Identifying Goals of Care Conversations in the Electronic Health Record Using Natural Language Processing and Machine Learning |
| |
| Authors: | Robert Y. Lee Lyndia C. Brumback William B. Lober James Sibley Elizabeth L. Nielsen Patsy D. Treece Erin K. Kross Elizabeth T. Loggers James A. Fausto Charlotta Lindvall Ruth A. Engelberg J. Randall Curtis |
| |
| Affiliation: | 1. Cambia Palliative Care Center of Excellence, University of Washington, Seattle, Washington, USA;2. Division of Pulmonary, Critical Care, and Sleep Medicine, Department of Medicine, Harborview Medical Center, University of Washington, Seattle, Washington, USA;3. Department of Biostatistics, University of Washington, Seattle, Washington, USA;4. Department of Biobehavioral Nursing and Health Informatics, University of Washington, Seattle, Washington, USA;5. Department of Bioinformatics and Medical Education, University of Washington, Seattle, Washington, USA;6. Department of Bioethics and Humanities, University of Washington, Seattle, Washington, USA;7. Department of Family Medicine, University of Washington, Seattle, Washington, USA;8. Clinical Research Division, Fred Hutchinson Cancer Research Center, Seattle, Washington, USA;9. Seattle Cancer Care Alliance, Seattle, Washington, USA;10. Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute, Boston, Massachusetts, USA;1. University of Technology Sydney, Ultimo, New South Wales, Australia;2. St Vincent Hospital, Darlinghurst, New South Wales, Australia;3. Calvary Hospital, Kogarah, New South Wales, Australia;4. University of Notre Dame Australia, New South Wales, Australia;5. University of New South Wales, Randwick, New South Wales, Australia;1. Department of Pediatrics, University of Alabama at Birmingham, Birmingham, Alabama, USA;2. Institute for Cancer Outcomes and Survivorship, University of Alabama at Birmingham, Birmingham, Alabama, USA;3. Department of Palliative and Supportive Care, University of Alabama at Birmingham, Birmingham, Alabama, USA;4. Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute, Boston, Massachusetts, USA;5. Department of Pediatrics, Boston Children''s Hospital, Boston, Massachusetts, USA;6. Pastoral Care Department, Children''s of Alabama, Birmingham, Alabama, USA;1. Department of Palliative, Rehabilitation and Integrative Medicine, The University of Texas MD Anderson Cancer, Houston, Texas, USA;2. Department of Biostatistics, The University of Texas MD Anderson Cancer, Houston, Texas, USA;1. Division of Research, Kaiser Permanente Northern California, Oakland, California;2. Department of Cardiology, Kaiser Oakland Medical Center, Oakland, California;3. Department of Health Systems Science, Kaiser Permanente Bernard J. Tyson School of Medicine, Pasadena, California;4. Departments of Epidemiology, Biostatistics and Medicine, University of California, San Francisco, San Francisco, California;6. Department of Medicine, Stanford University, Stanford, California |
| |
| Abstract: | ContextGoals-of-care discussions are an important quality metric in palliative care. However, goals-of-care discussions are often documented as free text in diverse locations. It is difficult to identify these discussions in the electronic health record (EHR) efficiently.ObjectivesTo develop, train, and test an automated approach to identifying goals-of-care discussions in the EHR, using natural language processing (NLP) and machine learning (ML).MethodsFrom the electronic health records of an academic health system, we collected a purposive sample of 3183 EHR notes (1435 inpatient notes and 1748 outpatient notes) from 1426 patients with serious illness over 2008–2016, and manually reviewed each note for documentation of goals-of-care discussions. Separately, we developed a program to identify notes containing documentation of goals-of-care discussions using NLP and supervised ML. We estimated the performance characteristics of the NLP/ML program across 100 pairs of randomly partitioned training and test sets. We repeated these methods for inpatient-only and outpatient-only subsets.ResultsOf 3183 notes, 689 contained documentation of goals-of-care discussions. The mean sensitivity of the NLP/ML program was 82.3% (SD 3.2%), and the mean specificity was 97.4% (SD 0.7%). NLP/ML results had a median positive likelihood ratio of 32.2 (IQR 27.5–39.2) and a median negative likelihood ratio of 0.18 (IQR 0.16–0.20). Performance was better in inpatient-only samples than outpatient-only samples.ConclusionUsing NLP and ML techniques, we developed a novel approach to identifying goals-of-care discussions in the EHR. NLP and ML represent a potential approach toward measuring goals-of-care discussions as a research outcome and quality metric. |
| |
| Keywords: | Natural language processing machine learning goals of care electronic health record quality improvement medical informatics |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
