With the help of artificial intelligence, computers are to simulate human thought processes. Machine learning is intended to support almost all medical specialties. But what is going on inside an AI algorithm, what are its decisions based on? Can you even entrust a medical diagnosis to a machine? Clarifying these questions remains a central aspect of AI research and development.
Radiology practices have a high volume of chest X-rays without clinically significant finding, which take up a lot of time. A new AI tool could improve workflows by providing an automatic report.
Artificial intelligence (AI) can be used to great effect in colonoscopies to spot abnormalities potentially leading to bowel cancer. This is the result of the recently completed COLO-DETECT trial.
Enter symptoms into ChatGPT, receive an accurate diagnosis? Research reveals that LLM AI models are not quite there yet, struggling to identify genetic conditions from patient-written descriptions.
Artificial Intelligence will be a critical component in ensuring a Europe-wide lung cancer screening programme can achieve its potential, according to speakers at a special ECR 2024 session. Delegates heard that the SOLACE project (Strengthening the screening of Lung Cancer in Europe) will be supported by AI in terms of workflow, diagnostics, and image and data analysis. Presentations in the…
Combining risk markers, systematic evaluation of MRI images and AI, researchers aim to predict the risk of prostate cancer more accurately than before. This could save many patients from a biopsy.
The interpretation of prostate MRI is notoriously difficult. Annotating AI shows promise to help improve diagnostic performance through increased cancer detection rates with fewer false positives.
As the adoption of AI into healthcare continues, concerns about the environmental impact of increasingly complex AI models grow. Therefore, researchers are looking for more sustainable AI solutions.
Dermatologists could benefit from a new algorithm that can help recognize patients with a highly aggressive form of basal cell carcinoma (BCC) of the face.
Researchers at MIT and ETH Zurich developed an AI model that identifies certain breast cancer stages likely to progress to invasive forms of cancer.
The pace of artificial intelligence (AI) adoption in personalised medicine is unsettling for great parts of the public. A new survey reflects the worried state of mind in the UK.
Can an AI predict the progression of multiple sclerosis in a patient over the subsequent months and years? Researchers in Belgium used machine learning to do just that – with promising results.
AI models perform increasingly well in answering medical questions. However, when it comes to explaining these answers, shortcomings become apparent, a new study shows.
Cancer, dementia, heart attack: these are the medical conditions people are most worried about, according to a new UK survey. It also reveals hopes for AI in the future of cancer research and care.
New research shows that the AI large language model ChatGPT can be tailored to provide accurate responses to questions about digital pathology and compile detailed results.
Ductal Carcinoma in Situ (DCIS) often develop into more invasive forms of breast cancer. To predict which DCIS patients are likely to be affected, researchers have developed an analytic AI-based tool.
From 45 minutes to just a few seconds: A new computer model utilises AI to examine cardiac MRI scans in the four-chamber plane, potentially offering speedy and dependable heart health evaluation.
Measuring temperatures in different face regions could be used to earlier detect chronic illnesses, such as diabetes and hypertension. Researchers now show the potential of an AI-based approach.
The huge amount of data generated by modern MRI scanners presents challenges in storage, accessibility, and security. To that end, Chinese researchers have developed a cloud MRI system.
Researchers have developed an AI model that increases the potential for detecting cancer through sugar analyses. The AI model is faster and better at finding abnormalities than current methods.
