Artificial Intelligence for Determination of Gastroscopy Surveillance Intervals
Ontology highlight
ABSTRACT:
DISEASE(S): Intestinal Metaplasia,Helicobacter Pylori Infection,Early Gastric Cancer,Carcinoma In Situ,Neoplasms,Gastritis,Low Grade Intraepithelial Neoplasia,Metaplasia,Atrophic Gastritis,High Grade Intraepithelial Neoplasia,Gastric Cancer,Gastritis, Atrophic,Stomach Neoplasms
PROVIDER: 877 | ecrin-mdr-crc |
REPOSITORIES: ECRIN MDR
Similar Datasets
Project description:We previously reported a microarray-based diagnostic system for heart transplant endomyocardial biopsies (EMBs), using either 3-archetype (3AA) or 4-archetype (4AA) unsupervised algorithms to estimate rejection. The present study aimed to examine the stability of machine-learning algorithms in new biopsies, compare 3AA vs. 4AA algorithms, assess supervised binary classifiers trained on histologic or molecular diagnoses, create a report combining many scores into an ensemble of estimates, and examine possible automated sign-outs. Algorithms derived in cohort 331 performed similarly in new biopsies despite differences in case mix. In the combined cohort, the 4AA model, including a parenchymal injury score, retained correlations with histologic rejection and DSA similar to the 3AA model. Supervised molecular classifiers predicted molecular rejection (AUCs>0.87) better than histologic rejection (AUCs<0.78), even when trained on histology diagnoses. A report incorporating many AA and binary classifier scores interpreted by one expert showed highly significant agreement with histology (p<0.001), but with many discrepancies as expected from the known noise in histology. An automated random forest score closely predicted expert diagnoses, confirming potential for automated sign-outs.Molecular algorithms are stable in new populations and can be assembled into an ensemble that combines many supervised and unsupervised estimates of the molecular disease states. (ClinicalTrials.gov NCT02670408).
2019-08-16 | GSE124897 | GEO
Project description:<p>The Vanderbilt Electronic Systems for Pharmacogenomic Assessment (VESPA) Project is a large electronic medical record (EMR)- and biobank-based initiative for translational pharmacogenomics discoveries. Key research resources utilized in this effort include the BioVU DNA databank and associated Synthetic Derivative database of clinical information, and software tools developed to identify drugs and clinical events using EHR-derived structured and unstructured ("free text") data. Cohorts include subjects with primarily drug-response phenotypes, and most cases and controls identified include three data types: ICD-9 codes, medication regimens, and medical test results. Advanced informatics methods, such as natural language processing, were also used for some phenotypes. Algorithms used event-sequence analyses to establish temporal relationships between drugs and phenotypes. Both cases and control algorithms excluded records that contained specific comorbidities and were refined to achieve positive predictive value (PPV) > 90%. For automated algorithms failing to meet this threshold, manual review was coupled with algorithms to validate that the included cases were true positives.</p> <p>A total of 11,639 subjects met phenotyping criteria for a least one of the 28 phenotypes investigated. Across all phenotypes cases and controls, 90% were reused as either a case or control for a least one other phenotype. Data are deposited for individual phenotypes in the VESPA substudies.</p> <p><b>Substudies</b>: <li>VESPA: Genome Wide Association Study of Serum Creatinine during Vancomycin Therapy and Vancomycin Pharmacokinetics - <a href="./study.cgi?study_id=phs000894">phs000894</a></li> <li>VESPA: Genome Wide Study of Clinically Diagnosed Ace Inhibitor Cough - <a href="./study.cgi?study_id=phs000992">phs000992</a></li> </p>
| phs000991 | dbGaP
