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.

Creating a Palliative Care Inpatient Response Plan for COVID-19-The UW Medicine Experience.

CONTEXT: The coronavirus disease 2019 (COVID-19) pandemic is stressing health care systems throughout the world. Significant numbers of patients are being admitted to the hospital with severe illness, often in the setting of advanced age and underlying comorbidities. Therefore, palliative care is an important part of the response to this pandemic. The Seattle area and UW Medicine have been on the forefront of the pandemic in the U.S. METHODS: UW Medicine developed a strategy to implement a palliative care response for a multihospital health care system that incorporates conventional capacity, contingency capacity, and crisis capacity. The strategy was developed by our palliative care programs with input from the health care system leadership. RESULTS: In this publication, we share our multifaceted strategy to implement high-quality palliative care in the context of the COVID-19 pandemic that incorporates conventional, contingency, and crisis capacity and focuses on the areas of the hospital caring for the most patients: the emergency department, intensive care units, and acute care services. The strategy focuses on key content areas, including identifying and addressing goals of care, addressing moderate and severe symptoms, and supporting family members. CONCLUSION: Strategy planning for delivery of high-quality palliative care in the context of the COVID-19 pandemic represents an important area of need for our health care systems. We share our experiences of developing such a strategy to help other institutions conduct and adapt such strategies more quickly.

Soothing the heart with music: A feasibility study of a bedside music therapy intervention for critically ill patients in an urban hospital setting.

OBJECTIVES: Music therapy has been shown to be effective for reducing anxiety and pain in people with a serious illness. Few studies have investigated the feasibility of integrating music therapy into general inpatient care of the seriously ill, including the care of diverse, multiethnic patients. This leaves a deficit in knowledge for intervention planning. This study investigated the feasibility and effectiveness of introducing music therapy for patients on 4 inpatient units in a large urban medical center. Capacitated and incapacitated patients on palliative care, transplantation, medical intensive care, and general medicine units received a single bedside session led by a music therapist. METHODS: A mixed-methods, pre-post design was used to assess clinical indicators and the acceptability and feasibility of the intervention. Multiple regression modeling was used to evaluate the effect of music therapy on anxiety, pain, pulse, and respiratory rate. Process evaluation data and qualitative analysis of observational data recorded by the music therapists were used to assess the feasibility of providing music therapy on the units and patients' interest, receptivity, and satisfaction. RESULTS: Music therapy was delivered to 150 patients over a 6-month period. Controlling for gender, age, and session length, regression modeling showed that patients reported reduced anxiety post-session. Music therapy was found to be an accessible and adaptable intervention, with patients expressing high interest, receptivity, and satisfaction. SIGNIFICANCE OF RESULTS: This study found it feasible and effective to introduce bedside music therapy for seriously ill patients in a large urban medical center. Lessons learned and recommendations for future investigation are discussed.

The Influence of Multimorbidity on Health Care Utilization at the End of Life for Patients with Chronic Conditions.

Objective: To evaluate the association between the number of chronic conditions and hospital utilization at the end of life. Background: An understanding of the association of multimorbidity with health care utilization at the end of life may inform interventions to improve quality of care for these patients. Methods: A mortality follow-back analysis using Washington State death records and electronic health records. Subject included patients in the UW Medicine system who had at least one chronic condition and died between 2010 and 2015. Utilization was measured by inpatient admissions, emergency department use, and intensive care unit (ICU) admissions in the last 30 days of life. Results: For all utilization types, patients with three or more chronic conditions (n = 5124) had significantly higher utilization (p < 0.001) in the last 30 days of life than those with two (n = 5775) or one condition (n = 11,169). Comparing 3 versus 2 versus 1 conditions, the following percentages of patients had each type of utilization: inpatient admissions (37% vs. 28% vs. 19%), ED admissions (5% vs. 4% vs. 2%), and ICU care (28% vs. 20% vs. 12%). Discussion: Multimorbidity was associated with greater health care utilization at the end of life among patients representing a range of ages and covered by diverse insurers.

Hospital resource utilization and presence of advance directives at the end of life for adults with congenital heart disease.

