Can we trust AI to read CXRs in Primary Care? 🤔
18 Apr 2024 • Radiological diagnosis is important across various specialities, and it is a common practice for primary care physicians interpret chest X-rays, despite their lower degree of expertise.
This fact highlights the need and, therefore, the opportunity to introduce tools such as artificial intelligence (AI) to support radiologists and other healthcare practitioners who need to interpret an X-ray.
A study published in Nature early this year aimed to externally validate an AI algorithm’s diagnoses in real clinical practice, comparing them to a radiologist’s diagnoses, which is considered the gold standard.👩🏻⚕️
🎓The findings of this study demonstrated accuracy, sensitivity and specificity of the AI algorithm and has proven to be useful by being able to identify images with or without abnormalities. However, further training is needed to increase the diagnostic capability of some of the conditions analysed.
For instance, the AI Algorithm confused a consolidation with mammary tissue and two nodules with the two mammary areolae.
✅ It is important that training is done in a real environment, with real images, in order to perform robust external validations.
‘Being able to reliably detect images without abnormalities can have a very positive impact, reducing waiting times for diagnoses, secondary tests to rule out conditions, streamlining practitioners work and, among others, ultimately favouring patient care and, indirectly, their health.’
👍The implementation of AI in healthcare appears to be an imminent reality that can offer significant benefits to both professionals and the general population. However, it is essential to implement safe and validated tools in clinical practice.