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
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 type | R21 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Univ of Massachusetts Med Sch Worcester NIH-funded |
| Lab location | 1 site (Worcester, United States) |
| Project ID | NIH-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
- Univ of Massachusetts Med Sch Worcester — Worcester, United States (Active)
Researchers
- Principal investigator: Liu, Feifan — Univ of Massachusetts Med Sch Worcester
- Study coordinator: Liu, Feifan
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.