OBJECTIVE: Overall health care resource utilization by adults with congenital heart disease has increased dramatically in the past two decades, yet little is known about utilization patterns at the end of life. The objective of this study is to better understand the patterns and influences on end-of-life care intensity for adults with congenital heart disease. METHODS: We identified a sample of adults with congenital heart disease (n = 65), cancer (n = 10 784), or heart failure (n = 3809) who died between January 2010 and December 2015, cared for in one multi-hospital health care system. We used multivariate analysis to evaluate markers of resource utilization, location of death, and documentation of advance care planning among patients with congenital heart disease versus those with cancer and those with heart failure. RESULTS: Approximately 40% of adults with congenital heart disease experienced inpatient and intensive care unit (ICU) hospitalizations in the last 30 days of life; 64% died in the hospital. Compared to patients with cancer, patients with adult congenital heart disease (ACHD) were more likely to have inpatient (adjusted risk ratio 1.57; 95% CI 1.12-2.18) and ICU admissions in the last 30 days of life (adjusted risk ratio 2.56; 95% CI 1.83-3.61), more likely to die in the hospital (adjusted risk ratio 1.75; 95% CI 1.43-2.13), and more likely to have documentation of advance care planning (adjusted risk ratio 1.46; 95% CI 1.09-1.96). Compared to patients with heart failure (HF), patients with ACHD were less likely to have an ICU admission in the last 30 days of life (adjusted risk ratio 0.73; 95% CI 0.54-0.99). CONCLUSIONS: Adults with congenital heart disease have significant hospital resource utilization near the end of life compared to patients with cancer, notable for more hospitalizations and a higher likelihood of death in the hospital. This population represents an important opportunity for the application of palliative and supportive care.

Race/Ethnicity, Socioeconomic Status, and Healthcare Intensity at the End of Life.

BACKGROUND: Although racial/ethnic minorities receive more intense, nonbeneficial healthcare at the end of life, the role of race/ethnicity independent of other social determinants of health is not well understood. OBJECTIVES: Examine the association between race/ethnicity, other key social determinants of health, and healthcare intensity in the last 30 days of life for those with chronic, life-limiting illness. SUBJECTS: We identified 22,068 decedents with chronic illness cared for at a single healthcare system in Washington State who died between 2010 and 2015 and linked electronic health records to death certificate data. DESIGN: Binomial regression models were used to test associations of healthcare intensity with race/ethnicity, insurance status, education, and median income by zip code. Path analyses tested direct and indirect effects of race/ethnicity with insurance, education, and median income by zip code used as mediators. MEASUREMENTS: We examined three measures of healthcare intensity: (1) intensive care unit admission, (2) use of mechanical ventilation, and (3) receipt of cardiopulmonary resuscitation. RESULTS: Minority race/ethnicity, lower income and educational attainment, and Medicaid and military insurance were associated with higher intensity care. Socioeconomic disadvantage accounted for some of the higher intensity in racial/ethnic minorities, but most of the effects were direct effects of race/ethnicity. CONCLUSIONS: The effects of minority race/ethnicity on healthcare intensity at the end of life are only partly mediated by other social determinants of health. Future interventions should address the factors driving both direct and indirect effects of race/ethnicity on healthcare intensity.

Predictors of Death in the Hospital for Patients with Chronic Serious Illness.

BACKGROUND: Most people prefer to die at home, yet most do not. Understanding factors associated with terminal hospitalization may inform interventions to improve care. OBJECTIVE: Among patients with chronic illness receiving care in a multihospital healthcare system, we identified the following: (1) predictors of death in any hospital; (2) predictors of death in a hospital outside the system; and (3) trends from 2010 to 2015. DESIGN: Retrospective cohort using death certificates and electronic health records. Settings/Subjects: Decedents with one of nine chronic illnesses. RESULTS: Among 20,486 decedents, those most likely to die in a hospital were younger (odds ratio [OR] 0.977, confidence interval [CI] 0.974-0.980), with more comorbidities (OR 1.188, CI 1.079-1.308), or more outpatient providers (OR 1.031, CI 1.015-1.047); those with cancer or dementia, or more outpatient visits were less likely to die in hospital. Among hospital deaths, patients more likely to die in an outside hospital had lower education (OR 0.952, CI 0.923-0.981), cancer (OR 1.388, CI 1.198-1.608), diabetes (OR 1.507, CI 1.262-1.799), fewer comorbidities (OR 0.745, CI 0.644-0.862), or fewer hospitalizations within the system during the prior year (OR 0.900, CI 0.864-0.938). Deaths in hospital did not change from 2010 to 2015, but the proportion of hospital deaths outside the system increased (p < 0.022). CONCLUSIONS: Patients dying in the hospital who are more likely to die in an outside hospital, and therefore at greater risk for inaccessibility of advance care planning, were more likely to be less well-educated and have cancer or diabetes, fewer comorbidities, and fewer hospitalizations. These findings may help target interventions to improve end-of-life care.

