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.

AI company to develop radiology-specific LLM reporting assistant
The system will assist radiologists by identifying lesions and drafting a single-sentence, localization-aware report alerting readers to the finding.
Healthcare AI today: AMA drills into Trump plan, Illinois forbids AI talk therapy, Mayo Clinic speeds ahead (again)
The AMA doesn’t refute much of the Trump AI Action Plan so much as amplify some of its talking points. One exception is the plan’s open disdain for ‘woke’ AI.
Opportunistic AI screening for osteoporosis via chest X-ray is cost-effective, feasible
Researchers found clear benefit based on their modeling study while highlighting the need for real-world investigations to further enhance the accuracy of their estimates.
4 ways clinical AI can complement—rather than compete with—patient-centered care
If humanistic medicine is to endure the slow-motion AI tsunami flooding the healthcare landscape, humans will have to see those two forces—humanistic medicine and healthcare AI—not as oppositional to each other but as potentially synergistic.
New AI tool could expedite treatment decisions for glioblastoma patients
The method utilizes findings from PET/MR imaging to differentiate between changes in tissue owed to treatment versus tumor progression.

AI adoption is lagging in radiology and the rest of healthcare. Brookings experts answer why

Lack of trust in algorithms, challenges in data collection, and regulatory barriers are all impeding progress, the Washington-based research outfit argued.

AI-powered ECG analysis could boost care for patients with hypertrophic cardiomyopathy

Advanced algorithms can pick up on key details in a 12-lead ECG that human readers are unable to see.

AFib, AI and heart-healthy diets: European Society of Cardiology previews EHRA 2022

The European Heart Rhythm Association's annual conference is headed to Denmark.

FDA greenlights AI software that detects fractures and traumatic injuries

A study published by Boston University School of Medicine revealed that fracture detection improved for readers by 10.4% with BoneView AI's assistance.

Regulators clear final hurdle in Microsoft’s $19.7B acquisition of Nuance Communications

Company officials said recently that they hope to close the mega merger deal by the end of March.

Deep learning model triages brain MRIs for abnormalities to prioritize reads

The deep learning model was trained to recognize abnormalities in real-time, reducing delays in image interpretation for clinically relevant findings.

Multimodal AI platform can accurately diagnose and stage thyroid cancer via ultrasound images

The platform was developed using a combination of four different AI methods, according to research presented at the 2022 Multidisciplinary Head and Neck Cancers Symposium.

AI can identify significant findings on scanned radiology reports, reduce manual workloads

Researchers created an automated pipeline that can spot clinically significant abnormalities that would require follow-up on documents scanned into the EHR.

Artificial Intelligence

AI company to develop radiology-specific LLM reporting assistant

Healthcare AI today: AMA drills into Trump plan, Illinois forbids AI talk therapy, Mayo Clinic speeds ahead (again)

Opportunistic AI screening for osteoporosis via chest X-ray is cost-effective, feasible

4 ways clinical AI can complement—rather than compete with—patient-centered care

New AI tool could expedite treatment decisions for glioblastoma patients