An artificial intelligence-based blood test that can identify cancer has been developed as a result of a recent study involving 724 patients.
In a 2021 study, researchers were able to categorize lung cancer thanks to blood testing techniques.
DNA from cancer cells is released into the bloodstream, and DELFI can spot the alterations. The kind of DNA is cell-free DNA. By counting and analyzing the genomes present in a blood sample, researchers can learn more about how DNA is stored inside cells. These discoveries can aid in the differentiation between healthy cells and cancer cells since malignant cells die and leak DNA fragments into the bloodstream. By using artificial intelligence and machine learning to search the fragments for anomalous patterns, DELFI can detect the existence of cancer.
Following the success in detecting lung cancer, the study team planned to utilize the technology to detect liver cancer.
Increased early diagnosis of liver cancer, according to Victor Velculescu, MD, PhD, professor of cancer genetics and epigenetics and co-director of the cancer genetics and epigenetics program at the Kimmel Cancer Center, could save lives.
724 blood samples from the US, the EU, and Hong Kong were subjected to the technique. They had to find the most typical form of primary liver cancer.
The US and the EU were where the majority of the samples were taken. The ML model was trained using the samples. To support the hypothesis, more than 200 samples from Hong Kong residents were examined. Samples came from 90 HCC patients, 66 HBV patients, 35 HBV-related liver cirrhosis patients, and 32 individuals without underlying risk factors.
Using the samples, the researchers were able to create a DELFI score. The results are related to cancer prevalence.
The median DELFI score for people without cancer who had viral hepatitis was 0.078 and 0.080, respectively. High scores were seen throughout all cancer stages, and the scores for the 75HCC patients in the US and EU samples were, on average, five to ten times higher.
Patients with an average risk of HCC exhibited a 98 percent specificity and an 88 percent sensitivity. For patients at high risk for the illness, it demonstrated an 85% sensitivity and an 80% specificity.
The study’s findings suggest that DELFI may enhance early detection but that more extensive research is required before it can be applied in a clinical context.
Due to accessibility, only 20% of people at high risk for liver cancer receive screenings. Comparing the new blood test to the already existing standard blood test, it can detect twice as many cases of liver cancer and improve early cancer diagnosis.