Radiology Information System Data Research Articles

Do-It-Yourself Business Intelligence for the Radiologist-Lessons Learned From 10-Year Trends in an Abdominal Imaging Division at a Tertiary Medical Center.

"Big data" has changed the way businesses operate in finance, insurance, communications, manufacturing, and logistics, with companies reporting successful outcomes from the implementation of data-driven analytics. Health care has slowly started leveraging big data analysis to identify more cost-efficient and effective care for patients. Business intelligence software aims to help with this transition, converting large data sets into useful, actionable information. Radiology practices have used business intelligence toolkits in the past to increase reading room productivity, scanner efficiency, and patient throughput. Although these tactics have driven down costs and increased volumes, an essential aspect of radiology practice growth-consumer satisfaction-remains largely unexplored. The first commandment of marketing is "know thy customer," which is the key to increasing radiology's value to referring clinicians who use our services. Our article explores the business case behind a basic business intelligence model, giving any radiologist the instruments to access and draw business conclusions from their radiology information system data.

Appropriateness of CT pulmonary angiograms according to current diagnostic guidelines based on risk stratification: A retrospective single-center study.

Assessment of appropriateness of CT pulmonary angiograms (CTPA) in patients with suspected pulmonary embolism (PE) is based on risk stratification algorithms such as simplified the Geneva Score (sGS) in combination with D-dimer blood tests. The aim of this study was to validate the diagnostic yield and appropriateness of CTPA examinations in accordance with 2014 European Society of Cardiology (ESC) guidelines. Data from 155 outpatients who underwent CTPA for clinical suspicion of PE were gathered from the radiology information system (RIS) and the clinical information system (CIS). We assessed the presence of sGS items and D-dimer blood test results in RIS from CTPA request forms and from clinical documentation in CIS. Based on the RIS, there were 2.6% patients with high (sGS≥3) and 97.4% patients with low pre-test PE probability (sGS<3), and CTPA indication was formally comprehendible in 75.5% using sGS and D-dimer blood tests. Based on RIS and CIS data in combination, there were 41.3% patients with high and 58.7% patients with low pre-test PE probability, and CTPA indication was formally comprehendible in 88.4%. Using RIS and CIS in combination, PE probability was upgraded from low to high probability in 39.7% compared with RIS alone. In 12.9%, there was a lack of data in RIS for CTPA justification. There is a high diagnostic yield when applying current diagnostic guidelines to our data. There was however a notable discrepancy between the data transferred to the CTPA request forms from the full clinical documentation, therefore not readily available for clinical decision making.

A silver bullet? The role of radiology information system data mining in defining gunshot injury trends at a South African tertiary-level hospital.

BackgroundSouth Africa (SA) has no national injury surveillance system, and hence, non-fatal gunshot injuries are not routinely recorded. Most firearm-related injuries require multi-detector computer tomography (MDCT) assessment at a tertiary-level facility. MDCT scanning for victims with gunshot injuries thus provide an indication of the societal burden of firearm trauma. The potential of the modern radiology information system (RIS) to serve as a robust research tool in such settings is not fully appreciated.ObjectiveThe aim of this study was to evaluate the use of institutional RIS data in defining MDCT scanning trends for gunshot victims presenting to a tertiary-level SA hospital.MethodA single-institution, retrospective, comparative study was conducted at the Tygerberg Hospital (TBH) Trauma Unit for the years 2013 and 2018. Using data-mining software, customised RIS searches for information on all gunshot-related emergency computed tomography scans in the respective years were performed. Demographic, temporal, anatomical and scan-protocol trends were analysed by cross tabulation, Chi-squared and Fisher’s exact tests.ResultsGunshot-related emergency MDCT scans increased by 62% (546 vs. 887) from 2013 to 2018. Lower-limb CT angiography was the commonest investigation in both periods. A higher proportion of victims in 2018 sustained thoracic injuries (12.5% vs. 19.8%; p < 0.01) and required imaging of more than two body parts (13.1% vs. 19.2%; p < 0.01).ConclusionBy using RIS data to demonstrate the increasing gunshot-related MDCT workload in the review period, as well as a pattern of more complex and potentially life-threatening injury, this study highlights the burden of firearm trauma in the society and the potential role of the modern RIS as a robust research tool.