Project description:<p>The Electronic Medical Record Phenotypes and Community-engaged Genomic Association Study aims to identify genetic variants mediating susceptibility to peripheral arterial disease (PAD). The study leverages a biorepository of blood samples of 1688 PAD cases and 1649 controls, and the electronic medical record (EMR) to annotate the biorepository. PAD cases were identified from the vascular laboratory database as having an ankle brachial index (ABI) <0.9 at rest or after exercise or having non-compressible vessels. Controls were without prior history of atherosclerotic vascular disease and when tested, no evidence of ischemia on a stress test. Phenotypes and environmental exposures including age, ethnicity, demographic and anthropometric data are derived from the Mayo Electronic Medical Record (EMR). Comorbidities were determined using algorithms for diabetes and hypertension based on ICD-9 codes and medication use. Relevant laboratory data, including lipid levels, fasting blood sugar and serum creatinine at index date or within a 1-year window of the index date were extracted. Medication classes at index date were identified using Mayo's Natural Language Processing-based system with RxNorm codification and NDF-RT terminologies mapping. Smoking status was confirmed by natural language processing of clinical notes. Genotyping of ~600,000 SNPs across the genome is being conducted at the Broad Institute using the Illumina 660W platform. Statistical analyses will be conducted to identify genetic variants associated with susceptibility to PAD.</p>
| phs000203 | dbGaP
Project description:Preprocessing data in a reproducible and robust way is one of the current challenges in untargeted metabolomics workflows. Data curation in liquid chromatography-mass spectrometry (LC-MS) involves the removal of unwanted features (retention time; m/z pairs) to retain only high-quality data for subsequent analysis and interpretation. The present work introduces a package for the Python programming language for pre-processing LC-MS data for quality control procedures in untargeted metabolomics workflows. It is a versatile strategy that can be customized or fit for purpose according to the specific metabolomics application. It allows performing quality control procedures to ensure accuracy and reliability in LC-MS measurements, and it allows preprocessing metabolomics data to obtain cleaned matrices for subsequent statistical analysis. The capabilities of the package are showcased with pipelines for an LC-MS system suitability check, system conditioning, signal drift evaluation, and data curation. These applications were implemented to preprocess data corresponding to a new suite of plasma candidate plasma reference materials developed by the National Institute of Standards and Technology (NIST; hypertriglyceridemic, diabetic, and African-American plasma pools) to be used in untargeted metabolomics studies. in addition to NIST SRM 1950 – Metabolites in Frozen Human Plasma. The package offers a rapid and reproducible workflow that can be used in an automated or semi-automated fashion, and it is an open and free tool available to all users.
2020-11-21 | MTBLS1919 | MetaboLights
Project description:Positional proteomics methodologies have transformed protease research and have brought mass spectrometry (MS)-based degradomics studies to the forefront of protease characterization and system-wide interrogation of protease signaling. Considerable advancements in sensitivity and throughput of liquid chromatography (LC)-MS/MS instrumentation enable generation of enormous positional proteomics datasets of protein termini and neo-termini of cleaved protease substrates. However, such progress has not been observed to the same extent in data analysis and post-processing steps, which arguably constitute the largest bottleneck in positional proteomics workflows. Here, we present a computational tool, CLIPPER 2.0, that builds on prior algorithms developed for MS-based protein termini analysis, facilitating peptide level annotation and data analysis. CLIPPER 2.0 can be used with several sample preparation workflows and proteomics search algorithms, and enables fast and automated database information retrieval, statistical and network analysis, as well as visualization of terminomic datasets. We demonstrate our tool by analyzing GluC and MMP9 cleavages in HeLa lysates. CLIPPER 2.0 is available at https://github.com/UadKLab/CLIPPER-2.0.
