Adding modality work list management to a filmless imaging department cut the CT transmission error rate in half, according to a study conducted at the Baltimore VA Medical Center. Most of the improvement came through the elimination of data entry
Adding modality work list management to a filmless imaging department cut the CT transmission error rate in half, according to a study conducted at the Baltimore VA Medical Center. Most of the improvement came through the elimination of data entry mistakes by technologists.
The study presented in June at the Symposium for Computer Applications in Radiology joins a growing body of evidence suggesting that more fully integrated systems can add efficiency to the filmless image reading process.
Another study presented at the symposium found that integrating a radiology information system with direct radiography can reduce processing time to less than one-third that required with a fast x-ray system. Most of the time savings came from eliminating film processing, but study authors said the RIS was responsible for 30% of the speed improvement.
In the Baltimore VA study, the error transmission rate had been 7.6% in a department that was generating more than 8000 CT exams per year, said Steve Severance, one of the authors. After work list management was added, the error rate dropped to 3.5%. Shifting from a shared to a switched Ethernet system for transmitting the images reduced the error rate to just 2%.
Human error accounted for more than two-thirds of failed transmissions before the changes but just 16% after. Installation of the switched Ethernet probably reduced time outs that resulted from network collisions, the researchers said.
Assuming that transmission errors result in 20 minutes of lost time per exam, the improvements slashed lost technologist and radiologist time from 25 working days to just seven.
The researchers credit the improvements to a recently adopted standard for work list modality management. The new DICOM standard makes it possible to synchronize medical imaging data with other types of patient data, including demographics. Rather than having the technologist enter data, possibly introducing error, he or she simply selects the patient from a work list on a computer screen. Data from the scan is then attached to patient data that was entered earlier.
The study comparing a RIS-enabled DR system to conventional x-ray was conducted at the Cleveland Clinic. Processing time for conventional x-ray was 307 minutes, more than half of it in film development time, said Gerald A. May, Ph.D., chief author and an employee at the Cannon Research Center in Palo Alto, CA. Processing time for DR was 142 minutes. Adding a RIS with work list modality management brought the figure down to 98 minutes.
Can AI Enhance PET/MRI Assessment for Extraprostatic Tumor Extension in Patients with PCa?
December 17th 2024The use of an adjunctive machine learning model led to 17 and 21 percent improvements in the AUC and sensitivity rate, respectively, for PET/MRI in diagnosing extraprostatic tumor extension in patients with primary prostate cancer.
Can Radiomics Bolster Low-Dose CT Prognostic Assessment for High-Risk Lung Adenocarcinoma?
December 16th 2024A CT-based radiomic model offered over 10 percent higher specificity and positive predictive value for high-risk lung adenocarcinoma in comparison to a radiographic model, according to external validation testing in a recent study.