Dataset Information

Multiscale classification of heart failure phenotypes by unsupervised clustering of unstructured electronic medical record data.

ABSTRACT: As a leading cause of death and morbidity, heart failure (HF) is responsible for a large portion of healthcare and disability costs worldwide. Current approaches to define specific HF subpopulations may fail to account for the diversity of etiologies, comorbidities, and factors driving disease progression, and therefore have limited value for clinical decision making and development of novel therapies. Here we present a novel and data-driven approach to understand and characterize the real-world manifestation of HF by clustering disease and symptom-related clinical concepts (complaints) captured from unstructured electronic health record clinical notes. We used natural language processing to construct vectorized representations of patient complaints followed by clustering to group HF patients by similarity of complaint vectors. We then identified complaints that were significantly enriched within each cluster using statistical testing. Breaking the HF population into groups of similar patients revealed a clinically interpretable hierarchy of subgroups characterized by similar HF manifestation. Importantly, our methodology revealed well-known etiologies, risk factors, and comorbid conditions of HF (including ischemic heart disease, aortic valve disease, atrial fibrillation, congenital heart disease, various cardiomyopathies, obesity, hypertension, diabetes, and chronic kidney disease) and yielded additional insights into the details of each HF subgroup's clinical manifestation of HF. Our approach is entirely hypothesis free and can therefore be readily applied for discovery of novel insights in alternative diseases or patient populations.

SUBMITTER: Nagamine T

PROVIDER: S-EPMC7721729 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multiscale classification of heart failure phenotypes by unsupervised clustering of unstructured electronic medical record data.

Nagamine Tasha T Gillette Brian B Pakhomov Alexey A Kahoun John J Mayer Hannah H Burghaus Rolf R Lippert Jörg J Saxena Mayur M

Scientific reports 20201207 1

As a leading cause of death and morbidity, heart failure (HF) is responsible for a large portion of healthcare and disability costs worldwide. Current approaches to define specific HF subpopulations may fail to account for the diversity of etiologies, comorbidities, and factors driving disease progression, and therefore have limited value for clinical decision making and development of novel therapies. Here we present a novel and data-driven approach to understand and characterize the real-world ...[more]

PMID: 33288774

Similar Datasets

Project description:BackgroundWe sought to systematically standardize the documentation of clinical and laboratory features in Kawasaki disease (KD) on the day of initial treatment and correlate the presentation with clinical outcomes.MethodsKawasaki disease features and classification were documented by the attending physician using a standardized documentation tool on the day of treatment for KD, including confidence in the KD diagnosis on a 4-point scale. Incomplete KD was further classified using American Heart Association (AHA) criteria (sufficient or insufficient) and baseline echocardiogram data. We prospectively recorded intravenous immunoglobulin (IVIG) resistance, coronary artery abnormalities (CAAs), periungual peeling, and retrospectively identified subsequent diagnoses of autoimmune/inflammatory disease.ResultsFrom November 2012 to October, 2015, 162 patients were treated for KD: 105 with complete KD (Group 1), 7 with incomplete KD based on CAAs on day of KD diagnosis (Group 2), 23 with incomplete KD meeting AHA criteria (Group 3), and 27 with incomplete KD and insufficient AHA criteria (Group 4). Group 4 patients had lower baseline median C-reactive protein levels (Group 4 median 4.65 mg/dL [interquartile range {IQR}, 2.3-13.6] vs Group 1 median 8.0 mg/dL [IQR, 4.5-17], Group 2 median 13.9 mg/dL [IQR, 1.4-18.2], Group 3 median 13.3 mg/dL [IQR, 4.9-20.2]), and no coronary abnormalities developed, although 11% had IVIG resistance. Group 4 had higher rates of subsequent autoimmune/inflammatory conditions diagnosed (11.1% in Group 4 vs <5% for all others, P = .02).ConclusionsStandardized documentation and classification of KD features may be useful to correlate with clinical outcomes, including subsequent diagnosis of autoimmune/autoinflammatory disease. Among patients with incomplete KD who did not meet AHA criteria and had a normal baseline echocardiogram, the IVIG resistance rate may have been related to a lower likelihood of an accurate diagnosis of KD.

Project description:Unstructured clinical narratives are continuously being recorded as part of delivery of care in electronic health records, and dedicated tagging staff spend considerable effort manually assigning clinical codes for billing purposes. Despite these efforts, however, label availability and accuracy are both suboptimal. In this retrospective study, we aimed to automate the assignment of top-level International Classification of Diseases version 9 (ICD-9) codes to clinical records from human and veterinary data stores using minimal manual labor and feature curation. Automating top-level annotations could in turn enable rapid cohort identification, especially in a veterinary setting. To this end, we trained long short-term memory (LSTM) recurrent neural networks (RNNs) on 52,722 human and 89,591 veterinary records. We investigated the accuracy of both separate-domain and combined-domain models and probed model portability. We established relevant baseline classification performances by training Decision Trees (DT) and Random Forests (RF). We also investigated whether transforming the data using MetaMap Lite, a clinical natural language processing tool, affected classification performance. We showed that the LSTM-RNNs accurately classify veterinary and human text narratives into top-level categories with an average weighted macro F1 score of 0.74 and 0.68 respectively. In the "neoplasia" category, the model trained on veterinary data had a high validation accuracy in veterinary data and moderate accuracy in human data, with F1 scores of 0.91 and 0.70 respectively. Our LSTM method scored slightly higher than that of the DT and RF models. The use of LSTM-RNN models represents a scalable structure that could prove useful in cohort identification for comparative oncology studies. Digitization of human and veterinary health information will continue to be a reality, particularly in the form of unstructured narratives. Our approach is a step forward for these two domains to learn from and inform one another.

Dataset Information

Multiscale classification of heart failure phenotypes by unsupervised clustering of unstructured electronic medical record data.

Publications

Multiscale classification of heart failure phenotypes by unsupervised clustering of unstructured electronic medical record data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets