Modelling of immune infiltration in prostate cancer treated with HDR-brachytherapy using Raman spectroscopy and machine learning

This is the authors' abstract. We don't add key points for this paper.

Prostate cancer is characterized by an immunosuppressive tumour environment. This work combines Raman spectroscopy with group-and-bases-restricted non-negative matrix factorization (GBR-NMF) and machine learning to assemble models of immune cell densities within the needle-core biopsies of patients undergoing high-dose-rate brachytherapy (HDR-BT). Raman spectral acquisition, as well as immunohistochemistry staining of CD68[Formula: see text], CD3[Formula: see text], and [Formula: see text] cells, was completed for biopsies collected before and 2 weeks following the first fraction of HDR-BT. Regression techniques, constructed using GBR-NMF scores, that produced the most accurate predictions of immune cell density by metrics of root mean-squared error (RMSE) and R[Formula: see text] were the gradient-boosted trees model of [Formula: see text] density (RMSE: 163 counts[Formula: see text], [Formula: see text]: 0.65) and the elastic net model of [Formula: see text]/ [Formula: see text] (RMSE: 0.25, [Formula: see text]: 0.82). The accuracy of these models, herein defined as the fraction of patient predictions within [Formula: see text] standard deviation of their measured values was 11/16 and 12/16, for CD68[Formula: see text] CD3[Formula: see text] and CD68[Formula: see text]/ CD8[Formula: see text] models, respectively. To further delineate which metabolites were most important in the CD68[Formula: see text]/ CD8[Formula: see text] model, this ratio was further predicted in stromal and epithelial tissues within the biopsies, and resulting models utilized the GBR-NMF scores of glutathione, collagen, palmitic acid, and the pre- or post-HDR-BT label to produce an optimal performance level according to RMSE and R[Formula: see text]. In summary, this study illustrates a novel methodology in which supervised machine learning techniques are used to model immune cells, which are prognostic indicators of disease progression.