AJMC October 10, 2024
Key Takeaways
- Artificial intelligence (AI) models ChatGPT-3.5 and DoximityGPT were evaluated for diagnosing pulmonary embolism, showing alignment with clinical diagnoses.
- DoximityGPT, tailored for health care, demonstrated higher diagnostic accuracy than ChatGPT-3.5, matching clinical diagnoses in 7 out of 10 cases.
- Both AI models offered risk stratification and management recommendations aligning with clinicians’ assessments, even when initial diagnoses differed.
Artificial intelligence (AI) is emerging as a transformative tool in health care, with the possibility to enhance clinical decision-making and disease management. At the CHEST 2024 annual meeting in Boston, late-breaking data showcased the potential of AI-based systems in diagnosing and managing pulmonary embolism (PE).
The study, presented by Zeina Morcos, MD, an internal medicine resident at Staten Island University...
Today's Sponsors
Today's Sponsor