Development of Electronic Health Record-Based Machine Learning Models to Predict Barrett's Esophagus and Esophageal Adenocarcinoma Risk.

INTRODUCTION: Screening for Barrett's esophagus (BE) is suggested in those with risk factors, but remains underutilized. BE/esophageal adenocarcinoma (EAC) risk prediction tools integrating multiple risk factors have been described. However, accuracy remains modest (area under the receiver-operating curve [AUROC] ≤0.7), and clinical implementation has been challenging. We aimed to develop machine learning (ML) BE/EAC risk prediction models from an electronic health record (EHR) database. METHODS: The Clinical Data Analytics Platform, a deidentified EHR database of 6 million Mayo Clinic patients, was used to predict BE and EAC risk. BE and EAC cases and controls were identified using International Classification of Diseases codes and augmented curation (natural language processing) techniques applied to clinical, endoscopy, laboratory, and pathology notes. Cases were propensity score matched to 5 independent randomly selected control groups. An ensemble transformer-based ML model architecture was used to develop predictive models. RESULTS: We identified 8,476 BE cases, 1,539 EAC cases, and 252,276 controls. The BE ML transformer model had an overall sensitivity, specificity, and AUROC of 76%, 76%, and 0.84, respectively. The EAC ML transformer model had an overall sensitivity, specificity, and AUROC of 84%, 70%, and 0.84, respectively. Predictors of BE and EAC included conventional risk factors and additional novel factors, such as coronary artery disease, serum triglycerides, and electrolytes. DISCUSSION: ML models developed on an EHR database can predict incident BE and EAC risk with improved accuracy compared with conventional risk factor-based risk scores. Such a model may enable effective implementation of a minimally invasive screening technology.

Visceral scalloping on abdominal computed tomography due to abdominal tuberculosis.

OBJECTIVE: Scalloping of visceral organs is described in pseudomyxoma peritonei, malignant ascites, among other conditions, but not tuberculosis. METHODS: We report findings from a retrospective study of patients with abdominal tuberculosis who had visceral scalloping on abdominal computed tomography (CT). Diagnosis of abdominal tuberculosis was made on the basis of combination of clinical, biochemical, radiological and microbiological criteria. The clinical data, hematological and biochemical parameters, and findings of chest X-ray, CT, Mantoux test, and HIV serology were recorded. RESULTS: Of 72 patients with abdominal tuberculosis whose CT scans were included, seven patients had visceral scalloping. The mean age of these patients was 32.14 ± 8.43 years and four were men. While six patients had scalloping of liver, one had splenic scalloping. The patients presented with abdominal pain (all), abdominal distension (five patients), loss of weight or appetite (all), and fever (four patients). Mantoux test was positive in five, while none had HIV infection. The diagnosis was based on fluid (ascitic or collections) evaluation in four patients, ileo-cecal biopsy in one patient, fine needle aspiration from omental thickening in one patient, and sputum positivity for acid fast bacilli (AFB) in one patient. On CT examination, four patients had ascites, five had collections, one had lymphadenopathy, four had peritoneal involvement, three had pleural effusion, and two had ileo-cecal thickening. All except one patient received standard ATT for 6 months or 9 months (one patient). Pigtail drainage for collections was needed for two patients. DISCUSSION: This report is the first description of visceral scalloping of liver and spleen in patients with abdominal tuberculosis. Previously, this finding has been reported primarily with pseudomyxoma peritonei and peritoneal carcinomatosis. CONCLUSION: Visceral scalloping may not conclusively distinguish peritoneal tuberculosis from peritoneal carcinomatosis or pseudomyxoma peritonei.

Simrank: Rapid and sensitive general-purpose k-mer search tool.

BACKGROUND: Terabyte-scale collections of string-encoded data are expected from consortia efforts such as the Human Microbiome Project http://nihroadmap.nih.gov/hmp. Intra- and inter-project data similarity searches are enabled by rapid k-mer matching strategies. Software applications for sequence database partitioning, guide tree estimation, molecular classification and alignment acceleration have benefited from embedded k-mer searches as sub-routines. However, a rapid, general-purpose, open-source, flexible, stand-alone k-mer tool has not been available. RESULTS: Here we present a stand-alone utility, Simrank, which allows users to rapidly identify database strings the most similar to query strings. Performance testing of Simrank and related tools against DNA, RNA, protein and human-languages found Simrank 10X to 928X faster depending on the dataset. CONCLUSIONS: Simrank provides molecular ecologists with a high-throughput, open source choice for comparing large sequence sets to find similarity.

Deep-sea oil plume enriches indigenous oil-degrading bacteria.

The biological effects and expected fate of the vast amount of oil in the Gulf of Mexico from the Deepwater Horizon blowout are unknown owing to the depth and magnitude of this event. Here, we report that the dispersed hydrocarbon plume stimulated deep-sea indigenous γ-Proteobacteria that are closely related to known petroleum degraders. Hydrocarbon-degrading genes coincided with the concentration of various oil contaminants. Changes in hydrocarbon composition with distance from the source and incubation experiments with environmental isolates demonstrated faster-than-expected hydrocarbon biodegradation rates at 5°C. Based on these results, the potential exists for intrinsic bioremediation of the oil plume in the deep-water column without substantial oxygen drawdown.