Artificial Intelligence

Artificial intelligence (AI) is becoming a crucial component of healthcare to help augment physicians and make them more efficient. In medical imaging, it is helping radiologists more efficiently manage PACS worklists, enable structured reporting, auto detect injuries and diseases, and to pull in relevant prior exams and patient data. In cardiology, AI is helping automate tasks and measurements on imaging and in reporting systems, guides novice echo users to improve imaging and accuracy, and can risk stratify patients. AI includes deep learning algorithms, machine learning, computer-aided detection (CAD) systems, and convolutional neural networks. 

Thumbnail

Deep learning applied to chest radiographs efficiently identifies early interstitial lung disease

The results could lead to expanded use of chest radiography in interstitial lung disease clinics, experts reported in the American Journal of Roentgenology.

AI scores 1 against a knee injury common among athletes

The AI development team was guided by a sports-medicine specialist dubbed “the go-to orthopedic surgeon for many of the greatest athletes on the planet.”

Thumbnail

New AI technology developments consistently recognize medical image anomalies

Promising new research methods have been able to train AI to more accurately spot image anomalies.

2-year chatbot mission unites scores of co-developers, yields ‘trustworthy and friendly Rosa’

Women’s health specialists have demonstrated the customization of a commercial AI-based chatbot platform for patients with hereditary breast and ovarian cancer. The pilot project took many hands and much manual labor to complete, but the team suggests the effort has been worth the payoffs.

AI has far to go before solving deafness, but along the way are opportunities to ‘reshape hearing healthcare’

AI technologies likely can go only so far toward improving on hearing aids and cochlear implants. However, AI and hearing experts expect fertile grounds to open for exploration in clinical as well as research arenas.

Americans wary of face recognition technology in healthcare

Only two-thirds of U.S. healthcare consumers are OK with surgeons using digital facial recognition to avoid medical error by confirming patient identity.

Artificial intelligence matches radiologists at predicting patients’ emphysema severity

Outputs from the assessed AI prototypes were robust across different scanners, though larger patients posed challenges, experts wrote in Academic Radiology

Thumbnail

Why deep learning trained on radiologist-labeled data may be worth added time, costs

This proved true for detecting pneumothorax, as networks developed on hand-labeled images outperformed tools refined via natural language processing.