Using saliva epigenetic data to develop and validate a multivariable predictor of esophageal cancer status.

Background: Salivary epigenetic biomarkers may detect esophageal cancer. Methods: A total of 256 saliva samples from esophageal adenocarcinoma patients and matched volunteers were analyzed with Illumina EPIC methylation arrays. Three datasets were created, using 64% for discovery, 16% for testing and 20% for validation. Modules of gene-based methylation probes were created using weighted gene coexpression network analysis. Module significance to disease and gene importance to module were determined and a random forest classifier generated using best-scoring gene-related epigenetic probes. A cost-sensitive wrapper algorithm maximized cancer diagnosis. Results: Using age, sex and seven probes, esophageal adenocarcinoma was detected with area under the curve of 0.72 in discovery, 0.73 in testing and 0.75 in validation datasets. Cancer sensitivity was 88% with specificity of 31%. Conclusion: We have demonstrated a potentially clinically viable classifier of esophageal cancer based on saliva methylation.

Development and validation of a multivariable risk factor questionnaire to detect oesophageal cancer in 2-week wait patients.

INTRODUCTION: Oesophageal cancer is associated with poor health outcomes. Upper GI (UGI) endoscopy is the gold standard for diagnosis but is associated with patient discomfort and low yield for cancer. We used a machine learning approach to create a model which predicted oesophageal cancer based on questionnaire responses. METHODS: We used data from 2 separate prospective cross-sectional studies: the Saliva to Predict rIsk of disease using Transcriptomics and epigenetics (SPIT) study and predicting RIsk of diSease using detailed Questionnaires (RISQ) study. We recruited patients from National Health Service (NHS) suspected cancer pathways as well as patients with known cancer. We identified patient characteristics and questionnaire responses which were most associated with the development of oesophageal cancer. Using the SPIT dataset, we trained seven different machine learning models, selecting the best area under the receiver operator curve (AUC) to create our final model. We further applied a cost function to maximise cancer detection. We then independently validated the model using the RISQ dataset. RESULTS: 807 patients were included in model training and testing, split in a 70:30 ratio. 294 patients were included in model validation. The best model during training was regularised logistic regression using 17 features (median AUC: 0.81, interquartile range (IQR): 0.69-0.85). For testing and validation datasets, the model achieved an AUC of 0.71 (95% CI: 0.61-0.81) and 0.92 (95% CI: 0.88-0.96) respectively. At a set cut off, our model achieved a sensitivity of 97.6% and specificity of 59.1%. We additionally piloted the model in 12 patients with gastric cancer; 9/12 (75%) of patients were correctly classified. CONCLUSIONS: We have developed and validated a risk stratification tool using a questionnaire approach. This could aid prioritising patients at high risk of having oesophageal cancer for endoscopy. Our tool could help address endoscopic backlogs caused by the COVID-19 pandemic.