Literature DB >> 33383291

Topic modeling to characterize the natural history of ANCA-Associated vasculitis from clinical notes: A proof of concept study.

Liqin Wang1, Eli Miloslavsky2, John H Stone2, Hyon K Choi3, Li Zhou1, Zachary S Wallace4.   

Abstract

OBJECTIVES: Clinical notes from electronic health records (EHR) are important to characterize the natural history, comorbidities, and complications of ANCA-associated vasculitis (AAV) because these details may not be captured by claims and structured data. However, labor-intensive chart review is often required to extract information from notes. We hypothesized that machine learning can automatically discover clinically-relevant themes across longitudinal notes to study AAV.
METHODS: This retrospective study included prevalent PR3- or MPO-ANCA+ AAV cases managed within the Mass General Brigham integrated health care system with providers' notes available between March 1, 1990 and August 23, 2018. We generated clinically-relevant topics mentioned in notes using latent Dirichlet allocation-based topic modeling and conducted trend analyses of those topics over the 2 years prior to and 5 years after the initiation of AAV-specific treatment.
RESULTS: The study cohort included 660 patients with AAV. We generated 90 topics using 113,048 available notes. Topics were related to the AAV diagnosis, treatment, symptoms and manifestations (e.g., glomerulonephritis), and complications (e.g., end-stage renal disease, infection). AAV-related symptoms and psychiatric symptoms were mentioned months before treatment initiation. Topics related to pulmonary and renal diseases, diabetes, and infections were common during the disease course but followed distinct temporal patterns.
CONCLUSIONS: Automated topic modeling can be used to discover clinically-relevant themes and temporal patterns related to the diagnosis, treatment, comorbidities, and complications of AAV from EHR notes. Future research might compare the temporal patterns in a non-AAV cohort and leverage clinical notes to identify possible AAV cases prospectively.
Copyright © 2020 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  ANCA-Associated Vasculitis; Electronic Health Records; Epidemiology; Natural Language Processing; Topic Modeling

Mesh:

Substances:

Year:  2020        PMID: 33383291      PMCID: PMC7902471          DOI: 10.1016/j.semarthrit.2020.10.012

Source DB:  PubMed          Journal:  Semin Arthritis Rheum        ISSN: 0049-0172            Impact factor:   5.532


  28 in total

1.  A security architecture for query tools used to access large biomedical databases.

Authors:  Shawn N Murphy; Henry C Chueh
Journal:  Proc AMIA Symp       Date:  2002

2.  Finding scientific topics.

Authors:  Thomas L Griffiths; Mark Steyvers
Journal:  Proc Natl Acad Sci U S A       Date:  2004-02-10       Impact factor: 11.205

3.  SNOMED-CT: The advanced terminology and coding system for eHealth.

Authors:  Kevin Donnelly
Journal:  Stud Health Technol Inform       Date:  2006

4.  Epidemiology and Outcomes of Granulomatosis With Polyangiitis in Pediatric and Working-Age Adult Populations In the United States: Analysis of a Large National Claims Database.

Authors:  Sirada Panupattanapong; Dustin L Stwalley; Andrew J White; Margaret A Olsen; Anthony R French; Mary E Hartman
Journal:  Arthritis Rheumatol       Date:  2018-12       Impact factor: 10.995

5.  Missing clinical information during primary care visits.

Authors:  Peter C Smith; Rodrigo Araya-Guerra; Caroline Bublitz; Bennett Parnes; L Miriam Dickinson; Rebecca Van Vorst; John M Westfall; Wilson D Pace
Journal:  JAMA       Date:  2005-02-02       Impact factor: 56.272

6.  Patients treated at multiple acute health care facilities: quantifying information fragmentation.

Authors:  Fabienne C Bourgeois; Karen L Olson; Kenneth D Mandl
Journal:  Arch Intern Med       Date:  2010-12-13

7.  The characterisation and determinants of quality of life in ANCA associated vasculitis.

Authors:  Neil Basu; Andrew McClean; Lorraine Harper; Esther Nicole Amft; Neeraj Dhaun; Raashid A Luqmani; Mark A Little; David Rw Jayne; Oliver Flossmann; John McLaren; Vinod Kumar; Lars P Erwig; David M Reid; Gareth T Jones; Gary J Macfarlane
Journal:  Ann Rheum Dis       Date:  2013-01-25       Impact factor: 19.103

8.  Patients' Use of Multiple Hospitals in a Major US City: Implications for Population Management.

Authors:  Lisa M Kern; Zachary Grinspan; Jason S Shapiro; Rainu Kaushal
Journal:  Popul Health Manag       Date:  2016-06-07       Impact factor: 2.459

9.  Development and Validation of a Deep Learning Algorithm for Mortality Prediction in Selecting Patients With Dementia for Earlier Palliative Care Interventions.

Authors:  Liqin Wang; Long Sha; Joshua R Lakin; Julie Bynum; David W Bates; Pengyu Hong; Li Zhou
Journal:  JAMA Netw Open       Date:  2019-07-03

Review 10.  An overview of topic modeling and its current applications in bioinformatics.

Authors:  Lin Liu; Lin Tang; Wen Dong; Shaowen Yao; Wei Zhou
Journal:  Springerplus       Date:  2016-09-20
View more
  2 in total

1.  Mining Medication Use Patterns from Clinical Notes for Breast Cancer Patients Through a Two-Stage Topic Modeling Approach.

Authors:  Kimberley Es Kondratieff; J Thomas Brown; Marily Barron; Jeremy L Warner; Zhijun Yin
Journal:  AMIA Annu Symp Proc       Date:  2022-05-23

2.  Validation of Antineutrophil Cytoplasmic Antibody-Associated Vasculitis as the Cause of End-Stage Renal Disease in the US Renal Data System.

Authors:  Claire E Cook; Xiaoqing Fu; Yuqing Zhang; John H Stone; Hyon K Choi; Zachary S Wallace
Journal:  ACR Open Rheumatol       Date:  2021-10-12
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.