Temporal Trends Between 2010 and 2015 in Intensity of Care at End-of-Life for Patients With Chronic Illness: Influence of Age Under vs. Over 65 Years.

CONTEXT: Recent analyses of Medicare data show decreases over time in intensity of end-of-life care. Few studies exist regarding trends in intensity of end-of-life care for those under 65 years of age. OBJECTIVES: To examine recent temporal trends in place of death, and both hospital and intensive care unit (ICU) utilization, for age-stratified decedents with chronic, life-limiting diagnoses (<65 vs. ≥65 years) who received care in a large healthcare system. METHODS: Retrospective cohort using death certificates and electronic health records for 22,068 patients with chronic illnesses who died between 2010 and 2015. We examined utilization overall and stratified by age using multiple regression. RESULTS: The proportion of deaths at home did not change, but hospital admissions in the last 30 days of life decreased significantly from 2010 to 2015 (hospital b = -0.026; CI = -0.041, -0.012). ICU admissions in the last 30 days also declined over time for the full sample and for patients aged 65 years or older (overall b = -0.023; CI = -0.039, -0.007), but was not significant for younger decedents. Length of stay (LOS) did not decrease for those using the hospital or ICU. CONCLUSION: From 2010 to 2015, we observed a decrease in hospital admissions for all age groups and in ICU admissions for those over 65 years. As there were no changes in the proportion of patients with chronic illness who died at home nor in hospital or ICU LOS in the last 30 days, hospital and ICU admissions in the last 30 days may be a more responsive quality metric than site of death or LOS for palliative care interventions.

Providing Pediatric Palliative Care Education Using Problem-Based Learning.

BACKGROUND: The Institute of Medicine and the American Academy of Pediatrics has called for improvement in education and training of pediatricians in pediatric palliative care (PPC). Given the shortage of PPC physicians and the immediate need for PPC medical education, this study reports the outcomes of a problem-based learning (PBL) module facilitated by academic general and subspecialty pediatric faculty (non-PPC specialists) to third year medical students. Objectives/Setting: To test the effectiveness of a PPC-PBL module on third year medical students' and pediatric faculty's declarative knowledge, attitudes toward, perceived exposure, and self-assessed competency in PPC objectives. DESIGN: A PBL module was developed using three PPC learning objectives as a framework: define core concepts in palliative care; list the components of a total pain assessment; and describe key principles in establishing therapeutic relationships with patients. A PPC physician and nurse practitioner guided pediatric faculty on facilitating the PPC-PBL. In Part 1, students identified domains of palliative care for a child with refractory leukemia and self-assigned questions to research and present at the follow-up session. In Part 2, students were expected to develop a care plan demonstrating the three PPC objectives. MEASUREMENTS: Measures included a knowledge exam and a survey instrument to assess secondary outcomes. RESULTS: Students' declarative knowledge, perceived exposure, and self-assessed competency in all three PPC learning objectives improved significantly after the PPC-PBL, p = 0.002, p < 0.001, and p < 0.001, respectively. There were no significant differences in faculty knowledge test scores from baseline to follow-up, but scores were generally high (median >80%). Students and faculty rated palliative care education as "important or very important" at baseline and follow-up. CONCLUSIONS: This study suggests that key concepts in PPC can be taught to medical students utilizing a PBL format and pediatric faculty resulting in improved knowledge and self-assessed competency in PPC.

Using Electronic Health Records for Quality Measurement and Accountability in Care of the Seriously Ill: Opportunities and Challenges.

BACKGROUND: As our population ages and the burden of chronic illness rises, there is increasing need to implement quality metrics that measure and benchmark care of the seriously ill, including the delivery of both primary care and specialty palliative care. Such metrics can be used to drive quality improvement, value-based payment, and accountability for population-based outcomes. METHODS: In this article, we examine use of the electronic health record (EHR) as a tool to assess quality of serious illness care through narrative review and description of a palliative care quality metrics program in a large healthcare system. RESULTS: In the search for feasible, reliable, and valid palliative care quality metrics, the EHR is an attractive option for collecting quality data on large numbers of seriously ill patients. However, important challenges to using EHR data for quality improvement and accountability exist, including understanding the validity, reliability, and completeness of the data, as well as acknowledging the difference between care documented and care delivered. Challenges also include developing achievable metrics that are clearly linked to patient and family outcomes and addressing data interoperability across sites as well as EHR platforms and vendors. This article summarizes the strengths and weakness of the EHR as a data source for accountability of community- and population-based programs for serious illness, describes the implementation of EHR data in the palliative care quality metrics program at the University of Washington, and, based on that experience, discusses opportunities and challenges. Our palliative care metrics program was designed to serve as a resource for other healthcare systems. DISCUSSION: Although the EHR offers great promise for enhancing quality of care provided for the seriously ill, significant challenges remain to operationalizing this promise on a national scale and using EHR data for population-based quality and accountability.