2024-05-02 | PXD047261 | Pride
Project description:The aim of this study was to determine reference intervals in an outpatient population from Vall d'Hebron laboratory using an indirect approach previously described in a Dutch population (NUMBER project). We used anonymized test results from individuals visiting general practitioners and analysed during 2018. Analytical quality was assured by EQA performance, daily average monitoring and by assessing longitudinal accuracy between 2018 and 2020 (using trueness verifiers from Dutch EQA). Per test, outliers by biochemically related tests were excluded, data were transformed to a normal distribution (if necessary) and means and standard deviations were calculated, stratified by age and sex. In addition, the reference limit estimator method was also used to calculate reference intervals using the same dataset. Finally, for standardized tests reference intervals obtained were compared with the published NUMBER results. Reference intervals were calculated using data from 509,408 clinical requests. For biochemical tests following a normal distribution, similar reference intervals were found between Vall d'Hebron and the Dutch study. For creatinine and urea, reference intervals increased with age in both populations. The upper limits of Gamma-glutamyl transferase were markedly higher in the Dutch study compared to Vall d'Hebron results. Creatine kinase and uric acid reference intervals were higher in both populations compared to conventional reference intervals. Medical test results following a normal distribution showed comparable and consistent reference intervals between studies. Therefore a simple indirect method is a feasible and cost-efficient approach for calculating reference intervals. Yet, for generating standardized calculated reference intervals that are traceable to higher order materials and methods, efforts should also focus on test standardization and bias assessment using commutable trueness verifiers.
| S-EPMC9119462 | biostudies-literature
Project description:We previously reported a system for assessing rejection in kidney transplant biopsies using microarray-based gene expression data, the Molecular Microscope® Diagnostic System (MMDx). Ensembles generated diagnoses that were both more accurate than the best individual classifiers, and nearly as stable as the best, consistent with expectations from the machine learning literature. Human experts had ~93% agreement (balanced accuracy) signing out the reports, and random forest-based automated sign-outs showed similar levels of agreement with the human experts (92% and 94% for predicting the expert MMDx sign-outs for T cell-mediated (TCMR) and antibody-mediated rejection (ABMR) respectively). In most cases disagreements, whether between experts or between experts and automated sign-outs, were in biopsies near diagnostic thresholds. Considerable disagreement with histology persisted. The balanced accuracies of MMDx sign-outs for histology diagnoses of TCMR and ABMR were 73% and 78% respectively. Disagreement with histology is largely due to the known noise in histology assessments (ClinicalTrials.gov NCT01299168).
2019-11-07 | GSE124203 | GEO
Project description:We have established a certification system for antibodies to be used in chromatin immunoprecipitation assays coupled to massive parallel sequencing (ChIP-seq). This certification comprises a standardized ChIP procedure and the attribution of a numerical quality control indicator (QCi) to biological replicate experiments. The QCi computation is based on a universally applicable quality assessment that quantitates the global deviation of randomly sampled subsets of ChIP-seq dataset with the original genome-aligned sequence reads. Comparison with a QCi database for >28,000 ChIP-seq assays were used to attribute quality grades (ranging from âAAAâ to âDDDâ) to a given dataset. In the present report we used the numerical QC system to assess the factors influencing the quality of ChIP-seq assays, including the nature of the target, the sequencing depth and the commercial source of the antibody. We have used this approach specifically to certify mono and polyclonal antibodies obtained from Active Motif directed against the histone modification marks H3K4me3, H3K27ac and H3K9ac for ChIP-seq. The antibodies received the grades AAA to BBA (www.ngs-qc.org). We propose to attribute such quantitative grading of all antibodies attributed with the label âChIP-seq gradeâ. The NGS-QC team has setup a certification procedure for Antibodies dedicated to ChIP-seq applications based on (1)a highly reproducible pipeline for performing ChIP-seq assays including the use of an automated liquid handling platform (TECAN EVO75) for ChIP and sequencing library preparation steps and (2) the use of the NGS-QC Generator tool for providing a ChIP-seq quality grade and to evaluate other parameters like the Optimal sequencing depth, the degree of reproducibility among biological replicates and the comparison of the quality grades of the certified antibody with datasets retrieved in the public domain. This quality certification structure makes possible to assign a measured Quality Stamp to ChIP-seq grade Antibodies.
2016-01-07 | E-GEOD-76618 | biostudies-arrayexpress
Project description:damidseq_pipeline: an automated pipeline for processing DamID sequencing datasets
| PRJNA284767 | ENA
Project description:Targeted determination of pri-miRNA processing
| PRJNA625651 | ENA