When it comes to detecting certain diseases, it can be a bit of a mixed bag because humans can make errors. For example when it comes to detecting breast cancer, current methods actually have pretty high rates of false positives. While it is better to be safe than sorry, the downside is that false positives can lead to stress on the patient’s end and potentially unnecessary medical interventions.
This is where the use of AI comes in, and according to Google, DeepMind has developed an AI model in which it can detect breast cancer from scans with fewer false positives compared to experts. The AI was fed scans and data from patients in both the US and the UK, where it eventually trained itself to detect breast cancer with 5.7% fewer false positives and 9.4% false negatives.
What this means is that in the future, AI could become the new method used to detect health problems like breast cancer, where the reduction in false positives and negatives could help save patients stress, and also potentially catch the problem early on. This is not the first time that Google’s DeepMind has been used to detect breast cancer.
Google is also not alone on this front, where other companies such as IBM have also been working on similar detection models.