upper limit for the maximum waiting time, after which the highest urgency is assigned to the examination. Results The average RTAT for all critical findings was significantly reduced in all prioritization simulations compared to the FIFO simulation (e.g., pneumothorax: 35.6 min vs. 80.1 min; p < 0.0001), while the maximum RTAT for most findings increased at the same time (e.g., pneumothorax: 1293 min vs 890 min; p < 0.0001). Our “upper limit” substantially reduced the maximum RTAT in all classes (e.g., pneumothorax: 979 min vs. 1293 min/1178 min; p < 0.0001). Conclusion Our simulations demonstrate that smart worklist prioritization by AI can reduce the average RTAT for critical findings in CXRs while maintaining a small maximum RTAT as FIFO. Key Points • Development of a realistic clinical workflow simulator based on empirical data from a hospital allowed precise assessment of smart worklist prioritization using artificial intelligence. • Employing a smart worklist prioritization without a threshold for maximum waiting time runs the risk of false negative predictions of the artificial intelligence greatly increasing the report turnaround time. • Use of a state-of-the-art convolution neural network can reduce the average report turnaround time almost to the upper limit of a perfect classification algorithm (e.g., pneumothorax: 35.6 min vs. 30.4 min).

Subspecialized radiological reporting reduces radiology report turnaround time

Objectives The objective of this study was to compare the radiology report turnaround time (RTAT) between decentralized/modality-based and centralized/subspecialized radiological reporting at a multi-center radiology enterprise. Methods RTAT values for MRI, CT, and conventional radiography were compared between decentralized/modality-based (04 September 2017–22 December 2017) and centralized/subspecialized radiology (03 September 2018–21 December 2018) reporting grouped into three subspecializations (body radiology, musculoskeletal radiology, and neuroradiology) at eleven sites of a multi-center radiology enterprise. For the objective of this investigation, hospitals were defined as major and minor hospitals. The Mann-Whitney U test served for statistical analyses. Results Change of reporting system from decentralized/modality-based to centralized/subspecialized radiology resulted overall in a significant decrease of the RTAT: from 82 to 77 min for the first signature (p < 0.001), and 119 to 107 min and 295 to 238 min for the second signature (p < 0.001). Subgroup analyses demonstrate a significant decrease of the RTAT for MRI reports (e.g., second signature RTAT, 1051 to 401 min; p < 0.001) and conventional radiographs (e. g., second signature RTAT, 278 to 171 min; p < 0.001). The RTAT at major hospitals decreased from 288 to 245 min (second signature; p < 0.001) while the corresponding RTAT of minor hospitals decreased more remarkably, from 300 to 198 min (p < 0.001). However, the results were heterogenous; in some analyses, the RTAT even increased. The effect size analyses represent small effects. Conclusions Change of reporting system from decentralized/modality-based to centralized/subspecialized radiology was associated with a significant decreased RTAT. Specifically, the RTAT for MRI reports and conventional radiographs was significantly reduced. A pronounced RTAT decrease was observed at minor hospitals.

Breast Imaging Second Opinion Consultation: A Single Institution’s Process of Improvement and Reform

Objective To review a single institution’s second opinion breast imaging process, data tracking, and metrics before and after implementing quality improvement changes and the effect on report turnaround time. Methods This Institutional Review Board approved retrospective quality improvement project was performed at a tertiary-care academic medical center and included patients 18 years or older who submitted their outside facility imaging for reinterpretation (any combination of mammography, breast ultrasonography, and/or magnetic resonance imaging performed within the last six months) with finalized second opinion reports between June 1, 2016, and July 17, 2017. Significant intradepartmental changes were implemented March 2017 with the goal to improve second opinion report turnaround time. Key metrics from 399 studies were analyzed before and after implemented changes. Two-sided Fisher’s exact test was used to assess the significance of results. Results After department interventions, the percentage of outside reports available at the time of surgical consultation improved from 82% (213/259) to 91% (127/140), an 11% improvement (P &lt; 0.05). The average number of days from initial second opinion consultation to the availability of final report improved from 10.2 days to 9 days, a 12% improvement. Prior to the changes, the number of days it took a radiologist to complete a report varied from 1 to 4 days, but afterwards was consistently 1 day or less. Conclusion Implementation of second opinion intradepartmental changes demonstrated a significant improvement in report turnaround time and the number of finalized reports available at the time of surgical consultation. An efficient second opinion process is crucial to a breast imaging center, as it ultimately expedites patient surgical and oncological care.

