Can artificial intelligence aid in the diagnosis of pancreatic cancer?

Question

Hello doctor,

I am 45 years old right now, and I am very interested in knowing if there are ways in which I could use artificial intelligence for the screening of pancreatic cancer in my case, considering our family history. I have a history of gastric cancer in the family, and my doctor keeps pushing me to get myself screened regularly because I have reached the age of 40.

I have learned that there has been some progress in the development of artificial intelligence technology for the screening of cancers, but I am not entirely sure about the way it could work for me.

Kindly help.

Answer 1

Hello,

Welcome to icliniq.com.

I read your query and can understand your concern.

Pancreatic cancer is notoriously difficult to diagnose in its early stages. Occasionally, the presence of pancreatic cancer is suggested by elevated liver transaminase (substances that help the organ's cells function, break down substances, and remove toxins from the body), bilirubin (a yellowish substance made during your body's normal process of breaking down old red blood cells), and alkaline phosphatase (a group of isoenzymes located on the outer layer of the cell membrane) levels on testing performed for other purposes.

I would suggest the further investigations include:

CBC (complete blood count): Blood test that analyzes various components of your blood
Hepatobiliary Tests: Obstructive jaundice is characterized by elevated levels of bilirubin (both conjugated and total), ALP (alkaline phosphatase), GGT (gamma glutamyl transferase, a serum which is extensively used as a parameter for liver dysfunction and as a marker of alcohol consumption), as well as AST (aspartate transferase, an enzyme which can be found in your liver, heart, muscle, and other body tissues) and ALT (alanine transaminase, a liver enzyme that gets into blood due to damage to liver cells).
Serum amylase (a digestive enzyme predominantly secreted by the pancreas and salivary glands) and/or lipase (an enzyme the body uses to break down fats in food so they can be absorbed in the intestines) levels. The levels are elevated in less than 50 percent of patients with resectable pancreatic cancers and only 25 percent of patients with unresectable tumors.
Tumor markers: Around 75 to 85 percent of patients have elevated CA (calcium) 19 to 9 levels, and 40 to 45 percent have elevated CEA (carcinoembryonic antigen) levels.
Genetic testing: This includes tests for germline mutations such as BRCA1 and 2 (breast cancer genes 1 and 2), testing for high microsatellite instability (MSI-H), which may indicate Lynch syndrome (the most common form of hereditary colorectal cancer, also known as hereditary nonpolyposis colorectal cancer syndrome); and next-generation sequencing for somatic genetic alterations in tumor tissue in patients with advanced disease.

In your case, approximately 5 to 10 percent of patients with pancreatic carcinoma have some genetic predisposition to developing the disease. Hereditary pancreatitis has been associated with a 40 percent cumulative risk of developing pancreatic cancer.

Pancreatic cancer poses a grave threat to mankind due to its poor prognosis and aggressive nature. An accurate diagnosis is critical for implementing a successful treatment plan, given the risk of exacerbation. The diagnosis of pancreatic cancer relies on medical imaging, which provides inaccurate information about the prognosis of the patient and makes it difficult for clinicians to select the optimal treatment.

Data derived from medical imaging has been integrated with artificial intelligence, an emerging technology, to facilitate clinical decision-making. This review explores the implementation of artificial intelligence for various imaging modalities to obtain a precise cancer diagnosis.

I hope this helps.

Kindly revert in case of further queries.