Pancreatic cancer (PC) is usually diagnosed at a late stage and the survival rate is often very low. Getting to know risk factors is of key importance for #EarlyDiagnosis. On the one hand, individuals that could benefit of an inclusion in a screening programme must be identified. On the other hand, it is crucial to understand which are the most appropriate tools for PC diagnosis and follow-up. Up to now, there is no diagnostic test considered ideal for #pancreatic cancer screening. In this field Artificial Intelligence (#AI) could play a key role allowing to improve current diagnostic tests, avoiding unnecessary exams and shortening the time until the diagnosis.
Risk factors for PC can be hereditary and non-hereditary.
#GeneticPredisposition is the main risk factor for developing PC. It is estimated that more than 10% of patients have a first degree or second degree relative that suffered from PC [1,2]. Having a first-degree relative increases the risk of developing the illness up to 2,5-8 times the average risk. This risk rises if the number of relatives affected is higher .
Sometimes it is possible to identify a #genetic mutation responsible for the increased risk. There are many different known mutations that can cause the development of PC in a family. Familiar syndromes with highest risk are Peutz Jeguers Syndrome, Li Fraumeni Syndrome, or hereditary pancreatitis.
The main goal of diagnostic tests used currently for PC screening in these high-risk situations is to detect the disease at a curable stage in asymptomatic patients. Some of the tests used are genetic analysis, Computer Tomography, Magnetic Resonance Image, or Ultrasound Endoscopy. Since there is no perfect test and due to the great variability in the risk of PC among the different syndromes and family history, the follow-up of these patients has been controversial. In people with hereditary pancreatitis, due the very increased risk of CP, the recommendation is to start screening at age 40. In people with familiar history of PC but no known hereditary syndrome, the general recommendation is to start screening at age 50 and continue it every year .
What we are certain about is that diagnostic tests should be as accurate as possible to detect the highest number of pancreatic changes with the lowest number of tests. This way you can guarantee the patient that, despite entering the screening at a young age, the problems existing in the pancreas will be detected by the test with a high reliability. We think AI will allow to improve PC diagnosis, avoiding unnecessary tests and probably including in its algorithms other factors such as habits, previous diseases or age to better characterize the real risk of developing PC and offering the patients and its relatives the best follow-up strategy.
1. R.E. Brand, H.T. Lynch. Hereditary pancreatic adenocarcinoma. A clinical perspective.
Med Clin North Am, 84 (2000), pp. 665-675
2. Lopez Serrano A. Risk factors and early diagnosis of pancreatic cancer. Gastroenterol Hepatol 2010 382-390
3. R.R. McWilliams, K.G. Rabe, C. Olswold, M. De Andrade, G.M. Petersen.
Risk of malignancy in first-degree relatives of patients with pancreatic carcinoma.
Cancer, 104 (2005), pp. 388-394
4. Goggins M, Overbeek KA, Brand R International Cancer of the Pancreas Screening (CAPS) consortium, et al. Management of patients with increased risk for familial pancreatic cancer: updated recommendations from the International Cancer of the Pancreas Screening (CAPS) Consortium Gut 2020;69:7-17.