Literature DB >> 35182715

Mixed-methods evaluation of three natural language processing modeling approaches for measuring documented goals-of-care discussions in the electronic health record.

Alison M Uyeda1, J Randall Curtis2, Ruth A Engelberg3, Lyndia C Brumback4, Yue Guo5, James Sibley6, William B Lober7, Trevor Cohen5, Janaki Torrence3, Joanna Heywood3, Sudiptho R Paul3, Erin K Kross3, Robert Y Lee3.   

Abstract

CONTEXT: Documented goals-of-care discussions are an important quality metric for patients with serious illness. Natural language processing (NLP) is a promising approach for identifying goals-of-care discussions in the electronic health record (EHR).
OBJECTIVES: To compare three NLP modeling approaches for identifying EHR documentation of goals-of-care discussions and generate hypotheses about differences in performance.
METHODS: We conducted a mixed-methods study to evaluate performance and misclassification for three NLP featurization approaches modeled with regularized logistic regression: bag-of-words (BOW), rule-based, and a hybrid approach. From a prospective cohort of 150 patients hospitalized with serious illness over 2018 to 2020, we collected 4391 inpatient EHR notes; 99 (2.3%) contained documented goals-of-care discussions. We used leave-one-out cross-validation to estimate performance by comparing pooled NLP predictions to human abstractors with receiver-operating-characteristic (ROC) and precision-recall (PR) analyses. We qualitatively examined a purposive sample of 70 NLP-misclassified notes using content analysis to identify linguistic features that allowed us to generate hypotheses underpinning misclassification.
RESULTS: All three modeling approaches discriminated between notes with and without goals-of-care discussions (AUCROC: BOW, 0.907; rule-based, 0.948; hybrid, 0.965). Precision and recall were only moderate (precision at 70% recall: BOW, 16.2%; rule-based, 50.4%; hybrid, 49.3%; AUCPR: BOW, 0.505; rule-based, 0.579; hybrid, 0.599). Qualitative analysis revealed patterns underlying performance differences between BOW and rule-based approaches.
CONCLUSION: NLP holds promise for identifying EHR-documented goals-of-care discussions. However, the rarity of goals-of-care content in EHR data limits performance. Our findings highlight opportunities to optimize NLP modeling approaches, and support further exploration of different NLP approaches to identify goals-of-care discussions.
Copyright © 2022 American Academy of Hospice and Palliative Medicine. Published by Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Natural language processing; electronic health record; goals of care; machine learning; medical informatics

Mesh:

Year:  2022        PMID: 35182715      PMCID: PMC9124686          DOI: 10.1016/j.jpainsymman.2022.02.006

Source DB:  PubMed          Journal:  J Pain Symptom Manage        ISSN: 0885-3924            Impact factor:   5.576


  53 in total

1.  Sensitivity and Specificity of a Machine Learning Algorithm to Identify Goals-of-care Documentation for Adults With Congenital Heart Disease at the End of Life.

Authors:  Jill M Steiner; Christina Morse; Robert Y Lee; J Randall Curtis; Ruth A Engelberg
Journal:  J Pain Symptom Manage       Date:  2020-06-26       Impact factor: 3.612

2.  The precision--recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases.

Authors:  Brice Ozenne; Fabien Subtil; Delphine Maucort-Boulch
Journal:  J Clin Epidemiol       Date:  2015-02-28       Impact factor: 6.437

Review 3.  Natural language processing in biomedicine: a unified system architecture overview.

Authors:  Son Doan; Mike Conway; Tu Minh Phuong; Lucila Ohno-Machado
Journal:  Methods Mol Biol       Date:  2014

Review 4.  Deep learning in clinical natural language processing: a methodical review.

Authors:  Stephen Wu; Kirk Roberts; Surabhi Datta; Jingcheng Du; Zongcheng Ji; Yuqi Si; Sarvesh Soni; Qiong Wang; Qiang Wei; Yang Xiang; Bo Zhao; Hua Xu
Journal:  J Am Med Inform Assoc       Date:  2020-03-01       Impact factor: 4.497

5.  National Consensus Project Clinical Practice Guidelines for Quality Palliative Care Guidelines, 4th Edition.

Authors:  Betty R Ferrell; Martha L Twaddle; Amy Melnick; Diane E Meier
Journal:  J Palliat Med       Date:  2018-09-04       Impact factor: 2.947

Review 6.  Natural language processing systems for capturing and standardizing unstructured clinical information: A systematic review.

Authors:  Kory Kreimeyer; Matthew Foster; Abhishek Pandey; Nina Arya; Gwendolyn Halford; Sandra F Jones; Richard Forshee; Mark Walderhaug; Taxiarchis Botsis
Journal:  J Biomed Inform       Date:  2017-07-17       Impact factor: 6.317

7.  The impact of advance care planning on end of life care in elderly patients: randomised controlled trial.

Authors:  Karen M Detering; Andrew D Hancock; Michael C Reade; William Silvester
Journal:  BMJ       Date:  2010-03-23

Review 8.  Artificial intelligence in healthcare: past, present and future.

Authors:  Fei Jiang; Yong Jiang; Hui Zhi; Yi Dong; Hao Li; Sufeng Ma; Yilong Wang; Qiang Dong; Haipeng Shen; Yongjun Wang
Journal:  Stroke Vasc Neurol       Date:  2017-06-21

9.  A Method of Short Text Representation Based on the Feature Probability Embedded Vector.

Authors:  Wanting Zhou; Hanbin Wang; Hongguang Sun; Tieli Sun
Journal:  Sensors (Basel)       Date:  2019-08-28       Impact factor: 3.576

10.  The retrospective chart review: important methodological considerations.

Authors:  Matt Vassar; Matthew Holzmann
Journal:  J Educ Eval Health Prof       Date:  2013-11-30
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.