Abstract Background and aims Seattle protocol biopsies for Barrett's Esophagus (BE) surveillance are labour intensive with low compliance. Dysplasia detection rates vary, leading to missed lesions. This can potentially be offset with computer aided detection. We have developed convolutional neural networks (CNNs) to identify areas of dysplasia and where to target biopsy. Methods 119 Videos were collected in high‐definition white light and optical chromoendoscopy with i‐scan (Pentax Hoya, Japan) imaging in patients with dysplastic and non‐dysplastic BE (NDBE). We trained an indirectly supervised CNN to classify images as dysplastic/non‐dysplastic using whole video annotations to minimise selection bias and maximise accuracy. The CNN was trained using 148,936 video frames (31 dysplastic patients, 31 NDBE, two normal esophagus), validated on 25,161 images from 11 patient videos and tested on 264 iscan‐1 images from 28 dysplastic and 16 NDBE patients which included expert delineations. To localise targeted biopsies/delineations, a second directly supervised CNN was generated based on expert delineations of 94 dysplastic images from 30 patients. This was tested on 86 i‐scan one images from 28 dysplastic patients. Findings The indirectly supervised CNN achieved a per image sensitivity in the test set of 91%, specificity 79%, area under receiver operator curve of 93% to detect dysplasia. Per‐lesion sensitivity was 100%. Mean assessment speed was 48 frames per second (fps). 97% of targeted biopsy predictions matched expert and histological assessment at 56 fps. The artificial intelligence system performed better than six endoscopists. Interpretation Our CNNs classify and localise dysplastic Barrett's Esophagus potentially supporting endoscopists during surveillance.
BackgroundScreening for Barrett's oesophagus relies on endoscopy, which is invasive and few who undergo the procedure are found to have the condition. We aimed to use machine learning techniques to develop and externally validate a simple risk prediction panel to screen individuals for Barrett's oesophagus.MethodsIn this prospective study, machine learning risk prediction in Barrett's oesophagus (MARK-BE), we used data from two case-control studies, BEST2 and BOOST, to compile training and validation datasets. From the BEST2 study, we analysed questionnaires from 1299 patients, of whom 880 (67·7%) had Barrett's oesophagus, including 40 with invasive oesophageal adenocarcinoma, and 419 (32·3%) were controls. We randomly split (6:4) the cohort using a computer algorithm into a training dataset of 776 patients and a testing dataset of 523 patients. We compiled an external validation cohort from the BOOST study, which included 398 patients, comprising 198 patients with Barrett's oesophagus (23 with oesophageal adenocarcinoma) and 200 controls. We identified independently important diagnostic features of Barrett's oesophagus using the machine learning techniques information gain and correlation-based feature selection. We assessed multiple classification tools to create a multivariable risk prediction model. Internal validation of the model using the BEST2 testing dataset was followed by external validation using the BOOST external validation dataset. From these data we created a prediction panel to identify at-risk individuals.FindingsThe BEST2 study included 40 diagnostic features. Of these, 19 added information gain but after correlation-based feature selection only eight showed independent diagnostic value including age, sex, cigarette smoking, waist circumference, frequency of stomach pain, duration of heartburn and acidic taste, and taking antireflux medication, of which all were associated with increased risk of Barrett's oesophagus, except frequency of stomach pain, with was inversely associated in a case-control population. Logistic regression offered the highest prediction quality with an area under the receiver-operator curve (AUC) of 0·87 (95% CI 0·84–0·90; sensitivity set at 90%; specificity of 68%). In the testing dataset, AUC was 0·86 (0·83–0·89; sensitivity set at 90%; specificity of 65%). In the external validation dataset, the AUC was 0·81 (0·74–0·84; sensitivity set at 90%; specificity of 58%).InterpretationOur diagnostic model offers valid predictions of diagnosis of Barrett's oesophagus in patients with symptomatic gastro-oesophageal reflux disease, assisting in identifying who should go forward to invasive confirmatory testing. Our predictive panel suggests that overweight men who have been taking antireflux medication for a long time might merit particular consideration for further testing. Our risk prediction panel is quick and simple to administer but will need further calibration and validation in a prospective study in primary care.FundingCharles Wolfson Charitable Trust and Guts UK.
Both anaemia and iron deficiency are being increasingly recognised in patients with inflammatory bowel disease (IBD) not only as manifestations of active disease but as factors influencing patient quality of life in their own right.1 As a result, guidelines have been formulated to facilitate the management of patients in these settings.2 In this study the authors have investigated the prevalence and the treatment requirements of both anaemia and iron deficiency in outpatients with IBD.
