CAN ARTIFICIAL INTELLIGENCE PREDICT THE RISK OF PANCREATIC CANCER USING DISEASE TRAJECTORIES?
Researchers used artificial intelligence (AI) approaches on real-world longitudinal clinical data to build monitoring programmes for the early diagnosis of individuals at high risk of pancreatic cancer, one of the most aggressive illnesses. CONCERNING THE RESEARCH The current study employed real-world longitudinal health records from a large number of patients to identify several people at high risk of pancreatic cancer. They used patient information from the Danish National Patient Registry (DNPR) and, later, the United States Veterans Affairs (US-VA) Corporate Data Warehouse (CDW) to apply freshly discovered machine learning (ML) algorithms. The former included clinical data from 8.6 million patients between 1977 and 2018, equivalent to 24,000 pancreatic cancer cases, and the latter included clinical data from three million patients, corresponding to 3,900 pancreatic cancer cases. The researchers developed and evaluated a wide range of machine learning models on the sequence of ill