Exploring the Role of Artificial Intelligence in an Emergency and Trauma Radiology Department

Emergency and trauma radiologists, emergency department’s physicians and nurses, researchers, departmental leaders, and health policymakers have attempted to discover efficient approaches to enhance the provision of quality patient care. There are increasing expectations for radiology practices to deliver a dedicated emergency radiology service providing 24/7/365 on-site attending radiologist coverage. Emergency radiologists (ERs) are pressed to meet the demand of increased imaging volume, provide accurate reports, maintain a lower proportion of discrepancy rate, and with a rapid report turnaround time of finalized reports. Thus, rendering the radiologists overburdened. The demand for an increased efficiency in providing quality care to acute patients has led to the emergence of artificial intelligence (AI) in the field. AI can be used to assist emergency and trauma radiologists deal with the ever-increasing imaging volume and workload, as AI methods have typically demonstrated a variety of applications in medical image analysis and interpretation, albeit most programs are in a training or validation phase. This article aims to offer an evidence-based discourse about the evolving role of artificial intelligence in assisting the imaging pathway in an emergency and trauma radiology department. We hope to generate a multidisciplinary discourse that addresses the technical processes, the challenges in the labour-intensive process of training, validation and testing of an algorithm, the need for emphasis on ethics, and how an emergency radiologist’s role is pivotal in the execution of AI-guided systems within the context of an emergency and trauma radiology department. This exploratory narrative serves the present-day health leadership’s information needs by proposing an AI supported and radiologist centered framework depicting the work flow within a department. It is suspected that the use of such a framework, if efficacious, could provide considerable benefits for patient safety and quality of care provided. Additionally, alleviating radiologist burnout and decreasing healthcare costs over time.

Implementing Case Management within a Large Medicolegal Death Investigation Agency

Medicolegal death investigation agencies must provide timely final autopsy reports in order to meet minimum accreditation standards. To ensure a timely turn around, the principles of case management were introduced into an agency with a large metropolitan jurisdiction. Forensic autopsies are typically complex and the associated ancillary studies often include forensic toxicology along with various specialty consults. Beginning in 2013, a forensic case management service was initiated to aid forensic pathologists in reducing report turnaround time. Despite increasing number of cases in 2014, the agency was able to maintain the accreditation standard of 90% turn around within 90 days. The case management service required process improvement, technology to track and trend, and increased interdisciplinary collaboration. The implementation of a case management system within the forensic autopsy service can improve processes to reduce report turnaround times.

Temporal evaluation of computed tomographic scans at a Level 1 trauma department in a central South African hospital

Background: Time is a precious commodity, especially in the trauma setting, which requires continuous evaluation to ensure streamlined service delivery, quality patient care and employee efficiency.Objectives: The present study analyses the authors’ institution’s multi-detector computed tomography (MDCT) scan process as part of the imaging turnaround time of trauma patients. It is intended to serve as a baseline for the institution, to offer a comparison with institutions worldwide and to improve service delivery.Method: Relevant categorical data were collected from the trauma patient register and radiological information system (RIS) from 01 February 2013 to 31 January 2014. A population of 1107 trauma patients who received a MDCT scan was included in the study. Temporal data were analysed as a continuum with reference to triage priority, time of day, type of CT scan and admission status. Results: The median trauma arrival to MDCT scan time (TTS) and reporting turnaround time (RTAT) were 69 (39–126) and 86 (53–146) minutes respectively. TTS was subdivided into the time when the patient arrived at trauma to the radiology referral (TTRef) and submission of the radiology request, to the arrival at the MDCT (RefTS) location. TTRef was statistically significantly longer than RefTS (p < 0.0001). RTAT was subdivided into the arrival at the MDCT to the start of the radiology report (STR) and time taken to complete the report (RT). STR was statistically significantly longer than RT (p < 0.0001). Conclusion: The time to scan (TTS) was comparable to, but unfortunately the report turnaround time (RTAT) lagged behind, the findings of some first-world institutions.