Empowering facilities to capture more incidental pulmonary nodules and identify lung cancer earlier is at the heart of what Eon does every day. That’s why Eon expanded its data science models to now identify incidental pulmonary nodules on Magnetic Resonance (MR) and X-Ray radiology reports in addition to CT.
Eon Patient Management platform uses Computational Linguistics to identify incidental pulmonary nodules on computed tomography (CT) reports with 98.95% accuracy, and 97% accuracy on MR and X-Ray radiology reports. This game-changing update allows facilities to capture approximately 25% more incidental pulmonary nodules and empowers providers to identify lung cancer earlier when treatment is most effective.
Eon uses Computational Linguistics, a data science discipline that interprets text similar to how the human brain does, to engineer the most advanced models on the market today. This approach allows providers to positively identify and track incidental pulmonary nodules with more accuracy than other forms of artificial intelligence like Natural Language Processing (NLP) and Computer Aided Detection (CAD). The technology is developed by a team of physicians and data scientists to provide incidental patient identification and management solutions with embedded evidence that decrease administrative burden and improve patient adherence to follow-up exams.
“By expanding our linguistics model, we now offer the most sophisticated solution on the market for early detection of lung cancer.”
— Dr. Erika Schneider, Chief Science Officer at Eon
With Eon’s proprietary Computational Linguistics data science model, EPM also extracts clinically relevant findings from radiology reports. The IPN model documents nodule location and characteristics like density, shape, edge, and calcification and automatically populates the information into the EPM dashboard. This allows evidence-based Fleischner Society guidelines to be automatically applied to create an actionable worklist. This approach helps providers by removing excess noise (false positives, low-risk nodules), ensures appropriate patient tracking, and automates complex follow-up.
Schneider adds, “Computational Linguistics is the gold standard for language understanding, in particular for lung nodule identification and characteristics extraction. By embedding evidence, the nodule characteristics focus providers’ attention on patients with a high probability of having lung cancer. The high accuracy and reproducibility of our model reduces false positives and does not require radiologists to use a structured report. This approach, along with the embedded risk prediction and automation, should enable providers to prioritize patients and improve their outcomes.”
Eon continues to be at the forefront of raising the bar on incidental disease identification and management solutions. And, expanding its data science models to multiple radiology modalities is another way to identify catastrophic disease earlier and improve patient outcomes.
