0
0
A groundbreaking study published in JAMA Cardiology on January 15, 2025, reveals that artificial intelligence (AI) can empower trained healthcare professionals (THCPs)—such as medical assistants, respiratory therapists, and nurses—to acquire lung ultrasound (LUS) images with diagnostic quality on par with expert practitioners. The research, led by Dr. Cristiana Baloescu from Yale University School of Medicine, highlights the transformative potential of AI in expanding access to high-quality diagnostic tools, especially in areas lacking expert personnel.
In a multicenter diagnostic validation study, participants aged 21 and older with shortness of breath were recruited from four clinical sites. Each participant underwent two LUS examinations: one conducted by a THCP using Lung Guidance AI and the other by a trained expert. Before performing the ultrasound procedures, THCPs received standardized training in AI-assisted LUS acquisition.
The results were impressive: 98.3% of the LUS images captured by THCPs were deemed of diagnostic quality. This performance showed no significant difference from the diagnostic quality of images obtained by expert practitioners, with a minimal difference of 1.7% (95% confidence interval: −1.6 to 5.0%).
The study’s findings suggest that AI can significantly enhance the diagnostic capabilities of healthcare workers in environments where expert ultrasound practitioners may be unavailable. “THCPs aided by AI achieved comparable performance to expert LUS users in acquiring images meeting diagnostic standards following brief software-focused training,” the authors noted.
This innovative use of AI has the potential to democratize access to diagnostic imaging, particularly in underserved regions and emergency settings where the presence of skilled LUS professionals may be limited. The study’s results are expected to pave the way for broader implementation of AI-guided diagnostic tools in clinical practice, improving patient care and outcomes worldwide.
However, the study authors also disclosed financial ties to the pharmaceutical and healthcare industries, raising questions about the influence of industry partnerships on the development and application of AI technologies in healthcare.
For more information, refer to the original study: Artificial Intelligence–Guided Lung Ultrasound by Nonexperts in JAMA Cardiology (DOI: 10.1001/jamacardio.2024.4991).
