Development of a natural language processing pipeline for assessment of cardiovascular risk in myeloproliferative neoplasms.
Ontology highlight
ABSTRACT:
SUBMITTER: Duminuco A
PROVIDER: S-EPMC11310405 | biostudies-literature | 2024 Aug
REPOSITORIES: biostudies-literature
Publications
Development of a natural language processing pipeline for assessment of cardiovascular risk in myeloproliferative neoplasms.
Duminuco Andrea A Au Yeung Joshua J Vaghela Raj R Virdee Sukhraj S Woodley Claire C Asirvatham Susan S Curto-Garcia Natalia N Sriskandarajah Priya P O'Sullivan Jennifer J de Lavallade Hugues H Radia Deepti D Kordasti Shahram S Palumbo Giuseppe G Harrison Claire C Harrington Patrick P
HemaSphere 20240808 8
Similar Datasets
Project description:We sought to apply natural language processing to the task of automatic risk of bias assessment in preclinical literature, which could speed the process of systematic review, provide information to guide research improvement activity, and support translation from preclinical to clinical research. We use 7840 full-text publications describing animal experiments with yes/no annotations for five risk of bias items. We implement a series of models including baselines (support vector machine, logistic regression, random forest), neural models (convolutional neural network, recurrent neural network with attention, hierarchical neural network) and models using BERT with two strategies (document chunk pooling and sentence extraction). We tune hyperparameters to obtain the highest F1 scores for each risk of bias item on the validation set and compare evaluation results on the test set to our previous regular expression approach. The F1 scores of best models on test set are 82.0% for random allocation, 81.6% for blinded assessment of outcome, 82.6% for conflict of interests, 91.4% for compliance with animal welfare regulations and 46.6% for reporting animals excluded from analysis. Our models significantly outperform regular expressions for four risk of bias items. For random allocation, blinded assessment of outcome, conflict of interests and animal exclusions, neural models achieve good performance; for animal welfare regulations, BERT model with a sentence extraction strategy works better. Convolutional neural networks are the overall best models. The tool is publicly available which may contribute to the future monitoring of risk of bias reporting for research improvement activities.
| S-EPMC9298308 | biostudies-literature
Project description:ObjectiveAccurate ascertainment of comorbidities is paramount in clinical research. While manual adjudication is labor-intensive and expensive, the adoption of electronic health records enables computational analysis of free-text documentation using natural language processing (NLP) tools.HypothesisWe sought to develop highly accurate NLP modules to assess for the presence of five key cardiovascular comorbidities in a large electronic health record system.MethodsOne-thousand clinical notes were randomly selected from a cardiovascular registry at Mass General Brigham. Trained physicians manually adjudicated these notes for the following five diagnostic comorbidities: hypertension, dyslipidemia, diabetes, coronary artery disease, and stroke/transient ischemic attack. Using the open-source Canary NLP system, five separate NLP modules were designed based on 800 "training-set" notes and validated on 200 "test-set" notes.ResultsAcross the five NLP modules, the sentence-level and note-level sensitivity, specificity, and positive predictive value was always greater than 85% and was most often greater than 90%. Accuracy tended to be highest for conditions with greater diagnostic clarity (e.g. diabetes and hypertension) and slightly lower for conditions whose greater diagnostic challenges (e.g. myocardial infarction and embolic stroke) may lead to less definitive documentation.ConclusionWe designed five open-source and highly accurate NLP modules that can be used to assess for the presence of important cardiovascular comorbidities in free-text health records. These modules have been placed in the public domain and can be used for clinical research, trial recruitment and population management at any institution as well as serve as the basis for further development of cardiovascular NLP tools.
