One of the most promising applications of artificial intelligence (AI) in healthcare is disease prediction. By analyzing vast amounts of data from patient records, biometric sensors, and other sources, AI can identify patterns and risk factors that might otherwise escape notice. And now, a new study published in the journal Scientific Reports has shown that AI can predict the onset of diseases up to six years before a clinical diagnosis.

The study, which was conducted by researchers at the University of Oxford and the University of San Francisco, used machine learning to analyze electronic health records from over 25,000 patients in the UK. The data covered periods ranging from one to 30 years prior to each patient’s first diagnosis of one of 11 common diseases, including diabetes, coronary artery disease, and dementia.

Using this data, the AI algorithm was able to identify which patients were likely to develop each disease, even years before their diagnosis. For example, the algorithm was able to predict the onset of dementia with an accuracy of 75