30-Day Readmission Rates in Patients Admitted for Heart Failure Exacerbation with and without Palliative Care Consultation: A Retrospective Cohort Study.

BACKGROUND: Palliative care consultation improves quality of care through symptom management, communication, care coordination, and earlier hospice referral, and it may decrease burdensome hospital readmissions at the end of life. OBJECTIVES: To compare 30-day readmission rates for patients admitted with exacerbation of congestive heart failure (CHF) receiving palliative care consultation services compared with controls. DESIGN: Retrospective cohort study using propensity score matching. A secondary, subgroup analysis compared patients with palliative care consults and patients with an incomplete consult order. Settings/Subjects: Single-center study in an academic acute inpatient setting. Of a pool of 8215 admissions from January 1, 2011 to April 6, 2014, 356 included a palliative care consultation, and 356 matched controls were found. RESULTS: The 30-day readmission rate was 50.8% for admissions including a palliative care consult and 36.0% for controls (OR 1.8, 95% CI 1.4-2.5). Those with a completed consult had fewer readmissions compared with those with an incomplete order, but this difference was not statistically significant (43% vs. 53%, χ2 = 1.9, p = 0.171). CONCLUSION: No reduction in the risk of 30-day readmission was observed in the palliative care group, suggesting that palliative care services may not have the same effect on readmission rates in CHF patients compared with others. The subgroup analysis suggests that the difference between palliative care and control groups may reflect residual confounding, possibly due to critical social variables that are not captured in the electronic medical record, highlighting the difficulty in studying this population.

Let's Talk Critical. Development and Evaluation of a Communication Skills Training Program for Critical Care Fellows.

RATIONALE: Although expert communication between intensive care unit clinicians with patients or surrogates improves patient- and family-centered outcomes, fellows in critical care medicine do not feel adequately trained to conduct family meetings. OBJECTIVES: We aimed to develop, implement, and evaluate a communication skills program that could be easily integrated into a U.S. critical care fellowship. METHODS: We developed four simulation cases that provided communication challenges that critical care fellows commonly face. For each case, we developed a list of directly observable tasks that could be used by faculty to evaluate fellows during each simulation. We developed a didactic curriculum of lectures/case discussions on topics related to palliative care, end-of-life care, communication skills, and bioethics; this month-long curriculum began and ended with the fellows leading family meetings in up to two simulated cases with direct observation by faculty who were not blinded to the timing of the simulation. Our primary measures of effectiveness were the fellows' self-reported change in comfort with leading family meetings after the program was completed and the quality of the communication as measured by the faculty evaluators during the family meeting simulations at the end of the month. MEASUREMENTS AND MAIN RESULTS: Over 3 years, 31 critical care fellows participated in the program, 28 of whom participated in 101 family meeting simulations with direct feedback by faculty facilitators. Our trainees showed high rates of information disclosure during the simulated family meetings. During the simulations done at the end of the month compared with those done at the beginning, our fellows showed significantly improved rates in: (1) verbalizing an agenda for the meeting (64 vs. 41%; Chi-square, 5.27; P = 0.02), (2) summarizing what will be done for the patient (64 vs. 39%; Chi-square, 6.21; P = 0.01), and (3) providing a follow-up plan (60 vs. 37%; Chi-square, 5.2; P = 0.02). More than 95% of our participants (n = 27) reported feeling "slightly" or "much" more comfortable with discussing foregoing life-sustaining treatment and leading family discussions after the month-long curriculum. CONCLUSIONS: A communication skills program can be feasibly integrated into a critical care training program and is associated with improvements in fellows' skills and comfort with leading family meetings.

Palliative care in the management of advanced HIV/AIDS.

The basic elements of palliative care can be translated into practice for patients with HIV/AIDS. More than half of clinical events and deaths occurring among patients on highly active antiretroviral therapy are classified as non-AIDS illnesses. Thus, end-of-life care for patients with late-stage AIDS needs to include any palliative measures that are used for patients without AIDS. This article reviews the epidemiology of HIV/AIDS, prognostic indicators, opportunistic infections, specific AIDS-defining and non-AIDS-defining malignancies, substance abuse/liver disease, and highly active antiretroviral therapy and comfort measures for late-stage AIDS patients.