Comparison of Methods To Identify Advance Care Planning in Patients with Severe Chronic Obstructive Pulmonary Disease Exacerbation

Using Natural Language Processing to Classify Serious Illness Communication with Oncology Patients

One core measure of healthcare quality set forth by the Institute of Medicine is whether care decisions match patient goals. High-quality "serious illness communication" about patient goals and prognosis is required to support patient-centered decision-making, however current methods are not sensitive enough to measure the quality of this communication or determine whether care delivered matches patient priorities. Natural language processing (NLP) offers an efficient method for identification and evaluation of documented serious illness communication, which could serve as the basis for future quality metrics in oncology and other forms of serious illness. In this study, we trained NLP algorithms to identify and characterize serious illness communication with oncology patients.

Identifying Goals of Care Conversations in the Electronic Health Record Using Natural Language Processing and Machine Learning

CONTEXT

Goals-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.

OBJECTIVES

To 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).

METHODS

From 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.

RESULTS

Of 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.

CONCLUSION

Using 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.

Advance Care Planning for Individuals With Chronic Obstructive Pulmonary Disease: A Scoping Review of the Literature

CONTEXT

Individuals with chronic obstructive pulmonary disease (COPD) typically experience a gradual worsening of the illness in the years before death. Owing to difficulties in predicting the disease trajectory or the timing of acute exacerbations, advance care planning (ACP) may be of particular importance for individuals with COPD.

OBJECTIVES

The objective of this study was to review and summarize the available literature on current practices around ACP in COPD.

METHODS

A scoping review of the literature was conducted following the Arksey and O'Malley framework. Original research studies of any design were included.

RESULTS

Twenty-eight studies were included. Across studies, there was agreement that ACP should be incorporated into routine COPD management. There was evidence that this does not occur in everyday practice, with conversations tending to focus on day-to-day symptom management. Barriers included prognosis uncertainty, insufficient time and training, and a lack of protocols for who is responsible for initiating ACP. Facilitators included the use of transition points for identifying the appropriate time to initiate ACP, and an increased focus on ACP in professional education. The occurrence of repeated episodes of acute care was identified as a key transition point for identifying the palliative stage of COPD and an appropriate time to initiate ACP.

CONCLUSION

The findings of this review confirm agreement among health care professionals and patients with COPD and their carers that ACP should be incorporated into routine COPD management. The use of transition points may help health care professionals overcome the barrier of prognosis uncertainty and identify patients who might benefit from ACP.

Psychometric Testing of the Korean Version of the Attitudes toward the Advance Directives in Low-Income Chronically Ill Older Adults

The purpose of this study was to examine the psychometric properties of the Advance Directive Attitude Survey in Korean (K-ADAS), a measure of attitudes toward advance directives (ADs). A total of 118 low-income, community-dwelling older adults (mean age, 75.09 years) participated. An exploratory factor analysis (EFA) was conducted to determine the factor structure of the K-ADAS. Validity was further assessed by known associations of the K-ADAS with perceived susceptibility and severity using part of the Advance Care Planning surveys. Its reliability was examined by calculating alpha coefficients. EFA determined a three-factor structure model with good model fit. Validity was further supported with significant correlations between the K-ADAS and susceptibility and severity. Reliability was supported by adequate level of Cronbach’s alpha. The K-ADAS was a valid and reliable measure for assessment of AD attitudes with a sound model fit. Thus, the K-ADAS can be used to assess AD attitudes among community-dwelling elders.