Using a combination of Natural Language Processing (NLP) and deep learning algorithms powered by emtelliPro™, DxPro’s Medical Language Understanding automatically correlates cross-functional, multi-disciplinary relationships from within the unstructured text of radiology, cardiology, and pathology reports to inform quality improvement programs and clinical research initiatives.

DxPro engine, which extracts clinical insights according to multiple ontologies including SNOMED, RadLex, and others, and even supports custom concepts. Feature extraction includes report segment, experiencer, negation, uncertainty, and development is underway for high-quality extraction of questions, additional relationship extraction (e.g. disease site, severity), and higher-level quality assurance (QA) features such as patient follow-ups, report compliance, and imaging appropriateness.

DxPro allows you to easily identify clinical insights from within narrative diagnostic reports in real-time to quickly identify individual diagnoses or multiple associated comorbidities using RadLex and SNOMED dictionaries using free text or concept terminologies.

Automatically identify and stratify patient cohorts for clinical investigation, population health research, teaching, and AI/ML development.

Proactively monitor follow-up recommendations to ensure timely adherence to procedure and timeframe directions and avoid medicolegal risk.

Referring Physician Case Reporting provides deeper insights into your referral patterns to better mange imaging appropriateness and resource planning.

Simplify resident and fellow training programs by automatically tracking condition or procedure based metrics against defined targets in a consolidated dashboard.