Abstract
Abstract Improved screening protocols (SP) for patients at high risk of developing HCC could lead to improved patient outcome and possibly cure if detected early. The current SPs, ultrasound with the possible addition of alphafetoprotein (AFP) measurement, suffer from insufficient sensitivity and specificity, and less than 30% of patients are diagnosed early enough to be suitable candidates for resection or transplantation. An easy to use biomarker for the early detection of HCC is clearly needed. We used mass spectrometry analysis of serum samples combined with specialized deep learning techniques to train and validate such a test. The development cohort consisted of patients undergoing transplant or resection for HCC (N = 52; median MELD = 14), and patients with advanced cirrhosis undergoing liver transplant (N = 53; median MELD = 25). Underlying cause of liver disease was 51% hepatitis C infection. The validation cohort consisted of patients with advanced HCC (N = 103; 70/26/7 Child-Pugh A/B/C) and liver disease but no HCC (N = 77; 68/7/2 Child-Pugh A/B/C), with 68% of patients having hepatitis B infection (HBV). The classifier was trained especially to avoid confounding by liver function. The resulting test showed a sensitivity/specificity of 73%/95% in cross validation in the development set overall. In the subset of T1 patients (or lesion size <2 cm) accuracy was 72% (75%). Performance was good across all represented causes of liver disease. The test was shown not to be confounded by liver function by classifying healthy patients (N = 17) as ‘no cancer’. In the validation set the performance was 89%/73%, with 91%/78% in the HBV subgroup and 90%/75% in the Child-Pugh A subgroup. The developed test shows promise in the early detection of HCC as a screening tool in high risk patients independent of the cause of underlying liver disease. While further validation will be necessary to conclusively prove its clinical validity, we believe such a test could substantially improve early detection of HCC. Citation Format: Devalingam Mahalingam, William K. Washburn, Glenn Halff, Leonidas Chelis, Stylianos Kakolyris, Stylianos Vradelis, Julia Grigorieva, Carlos Oliveira, Heinrich Roder, Joanna Roder. A mass spectrometry based serum test for the detection of hepatocellular carcinoma (HCC) in high risk patients. [abstract]. In: Proceedings of the 106th Annual Meeting of the American Association for Cancer Research; 2015 Apr 18-22; Philadelphia, PA. Philadelphia (PA): AACR; Cancer Res 2015;75(15 Suppl):Abstract nr 1567. doi:10.1158/1538-7445.AM2015-1567
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.