The usefulness of large sample size patient dose audits for optimisation of CT automatic exposure control (AEC) settings

The aim of this study was to demonstrate the usefulness of large sample size patient dose audits for optimisation of CT automatic exposure control (AEC) settings, even when the investigation is limited to only three scanners at a single institution. Pre-optimisation patient dose audits of common CT examinations (n > 200 for each protocol) on three CT scanners (two Philips Brilliance and one Toshiba Aquilion) using radiology information system (RIS) data were conducted showing sub-optimal CT AEC performance on the Toshiba scanner. Based on these results, an optimisation exercise was carried out on the non-optimally performing scanner by phantom measurement and investigation of system configuration. Post-optimisation patient dose audits were subsequently carried out to assess the success of the optimisation exercise demonstrating standardisation of doses; median dose-length-product values were reduced by up to 43% on the sub-optimal scanner without any adverse effect on clinical image quality. This study has demonstrated that large sample patient dose audits using RIS data can be instrumental in identifying and rectifying sub-optimal CT AEC performance, even when the investigation is limited to only three scanners at a single institution.

Computed tomographic colonography: how many and how fast should radiologists report?

ObjectivesTo determine if polyp detection at computed tomographic colonography (CTC) is associated with (a) the number of CTC examinations interpreted per day and (b) the length of time spent scrutinising the scan.MethodsRetrospective observational study from two hospitals. We extracted Radiology Information System data for CTC examinations from Jan 2012 to Dec 2015. For each examination, we determined how many prior CTCs had been interpreted by the reporting radiologist on that day and how long radiologists spent on interpretation. For each radiologist, we calculated their referral rate (proportion deemed positive for 6 mm+ polyp/cancer), positive predictive value (PPV) and endoscopic/surgically proven polyp detection rate (PDR). We also calculated the mean time each radiologist spent interpreting normal studies (“negative interpretation time”). We used multilevel logistic regression to investigate the relationship between the number of scans reported each day, negative interpretation time and referral rate, PPV and PDR.ResultsFive thousand one hundred ninety-one scans were interpreted by seven radiologists; 892 (17.2%) were reported as positive, and 534 (10.3%) had polyps confirmed. Both referral rate and PDR reduced as more CTCs were reported on a given day (p < 0.001), the odds reducing by 7% for each successive CTC interpreted. Radiologists reporting more slowly than their colleagues detected more polyps (p = 0.028), with each 16% increase in interpretation time associated with a 1% increase in PDR. PPV was unaffected.ConclusionsReporting multiple CTCs on a given day and rapid CTC interpretation are associated with decreased polyp detection. Radiologists should be protected from requirements to report too many CTCs or too quickly.Key Points• CT colonography services should protect radiologists from a need to report too fast (> 20 min per case) or for too long (> 4 cases consecutively without a break).• Professional bodies should consider introducing a target minimum interpretation time for CT colonography examinations as a quality marker.

Qualifying the use of RIS data for patient dose by comparison with DICOM header data

A system was developed in 2008 to calculate patient doses using Radiology Information System (RIS) data and presents these data as a patient dose audit. One of the issues with this system was the quality of user-entered data. It has been shown that Digital Imaging and Communication in Medicine (DICOM) header data can be used to perform dose audits with a high level of data accuracy. This study aims to show that using RIS data for dose audits is not only a viable alternative to using DICOM header data, but that it has advantages. A new system was developed to pull header data from DICOM images easily and was installed on a workstation within a hospital department. Data were recovered for a common set of examinations using both RIS and DICOM header data. The data were compared on a result-by-result basis to check for consistency of common fields between RIS and DICOM, as well as assessing the value of data fields uncommon to both systems. The study shows that whilst RIS is not as accurate as DICOM, it does provide enough accurate data and that it has other advantages over using a DICOM approach. These results suggest that a 'best of both worlds' may be achievable using Modality Performed Procedure Step (MPPS).

A preliminary study into performing routine tube output and automatic exposure control quality assurance using radiology information system data

Data are currently being collected from hospital radiology information systems in the North West of the UK for the purposes of both clinical audit and patient dose audit. Could these data also be used to satisfy quality assurance (QA) requirements according to UK guidance? From 2008 to 2009, 731 653 records were submitted from 8 hospitals from the North West England. For automatic exposure control QA, the protocol from Institute of Physics and Engineering in Medicine (IPEM) report 91 recommends that milliamperes per second can be monitored for repeatability and reproducibility using a suitable phantom, at 70-81 kV. Abdomen AP and chest PA examinations were analysed to find the most common kilovoltage used with these records then used to plot average monthly milliamperes per second with time. IPEM report 91 also recommends that a range of commonly used clinical settings is used to check output reproducibility and repeatability. For each tube, the dose area product values were plotted over time for two most common exposure factor sets. Results show that it is possible to do performance checks of AEC systems; however more work is required to be able to monitor tube output performance. Procedurally, the management system requires work and the benefits to the workflow would need to be demonstrated.