According to the study published in the journal Biology Methods & Protocols, researchers at the University of Cambridge and Imperial College London trained an AI mode using a combination of machine and deep learning to look at "DNA methylation" patterns and identify 13 different types. Gave. Detects cancer—including breast, liver, lung and prostate cancer—cancerous tissue with 98.2 percent accuracy.
"Genetic information is encoded in DNA by a pattern of four bases, T, G and C. Due to environmental changes outside the cell some DNA bases can be modified by adding methyl groups. This process is called 'DNA methylation' Is." The researchers explained.
Every cell contains millions of DNA methylation marks. Researchers have observed changes in these markers in early cancer development; They can help in early diagnosis of cancer.
Shamith Samarajiva, lead author of the paper, said, "Computational methods like this model, through better training on more diverse data and rigorous testing in the clinic, will ultimately provide AI models that can help doctors detect and screen cancer early." Are."
“This will provide better outcomes for patients,” he said.
Additionally, the researchers noted that identifying these abnormal methylation patterns (possibly from biopsies) would help healthcare providers detect cancer early.
He said this could potentially dramatically improve patient outcomes, as most cancers are curable if detected early.
"Genetic information is encoded in DNA by a pattern of four bases, T, G and C. Due to environmental changes outside the cell some DNA bases can be modified by adding methyl groups. This process is called 'DNA methylation' Is." The researchers explained.
Every cell contains millions of DNA methylation marks. Researchers have observed changes in these markers in early cancer development; They can help in early diagnosis of cancer.
Shamith Samarajiva, lead author of the paper, said, "Computational methods like this model, through better training on more diverse data and rigorous testing in the clinic, will ultimately provide AI models that can help doctors detect and screen cancer early." Are."
“This will provide better outcomes for patients,” he said.
Additionally, the researchers noted that identifying these abnormal methylation patterns (possibly from biopsies) would help healthcare providers detect cancer early.
He said this could potentially dramatically improve patient outcomes, as most cancers are curable if detected early.
