Early Detection of Lung Cancer through AI Algorithm
A new study published in the British Journal of General Practice suggests that GPs may soon be able to identify patients with an increased risk of lung cancer up to 4 months earlier than is currently possible. Researchers at Amsterdam UMC have created an algorithm that analyzes medical information from general practice, including unstructured notes made by GPs over the years.
The algorithm has been developed based on data from more than half a million patients and can pick up predictive signals from patients’ medical history. “The algorithm identifies a large proportion of these patients up to 4 months earlier than is currently the case,” says Martijn Schut, Professor of Translational Artificial Intelligence at Amsterdam UMC.
Unlike other studies that used predefined and coded variables, such as ‘smoking’ or ‘coughing up blood’, this algorithm analyzes the GP’s notes, which contain rich information about the patients’ history. “With this information, we can detect patients with cancer much earlier thanks to the algorithm,” adds Ameen Abu Hanna, Professor of Clinical Information Science at Amsterdam UMC.
The study analyzed the files of 525,526 patients, of which 2,386 were diagnosed with lung cancer. The algorithm was able to identify 62% of patients with lung cancer 4 months earlier than current methods. This early detection could significantly improve survival rates and quality of life for patients, as well as reduce costs.
Lung cancer remains one of the most common cancers with a poor prognosis, having a 5-year mortality rate above 80%. Previous research has shown that receiving a diagnosis just four weeks earlier already has a noticeable effect on the forecast. Therefore, a four-month gain is likely to be very relevant.
While the algorithm shows promising results, further research is needed to validate its effectiveness in different countries and healthcare systems. The method may also offer relief for other types of cancer that are often diagnosed at an advanced stage, such as pancreatic, stomach, or ovarian cancer.
The development of this algorithm is a significant step forward in the early detection of lung cancer. By identifying patients at risk earlier, GPs can refer them for further investigation and treatment, potentially improving outcomes and reducing mortality rates.
