Radiologic Data Mining Platform Optimizes Value-Based Care

The cloud-based platform enables faster, easier access to actionable insights and provides advanced features, including a new quantitative findings analysis capability, which helps radiologists reduce care delays, evaluate merit-based incentive payment system (MIPS) measures, and strengthen quality improvement efforts.

By leveraging robust data mining algorithms, mPower transforms unstructured radiology reports to quickly provide radiologists access to detailed, actionable information in Nuance’s PowerScribe 360 reports and other clinical data sources. mPower can help radiologists decrease patient length of stay (LOS) by up to three days by tracking inpatient recommendations and facilitating interventional procedure care coordination, reducing inappropriate imaging by identifying outliers, guiding quality improvement, and reducing unnecessary ordering of images.

Other benefits include improved billing compliance, reimbursement, and outcomes documentation by facilitating MIPS and other regulatory reporting; automatic extraction of follow-up recommendations from reports in order to create detailed profiles for consistency, so as to remediate recommendation variability while identifying overdue examinations; help practice managers develop an operationally efficient organization that profitably delivers effective clinical care; and provide enhanced security, as the cloud-based platform is hosted in Microsoft (Redmond, WA, USA) Azure.

“Nuance understands the value-based challenges that radiologists currently face and how to harness technology to address them. When used to augment a radiologist’s work, Nuance’s mPower Clinical Analytics platform can triple the positive impact of recommendation tracking systems,” said Ben Wandtke, MD, MSc, chief of diagnostic imaging at FF Thompson Hospital (Canandaigua, NY, USA). “Not only does this cloud-based technology help optimize productivity and efficiency, it also improves compliance and increases technical revenue for radiology practices.”

The use of computational data mining techniques allows extraction of meaningful information from real-life clinical data, doing away with at least some of the subjectivity of clinical prognosis, and allowing epidemiology to work at the patient level more precisely. But data mining approaches often have inherent problems in that the classification of the data for information retrieval is based on decision-making learnt from examples set by doctors, and so they may incorporate the very subjectivity that the mining wishes to avoid.