Doctors may soon have the capability to detect and diagnose cancer in patients using artificial intelligence (AI), enabling earlier treatment, according to a new study.
Early detection could significantly improve patient outcomes, as cancer is treatable or curable if detected at an early stage
Published in the journal Biology Methods and Protocols, the study by researchers from Cambridge University and Imperial College London describes how an AI model was trained using machine and deep learning techniques to examine “DNA methylation” patterns. This model successfully identified 13 different types of cancer, including breast, liver, lung, and prostate cancers, from non-cancerous tissue with 98.2 percent accuracy.
“Genetic information is encoded in DNA by patterns of the four bases — denoted by A, T, G, and C — that make up its structure. Environmental changes outside the cell can cause some DNA bases to be modified by adding a methyl group. This process is called ‘DNA methylation’,” the researchers explained. Each cell contains millions of these DNA methylation marks, and changes to these marks have been observed in the early development of cancer, potentially aiding in early cancer diagnosis.
“Computational methods such as this model, through better training on more varied data and rigorous testing in the clinic, will eventually provide AI models that can help doctors with early detection and screening of cancers,” said the paper’s lead author, Shamith Samarajiwa. “This will provide better patient outcomes,” he added. The researchers also mentioned that identifying these unusual methylation patterns, potentially from biopsies, would allow healthcare providers to detect cancer early. Early detection could significantly improve patient outcomes, as most cancers are treatable or curable if detected at an early stage, they added.