| S-EPMC8428009 | biostudies-literature
Project description:Philadelphia chromosome-negative myeloproliferative neoplasms (MPN) are clonal disorders of a hematopoietic stem cell, characterized by an abnormal proliferation of largely mature cells driven by mutations in JAK2, CALR, and MPL. All these mutations lead to a constitutive activation of the JAK-STAT signaling, which represents a target for therapy. Beyond driver ones, most patients, especially with myelofibrosis, harbor mutations in an array of "myeloid neoplasm-associated" genes that encode for proteins involved in chromatin modification and DNA methylation, RNA splicing, transcription regulation, and oncogenes. These additional mutations often arise in the context of clonal hematopoiesis of indeterminate potential (CHIP). The extensive characterization of the pathologic genome associated with MPN highlighted selected driver and non-driver mutations for their clinical informativeness. First, driver mutations are enlisted in the WHO classification as major diagnostic criteria and may be used for monitoring of residual disease after transplantation and response to treatment. Second, mutation profile can be used, eventually in combination with cytogenetic, histopathologic, hematologic, and clinical variables, to risk stratify patients regarding thrombosis, overall survival, and rate of transformation to secondary leukemia. This review outlines the molecular landscape of MPN and critically interprets current information for their potential impact on patient management.
| S-EPMC8391705 | biostudies-literature
Project description:Chronic myeloproliferative neoplasms (MPNs) are a group of related conditions characterized by the overproduction of cells from one or more myeloid lineages. More than 95% of cases of polycythemia vera, and roughly half of essential thrombocythemia and primary myelofibrosis acquire a unique somatic 1849G>T JAK2 mutation (encoding V617F) that is believed to be a critical driver of excess proliferation. We report here that JAK2(V617F)-associated disease is strongly associated with a specific constitutional JAK2 haplotype, designated 46/1, in all three disease entities compared to healthy controls (polycythemia vera, n = 192, P = 2.9 x 10(-16); essential thrombocythemia, n = 78, P = 8.2 x 10(-9) and myelofibrosis, n = 41, P = 8.0 x 10(-5)). Furthermore, JAK2(V617F) specifically arises on the 46/1 allele in most cases. The 46/1 JAK2 haplotype thus predisposes to the development of JAK2(V617F)-associated MPNs (OR = 3.7; 95% CI = 3.1-4.3) and provides a model whereby a constitutional genetic factor is associated with an increased risk of acquiring a specific somatic mutation.
| S-EPMC4120192 | biostudies-literature
Project description:PurposePerformance status (PS), an essential indicator of patients' functional abilities, is often documented in clinical notes of patients with cancer. The use of natural language processing (NLP) in extracting PS from electronic medical records (EMRs) has shown promise in enhancing clinical decision-making, patient monitoring, and research studies. We designed and validated a multi-institute NLP pipeline to automatically extract performance status from free-text patient notes.Patients and methodsWe collected data from 19,481 patients in Harris Health System (HHS) and 333,862 patients from veteran affair's corporate data warehouse (VA-CDW) and randomly selected 400 patients from each data source to train and validate (50%) and test (50%) the proposed pipeline. We designed an NLP pipeline using an expert-derived rule-based approach in conjunction with extensive post-processing to solidify its proficiency. To demonstrate the pipeline's application, we tested the compliance of PS documentation suggested by the American Society of Clinical Oncology (ASCO) Quality Metric and investigated the potential disparity in PS reporting for stage IV non-small cell lung cancer (NSCLC). We used a logistic regression test, considering patients in terms of race/ethnicity, conversing language, marital status, and gender.ResultsThe test results on the HHS cohort showed 92% accuracy, and on VA data demonstrated 98.5% accuracy. For stage IV NSCLC patients, the proposed pipeline achieved an accuracy of 98.5%. Furthermore, our analysis revealed a documentation rate of over 85% for PS among NSCLC patients, surpassing the ASCO Quality Metrics. No disparities were observed in the documentation of PS.ConclusionOur proposed NLP pipeline shows promising results in extracting PS from free-text notes from various health institutions. It may be used in longitudinal cancer data registries.
| S-EPMC11369884 | biostudies-literature
Project description:[This corrects the article DOI: 10.2196/36119.].
