Researchers at Harvard Medical School have developed an automated report monitoring system that eases the task of keeping track of radiology cases for clinical and teaching purposes.
Researchers at Harvard Medical School have developed an automated report monitoring system that eases the task of keeping track of radiology cases for clinical and teaching purposes.
"The system we developed allows users to automate case-tracking for clinical follow-up or teaching purposes," said Chun-Shan Yam, Ph.D., a radiology instructor at Harvard Medical School.
Under the system, radiologists can collect reports for their tracking cases on the fly while dictating. Case-tracking can be initiated by dictating a keyword into the report. Any existing and future reports associated with the same patient will then automatically be collected. Yam described the system in the January issue of the American Journal of Roentgenology.
"Keeping track of radiology cases is time-consuming," he said. "Normally, radiologists must remember the patient's name or ID number, or make a note for tracking, which is why you often find bunches of little papers in radiologists' lab coats."
An automated system can streamline clinical workflow, reduce concerns about Heath Insurance Portability and Accountability Act compliance, and eliminate human error from writing and typing.
Because the report transfer is based on HL7, the only software requirement is the ability to receive HL7 reports. Yam uses commercially available software (LinkTool, LINK Medical Computing) and developed his system on a PC platform.
Any system that can perform TCP/IP communications, including Mac OS, Linux, and Unix, can use the report monitoring method. A number of commercial HL7 products are available on the Internet.
Although this system was initially designed for tracking teaching cases, its flexibility for creating custom functions allows it to also be used for other research activities and daily radiology practices, according to Yam.
"Because the system contains all the RIS reports, both preliminary and final, we are extending it for data mining and quality assurance," he said.
Could a Deep Learning Model for Mammography Improve Prediction of DCIS and Invasive Breast Cancer?
April 15th 2024Artificial intelligence (AI) assessment of mammography images may significantly enhance the prediction of invasive breast cancer and ductal carcinoma in situ (DCIS) in women with breast cancer, according to new research presented at the Society for Breast Imaging (SBI) conference.
MRI-Based AI Model Shows Promise in Predicting Lymph Node Metastasis with Breast Cancer
April 15th 2024For the prediction of axillary lymph node metastasis in patients with breast cancer, an MRI-based, 4D convolutional neural network model demonstrated an AUC of 87 percent and sensitivity of 89 percent, according to new research.