BACKGROUND AND AIMS
Pancreatic cancer (PDAC) is a highly lethal malignancy, requiring efficient detection when the primary tumor is still resectable. We had previously developed the MxPancreasScore comprising nine analytes and serum CA19-9, achieving an accuracy of 90.6%. The necessity for five different analytic platforms and multiple analytic runs however hindered clinical applicability. Therefore, we aimed to develop a simpler single-analytical run, single-platform diagnostic signature.
941 patients (PDAC=356, CP=304, non-pancreatic disease=281) in three multicenter independent test and validation cohorts (ID, VD1, VD2) were evaluated. Targeted quantitative plasma metabolite analysis was performed on a LC-MS/MS platform. A machine learning aided algorithm identified an improved (i-Metabolic) and minimalistic metabolic (m-Metabolic) signatures, and compared for performance.
The i-Metabolic Signature, (12 analytes plus CA19-9) distinguished PDAC from CP with AUC (95%CI) of 97.2 (97.1-97.3)%, 93.5 (93.4-93.7)%, and 92.2 (92.1-92.3)% in the ID-, VD1- and VD2 cohorts, respectively. In the VD2 cohort, the m-Metabolic signature (4 analytes plus CA19-9) discriminated PDAC from CP with a sensitivity of 77.3% and specificity of 89.6% with an overall accuracy of 82.4%. For the subsets of PDAC patients with resectable stages IA-IIB tumors (N=45), the sensitivity, specificity and accuracy were 73.2%, 89.6%, and 82.7% respectively; for those with detectable CA19.9 >2 U/ml, 81.6%, 88.7% and 84.5% respectively; and for those with CA19.9 <37 U/ml, 39.7%, 94.1%, and 76.3% respectively.
The single-platform, single-run, m-Metabolic signature of just four metabolites used in combination with serum CA19-9 levels is an innovative accurate diagnostic tool for PDAC at the time of clinical presentation, warranting further large-scale evaluation.