Methods
In a cross-sectional study, all outpatients with IBD at our centre were identified. After excluding for pregnancy, recent surgery and blood dyscrasias, 543 outpatients with IBD were identified (265 with ulcerative colitis, 268 with Crohn9s disease, 10 with indeterminate colitis). In addition to both gender and age, haemoglobin, iron status and iron therapy were also collected. Disease activity was confirmed by endoscopic and/or radiological assessment. C reactive protein (CRP) was also collected as a presumed surrogate for disease activity.
Results
Of the 543 patients with IBD, 91 patients (16.8%) were anaemic of which 45 patients (49.5%) had biochemical evidence of iron deficiency. 38 patients (14.3%) with ulcerative colitis compared with 52 patients (19.5%) with Crohn9s disease were anaemic (p=0.102). Anaemia was associated with the presence of iron deficiency (p<0.001) and active disease (p=0.005) but not with gender. Similarly, iron deficiency was also associated with active disease (p<0.001) but not gender or the type of IBD. CRP was significantly different in patients with and without both anaemia and iron deficiency (p<0.001). In patients with active disease, both haemoglobin (p=0.010) and CRP (p<0.001) were significantly different to those with inactive disease but not MCV or ferritin. Of the 38 patients who were on oral iron, 11 (29%) had a suboptimal response and required intravenous iron. 6 out of 12 patients being administered intravenous iron required erythropoetin.
Conclusion
Anaemia is a common finding in outpatients with IBD with frequency of up to 20% of which almost half had evidence of iron deficiency. In contrast to oral iron therapy, intravenous iron and erythropoietin therapy were required for only 2% and 1% of patients respectively. Anaemia was associated with an older age, active disease and iron deficiency. Both anaemia, iron deficiency and CRP appear to act as surrogate markers for active disease.
Barrett's oesophagus (BE) is a precursor to oesophageal adenocarcinoma (OAC). Endoscopic surveillance is performed to detect dysplasia arising in BE as it is likely to be amenable to curative treatment. At present, there are no guidelines on who should perform surveillance endoscopy in BE. Machine learning (ML) is a branch of artificial intelligence (AI) that generates simple rules, known as decision trees (DTs). We hypothesised that a DT generated from recognised expert endoscopists could be used to improve dysplasia detection in non-expert endoscopists. To our knowledge, ML has never been applied in this manner.Video recordings were collected from patients with non-dysplastic (ND-BE) and dysplastic Barrett's oesophagus (D-BE) undergoing high-definition endoscopy with i-Scan enhancement (PENTAX®). A strict protocol was used to record areas of interest after which a corresponding biopsy was taken to confirm the histological diagnosis. In a blinded manner, videos were shown to 3 experts who were asked to interpret them based on their mucosal and microvasculature patterns and presence of nodularity and ulceration as well as overall suspected diagnosis. Data generated were entered into the WEKA package to construct a DT for dysplasia prediction. Non-expert endoscopists (gastroenterology specialist registrars in training with variable experience and undergraduate medical students with no experience) were asked to score these same videos both before and after web-based training using the DT constructed from the expert opinion. Accuracy, sensitivity, and specificity values were calculated before and after training where p < 0.05 was statistically significant.Videos from 40 patients were collected including 12 both before and after acetic acid (ACA) application. Experts' average accuracy for dysplasia prediction was 88%. When experts' answers were entered into a DT, the resultant decision model had a 92% accuracy with a mean sensitivity and specificity of 97% and 88%, respectively. Addition of ACA did not improve dysplasia detection. Untrained medical students tended to have a high sensitivity but poor specificity as they "overcalled" normal areas. Gastroenterology trainees did the opposite with overall low sensitivity but high specificity. Detection improved significantly and accuracy rose in both groups after formal web-based training although it did it reach the accuracy generated by experts. For trainees, sensitivity rose significantly from 71% to 83% with minimal loss of specificity. Specificity rose sharply in students from 31% to 49% with no loss of sensitivity.ML is able to define rules learnt from expert opinion. These generate a simple algorithm to accurately predict dysplasia. Once taught to non-experts, the algorithm significantly improves their rate of dysplasia detection. This opens the door to standardised training and assessment of competence for those who perform endoscopy in BE. It may shorten the learning curve and might also be used to compare competence of trainees with recognised experts as part of their accreditation process.
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)
