Google-based search tool mines RIS data

Article

Radiology text and image data account for a significant portion of patient electronic medical record information in hospital archives, yet few means exist to aid radiologists in extracting relevant information from these databases.

Radiology text and image data account for a significant portion of patient electronic medical record information in hospital archives, yet few means exist to aid radiologists in extracting relevant information from these databases.

Recent work adds a new data mining tool in the form of a secure Google-based search engine.

"Radiologists are just scratching the surface of utilizing the information that exists in their RIS/PACS archives," said Dr. Joseph P. Erinjeri, an interventional radiology fellow at New York Presbyterian Hospital and Memorial Sloan-Kettering Cancer Center.

While most RIS provide some degree of report search capability, until now it was never easy to figure out how to get the desired information.

Erinjeri and colleagues created a free open source Google-like interface called Radsearch to mine their RIS. They applied Google's core search technologies to do the actual searching.

"This tool is different from methods we've used to search our RIS in the past. It lets the user skip the step of first creating a custom-designed SQL query, a step that took considerable time and expense because our information systems staff was needed to perform it," he said.

With Radsearch, users can create their query in a more familiar way, by typing in keywords or phrases and letting Google's algorithms do the work.

Radsearch employs the Google Desktop application programmers interface. This provides access to Google's core search technologies while retaining the ability to customize the application for use in radiology.

Since Radsearch is RIS/PACS-specific, details of how to get this type of schema to work will be different at each institution. The paper describes how to create this type of application using Google's free enterprise software.

Storing data in PACS and RIS archives was a monumental step in improving the quality of care that radiologists provide, Erinjeri said. The next step in that process is to create tools that let users access the information more efficiently, whether for treatment, teaching, or research.

"It's important to remember that what made the Internet take off in the late 1990s was not the digital storage; it was the ability to search and instantly find information," he said.

The goal of this work is to allow radiologists to directly and efficiently mine data from years of radiology reports while at the same time protecting patient privacy, according to Erinjeri.

"Radiologists have always been on the forefront of using technology to improve patient care," he said. "This class of tools will help us continue to do so."

Recent Videos
Can AI Assessment of Longitudinal MRI Scans Improve Prediction for Pediatric Glioma Recurrence?
A Closer Look at MRI-Guided Adaptive Radiotherapy for Monitoring and Treating Glioblastomas
Incorporating CT Colonography into Radiology Practice
What New Research Reveals About Computed Tomography and Radiation-Induced Cancer Risk
What New Interventional Radiology Research Reveals About Treatment for Breast Cancer Liver Metastases
New Mammography Studies Assess Image-Based AI Risk Models and Breast Arterial Calcification Detection
Can Deep Learning Provide a CT-Less Alternative for Attenuation Compensation with SPECT MPI?
Employing AI in Detecting Subdural Hematomas on Head CTs: An Interview with Jeremy Heit, MD, PhD
Pertinent Insights into the Imaging of Patients with Marfan Syndrome
What New Brain MRI Research Reveals About Cannabis Use and Working Memory Tasks
Related Content
© 2025 MJH Life Sciences

All rights reserved.