P158 Raman Spectroscopy demonstrates biomolecular changes and predicts response to biological therapy in inflammatory bowel disease

Introduction Biological therapy in the management of IBD is increasing however, response rates remain modest. Raman Spectroscopy describes the scattering of inelastic light giving spectra that is highly specific for individual molecules revealing tissue biochemistry. Our aim was to establish spectral changes in IBD following biological and whether Raman Spectroscopy can predict response to biological therapy. Methods IBD patients who underwent endoscopic assessment pre- and 12 weeks post-biological therapy were recruited. Biopsies were taken for ex vivo Raman Spectroscopy analysis alongside biopsies for histological analysis. Response to treatment was defined when both a reduction in the endoscopic score of activity (UCEIS for UC and SES-CD for CD) and histological healing (defined as Nancy (0–1) in UC and modified Riley (0) in CD) was present. For spectral analysis we used artificial neural networks and a supervised learning model to demonstrate spectral differences and build predictive modelling, based on an 80:20% (network training: network testing) split of the data. Results A total of 1800 Raman Spectra (18 patients-7 UC/11 CD) were analysed. Using data projection, there is clear separation between responder (3 UC and 3 CD) and non-responders (4 UC and 8 CD). The key spectral differences between pre- vs. post-biologic in responders are demonstrated using feature extraction (figure 1a & 1b). There was an increase at 1302 cm-1 after biological therapy and when healing was achieved, which may indicate a potential biomarker of healing. When comparing the pre-biological spectra, a machine learning algorithm is able to differentiate between responders from non-responders with a sensitivity, specificity, NPV and accuracy of 100.0% (95% CI 93.5–100.0), 92.3% (95% CI 83.0–97.5), 100.0% and 95.8% (95% CI 90.5–98.6) respectively in UC and CD. Conclusion We have demonstrated changes in response to biological therapy and a potential biomarker for mucosal healing using Raman Spectroscopy, and can differentiate responders from non-responders in IBD. Using this modelling there is a potential to predict response to biological therapy, however prospective prediction will not need to take place before clinical application. To our knowledge, this is the first study demonstrating these changes.