ABSTRACT
Introduction Previously our group had identified 20 features which were associated with the development of upper gastrointestinal (UGI) cancers using a machine learning approach.[1] We sought to refine this model and to validate this in an independent dataset to assess its generalisability in an interim analysis. Methods We selected patients who were recruited for the multicentre Saliva to Predict rIsk of disease using Transcriptomics and epigenetics (SPIT) study to develop our model. Patients were recruited from 2-week wait suspected UGI pathways and additionally enriched with patients with confirmed oesophageal adenocarcinoma admitted as inpatients. We used regularised logistic regression (glmnet) from the caret package in R software to create the model. 60% of the data with 10-fold cross validation was used for training, with the remaining 40% for testing. For validation, we used data from the predicting RIsk of disease uSing detailed Questionnaires (RISQ) study, an ongoing prospective multicentre study using the questionnaire based on the our previous work.1 We evaluated the model using area under the receiver operating characteristic curve (AUC). Results We included 93 cancer and 715 non-cancer patients for training and testing and 21 cancer and 203 non-cancer patients for validation. We further reduced the model to 18 features without significant detriment to model performance. In the training and testing data AUC was 0.86 (95%CI: 0.81- 0.91) and 0.75 (95%CI: 0.67-0.83) respectively. We set a threshold of 0.03 as a cut off based on a cost function where false negatives had a 50-time greater impact than false positive cases (figure 1). For the validation cohort we achieved an AUC of 0.95 (95%CI: 0.90-1.00). This equated to a sensitivity 0.952 and a specificity of 0.897 for detecting cancer. Conclusions Initial results from our model compare favourably with the Edinburgh Dysphagia Scale, which has a sensitivity and specificity of 0.984 and 0.093 respectively.2 It also appears to have a high specificity, potentially helping to reduce unnecessary endoscopies. We aim to further increase the size of the validation cohort to ensure its robustness and generalisability. Our model could be applied to triaging and prioritising endoscopic referral backlogs as a result of COVID- 19.3.
ABSTRACT
Background/AimsThe impact of the COVID-19 pandemic on adolescent and youngpatients with chronic diseases is likely to be multi-factorial, andinfluenced by various aspects, such as age, sex, education, ethnicity, as well as disease control or personal coping strategies. Adolescentsand young adults are at a time in their live when disruption in theireducation and social life, as well as uncertainty related to professionalprospects and long-term disease outcomes are all associated withsignificant personal concerns. The aim of this survey was to assess themain determinants of COVID-19 associated concern in adolescent andyoung adults with JSLE and JDM as well as their well-being andresilience.MethodsQuestionnaires comprising of questions related to patient and diseasecharacteristics, wellbeing, resilience and concern about the COVID-19pandemic were disseminated through hospital contacts and patient charities social media platforms. Participation was voluntary andimplied consent. The preliminary results of this ongoing survey havebeen analysed using descriptive statistics and linear regression (R).ResultsThe main patient and disease characteristics, self-reported well-being, resilience and perceived concern about the COVID-19 pandemic arepresented in comparison in male vs. female patients. Linear regressionshowed that the strongest determinant of COVID-19 concern was selfreported disease activity (p < 0.0003). The self-reported diseaseactivity was associated with the COVID-19 concern level in bothfemale (P = 0.003) and male patients (p = 0.004) and also with diseaseduration in males (P = 0.018). The COVID concern was not affected byany other factors such as, employment, education, well-being orresilience.ConclusionThe preliminary analysis of our survey showed that patient-reportedCOVID-19 concern during the pandemic was strongly determined bythe self-reported disease activity irrespective of patients' sex, despitesignificantly increased concern in the female compared to malepatients, and association with disease duration in male patients only.We propose that further strategies for better patient support during thepandemic should focus on their optimal disease control as well as takeinto consideration the sex-biased patient concerns.