Background: Routine screening to detect silent but deadly cancers such as pancreatic ductal adenocarcinoma (PDAC) can significantly improve survival, creating an important need for a convenient screening test. High-resolution proton (1H) magnetic resonance spectroscopy (MRS) of plasma identifies circulating metabolites that can allow detection of cancers such as PDAC that have highly dysregulated metabolism.
Methods: We first acquired 1H MR spectra of human plasma samples classified as normal, benign pancreatic disease and malignant (PDAC). We next trained a system of artificial neural networks (ANNs) to process and discriminate these three classes using the full spectrum range and resolution of the acquired spectral data. We then identified and ranked spectral regions that played a salient role in the discrimination to provide interpretability of the results. We tested the accuracy of the ANN performance using blinded plasma samples.
Results: We show that our ANN approach yields, in a cross validation-based training of 170 samples, a sensitivity and a specificity of 100% for malignant versus non-malignant (normal and disease combined) discrimination. The trained ANNs achieve a sensitivity and specificity of 87.5% and 93.1% respectively (AUC: ROC = 0.931, P-R = 0.854), with 45 blinded plasma samples. Further, we show that the salient spectral regions of the ANN discrimination correspond to metabolites of known importance for their role in cancers.
Conclusions: Our results demonstrate that the ANN approach presented here can identify PDAC from 1H MR plasma spectra to provide a convenient plasma-based assay for population-level screening of PDAC. The ANN approach can be suitably expanded to detect other cancers with metabolic dysregulation.
Early detection of cancer on a large scale through simple methods remains challenging. Several studies have reported new methods for a simple blood-based diagnostic test. However, those already proposed can struggle to balance high accuracy with lower cost. This work uses a combination of computer methods and a tool called magnetic resonance spectroscopy, which is an affordable diagnostic tool that does not require complex sample preparation, to identify patterns of metabolites in blood samples capable of distinguishing cancer from non-cancer samples. The approach presented here results in an accuracy of 100% in the training set of 170 blood samples used to build the method, and 91% in a separate validation set of 45 blood samples used to test the method.
© 2025. The Author(s).