Radiologists used AI to categorize breast cancer findings within x-rays in a study with conflicting results — and some misinformation could put patients at risk. Here is detail from a new study.
As part of the study, 27 radiologists read 50 mammograms and provided their Breast Imaging Report and Data System assessment toThe AI system’s prediction had a significant impact on the accuracy of every group of radiologists.
The AI system’s prediction had a significant impact on the accuracy of every group of radiologists . Readers were more likely to assign an incorrect BI-RADS category when the AI system suggested the same category — and vice versa, as HealthImaging.com pointed out in its analysis of the study. The study concluded that when radiologists used AI-suggested categories to assign BI-RADS scores, they — the radiologists — performed worse than when they did it on their own.
Even experienced radiologists were negatively influenced when giving BI-RADS category results, the study found.
France Dernières Nouvelles, France Actualités
Similar News:Vous pouvez également lire des articles d'actualité similaires à celui-ci que nous avons collectés auprès d'autres sources d'information.
New study finds ChatGPT outperforms doctors in giving 'empathetic' adviceA panel of licensed health-care professionals preferred the chatbot’s responses to nearly 200 inquiries 79 percent of the time.
Lire la suite »
Many California hospitals are near wildfire danger zones, study saysWildfires regularly sweep through California, destroying forests and threatening homes. But a recent study shows an unexpected danger of the fires: They can shut down, or prevent access to, hospitals and other inpatient facilities.
Lire la suite »
Quiet and parents' touch help opioid users' newborns: studyNew research shows that babies born to opioid users have shorter hospital stays when care includes more parent involvement and a quieter environment.
Lire la suite »
Quiet and parents' touch help opioid users' newborns: studyNew research shows that babies born to opioid users have shorter hospital stays when care includes more parent involvement and a quieter environment.
Lire la suite »
Comparative study of adaptive variational quantum eigensolvers for multi-orbital impurity models - Communications PhysicsQuantum embedding approaches to simulate condensed matter on quantum computers have been proposed, yet applications are limited to simplest models. The authors perform a systematic study of ground state preparation with variational quantum algorithms for correlated multi-orbital impurity models, addressing key issues toward real materials simulations.
Lire la suite »