Using artificial intelligence in a primary care setting to identify patients at risk for cancer: a risk prediction model based on routine laboratory tests

Risk prediction models may help healthcare providers, including GPs, in the process of clinical decision making by estimating the probability of specific outcomes in a population. In primary care, they have potential to impove the early diagnosis of cancer, which can lead to a better prognosis and lower mortality. This Danish study evaluated the ability of an artificial intelligence (AI) model to predict the risk of cancer in patients referred from primary care based on routine blood tests. A panel of 25 pre-determined routine blood tests was validated using test data collected from an area with 350,000 inhabitants that was served by 106 GPs. Overall, the study found that the risk score produced by the AI could be a valuable tool in the clinical decision-making but needed to be further validated to assess its applicability in other populations. Read the full paper here.