Scientists develop new AI system to identify patients with bowel cancer

Scientists have come up with a new artificial intelligence (AI) system to identify patients with bowel cancer. The new Artificial Intellgience system claims to help identify patients with bowel cancer. This technique may help predict the severity of the malignant disease. In a study published in the journal Science Translational Medicine, scientists have described the method and added to advances in technologies that analyse circulating tumour DNA (ctDNA).

READ | Artificial Intelligence performs better than expert radiologists in spotting breast cancer

According to researchers from the Huazhong University of Science and Technology in China, the new Artificial Intelligence system can help spot bowel cancers in at-risk patients at earlier stages. Researchers said the type of cancer is most treatable if it is detected before they have spread to other sites in the body.

READ | IIT-Hyd researchers unravel protein that repairs damaged DNA

Although Colonoscopy is regarded as the "gold standard" for diagnosis, scientists said the procedure is uncomfortable and invasive and can lead to complications, which makes patients unwilling to undergo screening at times. The scientists leveraged Artificial Intelligence techniques, where systems self-learned to perform specific tasks without explicit instructions, to develop a less invasive diagnostic method that can detect bowel cancer in at-risk patients.

READ | Malaria carrying mosquitoes sense insecticide with leg proteins: Study

According to the study, the technology works by screening for methylation markers, which are chemical modifications to DNA which are frequently found in tumours. The researchers first created a diagnostic model based on nine methylation markers associated with bowel cancer, which they identified by studying samples of the blood component plasma from 801 patients with malignant disease, as well as 1,021 controls.

READ | Inheritance prediction card designed for sickle cell Anaemia & Thalassemia

This model accurately distinguished patients from healthy individuals with a sensitivity of 87.5 per cent, and outperformed a clinically available blood test named CEA. With longer follow-up periods, the researchers said the machine learning model needs to be further assessed for reliability in detecting tumour in patients.

READ | 'Brain circuit involved in impulsive feeding behaviour found'

(With PTI inputs)