Breast cancer is a lethal disease. It is so dangerous that in Britain, as a precautionary measure Women aged above 50 are advised to get a mammogram every three years. Two independent experts analyze the results. However, as a human, there is always a chance of error. Humans can do a mistake and can diagnose a healthy person with breast cancer due to misinterpreting the scans. Recently, it has been discovered that Artificial Intelligence can better diagnose Breast Cancer than humans.
Google Health Initiative
Woman in early stages of breast cancer do not show any sign that’s why they are advised to undergo regular screening. Regular screening helps to detect breast cancer at an early stage. In order to give women more protection and better health facilities, researchers at Google Health have trained a model that can detect breast cancer from scans from thousands of women in Britain and the United States. This computer program can detect breast cancer more accurately than human experts. Researchers are very happy about their success and hope that it will prove to be a breakthrough innovation in fight against this global killer.
Experts have also reviewed the results of the AI model and were surprised to know that even though the model had no idea about the previous history of the patient, still it managed to diagnose cancer like experts. It has also helped to reduce misdiagnose of breast cancer in the United States by 9.4 percent and in Britain by 2.7 percent. It also reduced cases of incorrect identification in the United States by 5.7 percent and in Britain by 1.2 percent.
In Britain, all mammograms are reviewed by two radiologists, which is though necessary but labor-intensive process. According to Dominic King, UK lead at Google Health, “The earlier you identify the breast cancer the better it is for patient. We think about this technology in a way that supports and enables an expert, or a patient ultimately, to get the best outcome from whatever diagnostics they’ve had”.
The results from AI model were also compared with that of human scan reader by the team at Google Health.