Using deep learning to improve the accuracy of radiology reports for diagnosing pulmonary embolism

DeepCertainty: Deep Learning for Contextual Diagnostic Uncertainty Measurement in Radiology Reports

NIH-funded research Univ of Massachusetts Med Sch Worcester · NIH-10909001

This study is working on making radiology reports clearer and more accurate for diagnosing pulmonary embolism, which is a serious heart condition, so that doctors can better understand the results and provide better care for patients.

Quick facts

Grant typeR21 grant
Study typeNIH-funded research
Funding institutionUniv of Massachusetts Med Sch Worcester NIH-funded
Lab location1 site (Worcester, United States)
Project IDNIH-10909001 on NIH RePORTER

What this research studies

This research focuses on enhancing the clarity and accuracy of radiology reports, specifically for diagnosing pulmonary embolism (PE), a serious cardiovascular condition. By employing a deep learning approach, the study aims to assess and communicate diagnostic uncertainty in radiology reports more effectively. The goal is to bridge the gap between radiologists' intended messages and how referring physicians interpret these reports, ultimately improving patient care. The methodology involves developing a system that is trainable, calibratable, and explainable, ensuring that it can adapt to various clinical contexts.

Who could benefit from this research

Good fit: Ideal candidates for this research are patients who are being evaluated for pulmonary embolism in emergency departments.

Not a fit: Patients who are not undergoing evaluation for pulmonary embolism or those with other unrelated medical conditions may not benefit from this research.

Why it matters

Potential benefit: If successful, this research could lead to more accurate diagnoses of pulmonary embolism, reducing misinterpretations and improving patient outcomes.

How similar studies have performed: Other research has shown promise in using machine learning techniques to improve diagnostic accuracy in radiology, indicating that this approach could be effective.

Where this research is happening

Worcester, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.