| S-EPMC8990338 | biostudies-literature
Project description:The developmental history of blood cancer begins with mutation acquisition and the resulting malignant clone expansion. The two most prevalent driver mutations found in myeloproliferative neoplasms-JAK2V617F and CALRm-occur in hematopoietic stem cells, which are highly complex to observe in vivo. To circumvent this difficulty, we propose a method relying on mathematical modeling and statistical inference to determine disease initiation and dynamics. Our findings suggest that CALRm mutations tend to occur later in life than JAK2V617F. Our results confirm the higher proliferative advantage of the CALRm malignant clone compared to JAK2V617F. Furthermore, we illustrate how mathematical modeling and Bayesian inference can be used for setting up early screening strategies.
| S-EPMC9478641 | biostudies-literature
Project description:Cardiovascular events are the leading cause of death in patients with JAK2V617F myeloproliferative neoplasms. Their mechanisms are poorly understood. To investigate the role of microvesicles in these events, we performed a proteomic analysis of microvesicles derived from red blood cells from mice with a myeloproliferative neoplasms (Jak2V617F Flex/WT ;VE-cadherin-Cre) vs. littermate controls.
2020-02-17 | PXD014451 | Pride
Project description:BackgroundProcessing data from electronic health records (EHRs) to build research-grade databases is a lengthy and expensive process. Modern arthroplasty practice commonly uses multiple sites of care, including clinics and ambulatory care centers. However, most private data systems prevent obtaining usable insights for clinical practice.ObjectiveThis study aims to create an automated natural language processing (NLP) pipeline for extracting clinical concepts from EHRs related to orthopedic outpatient visits, hospitalizations, and surgeries in a multicenter, single-surgeon practice. The pipeline was also used to assess therapies and complications after total hip arthroplasty (THA).MethodsEHRs of 1290 patients undergoing primary THA from January 1, 2012 to December 31, 2019 (operated and followed by the same surgeon) were processed using artificial intelligence (AI)-based models (NLP and machine learning). In addition, 3 independent medical reviewers generated a gold standard using 100 randomly selected EHRs. The algorithm processed the entire database from different EHR systems, generating an aggregated clinical data warehouse. An additional manual control arm was used for data quality control.ResultsThe algorithm was as accurate as human reviewers (0.95 vs 0.94; P=.01), achieving a database-wide average F1-score of 0.92 (SD 0.09; range 0.67-0.99), validating its use as an automated data extraction tool. During the first year after direct anterior THA, 92.1% (1188/1290) of our population had a complication-free recovery. In 7.9% (102/1290) of cases where surgery or recovery was not uneventful, lateral femoral cutaneous nerve sensitivity (47/1290, 3.6%), intraoperative fractures (13/1290, 1%), and hematoma (9/1290, 0.7%) were the most common complications.ConclusionsAlgorithm evaluation of this dataset accurately represented key clinical information swiftly, compared with human reviewers. This technology may provide substantial value for future surgeon practice and patient counseling. Furthermore, the low early complication rate of direct anterior THA in this surgeon's hands was supported by the dataset, which included data from all treated patients in a multicenter practice.
| S-EPMC11922490 | biostudies-literature
Project description:The ever-increasing number of materials science articles makes it hard to infer chemistry-structure-property relations from literature. We used natural language processing methods to automatically extract material property data from the abstracts of polymer literature. As a component of our pipeline, we trained MaterialsBERT, a language model, using 2.4 million materials science abstracts, which outperforms other baseline models in three out of five named entity recognition datasets. Using this pipeline, we obtained ~300,000 material property records from ~130,000 abstracts in 60 hours. The extracted data was analyzed for a diverse range of applications such as fuel cells, supercapacitors, and polymer solar cells to recover non-trivial insights. The data extracted through our pipeline is made available at polymerscholar.org which can be used to locate material property data recorded in abstracts. This work demonstrates the feasibility of an automatic pipeline that starts from published literature and ends with extracted material property information.
| S-EPMC10073792 | biostudies-literature