London (EMS). Doctors, scientists and researchers have created an artificial intelligence model that can accurately identify cancer. According to a report, researchers say that this can speed up the diagnosis of the disease and fast-track patients for treatment. Cancer is a leading cause of death worldwide.
According to the World Health Organization, it results in about 10 million deaths annually. However, in many cases, the disease can be cured if detected early and treated swiftly. An AI tool designed by experts from the Royal Marsden NHS Foundation Trust, the Institute of Cancer Research, London and Imperial College London can identify whether an abnormal growth found on a CT scan is cancer or not. According to a study, the algorithm currently Works more efficiently and effectively than other methods. The team used CT scans of nearly 500 patients with large lung nodules to develop the AI algorithm using radiomics. The technology can extract important information from medical images that is not easily seen by the human eye.
The AI model was tested to determine whether it could correctly identify cancerous nodules. The study used a measure called Area Under the Curve to see how effective the model was at predicting cancer. 1 area under the curve indicates a perfect model, while 0.5 area under the curve would be expected if the model was estimating randomly. The results showed that the AI model could identify the risk of cancer for each nodule with an AUC of 0.87.
According to these preliminary results, the model can accurately identify large lung nodules of cancer. The AI model could help doctors make quicker decisions about patients with abnormal growths who are currently considered moderate-risk. It is known that many times cancer patients die because the machine delays in detecting the disease. However, now the picture is about to change.
