Equity in Using Artificial Intelligence Mortality Predictions to Target Goals of Care Documentation.

BACKGROUND: Artificial intelligence (AI) algorithms are increasingly used to target patients with elevated mortality risk scores for goals-of-care (GOC) conversations. OBJECTIVE: To evaluate the association between the presence or absence of AI-generated mortality risk scores with GOC documentation. DESIGN: Retrospective cross-sectional study at one large academic medical center between July 2021 and December 2022. PARTICIPANTS: Hospitalized adult patients with AI-defined Serious Illness Risk Indicator (SIRI) scores indicating > 30% 90-day mortality risk (defined as "elevated" SIRI) or no SIRI scores due to insufficient data. INTERVENTION: A targeted intervention to increase GOC documentation for patients with AI-generated scores predicting elevated risk of mortality. MAIN MEASURES: Odds ratios comparing GOC documentation for patients with elevated or no SIRI scores with similar severity of illness using propensity score matching and risk-adjusted mixed-effects logistic regression. KEY RESULTS: Among 13,710 patients with elevated (n = 3643, 27%) or no (n = 10,067, 73%) SIRI scores, the median age was 64 years (SD 18). Twenty-five percent were non-White, 18% had Medicaid, 43% were admitted to an intensive care unit, and 11% died during admission. Patients lacking SIRI scores were more likely to be younger (median 60 vs. 72 years, p < 0.0001), be non-White (29% vs. 13%, p < 0.0001), and have Medicaid (22% vs. 9%, p < 0.0001). Patients with elevated versus no SIRI scores were more likely to have GOC documentation in the unmatched (aOR 2.5, p < 0.0001) and propensity-matched cohorts (aOR 2.1, p < 0.0001). CONCLUSIONS: Using AI predictions of mortality to target GOC documentation may create differences in documentation prevalence between patients with and without AI mortality prediction scores with similar severity of illness. These finding suggest using AI to target GOC documentation may have the unintended consequence of disadvantaging severely ill patients lacking AI-generated scores from receiving targeted GOC documentation, including patients who are more likely to be non-White and have Medicaid insurance.

Advanced Care Planning in Chronic Kidney Disease: Qualitative Impact of the MY WAY Intervention.

CONTEXT: Despite recommendations for shared decision-making and advanced care planning (ACP) for people with chronic kidney disease (CKD), such conversations are infrequent. The MY WAY educational and patient coaching intervention aimed to promote high-quality ACP. OBJECTIVES: This qualitative substudy sought to gain participant feedback on the MY WAY ACP coaching intervention, and how it impacted their wishes, perceptions of kidney care, and factors that helped them reflect on ACP. METHODS: We conducted semi-structured interviews with participants from the intervention arm of the MY WAY study about their prior experience with ACPs in the context of CKD, impressions of the MY WAY intervention, and outcomes of the MY WAY intervention. We conducted a qualitative thematic analysis of transcribed interviews. RESULTS: Among 15 intervention participants, the following major themes emerged: 1) Patients with CKD approach ACP with varied experiences; 2) Patients felt the MY WAY coaching intervention supported ACP by reinforcing values; and 3) Patients found the coaching intervention focused on end of life, but not necessarily on decision making regarding CKD. CONCLUSION: Participants perceived the coaching intervention to have high utility in facilitating ACP, but had a limited impact on CKD-specific decision-making. These findings suggest that the coach plays a crucial role in comfort with ACP conversations and that ACP readiness and engagement may not correlate with treatment preferences or understanding of CKD treatment decisions.

Artificial intelligence for better goals of care documentation.

OBJECTIVES: Lower rates of goals of care (GOC) conversations have been observed in non-white hospitalised patients, which may contribute to racial disparities in end-of-life care. We aimed to assess how a targeted initiative to increase GOC documentation rates is associated with GOC documentation by race. METHODS: We retrospectively assessed GOC documentation during a targeted GOC initiative for adult patients with an artificial intelligence predicted elevated risk of mortality. Patients were admitted to an urban academic medical centre in Pittsburgh, Pennsylvania between July 2021 and 31 December 2022. RESULTS: The 3643 studied patients had a median age of 72 (SD 13.0) and were predominantly white (87%) with 42% admitted to an intensive care unit and 15% dying during admission. GOC documentation was completed for 28% (n=1019/3643). By race, GOC was documented for 30% black (n=105/351), 28% white (n=883/3161) and 24% other (n=31/131) patients (p=0.3933). There was no statistical difference in the rate of documented GOC among races over time (p=0.5142). CONCLUSIONS: A targeted initiative to increase documented GOC conversations for hospitalised patients with an elevated risk of mortality is associated with similar documentation rates across racial groups. Further research is needed to assess whether this initiative may promote racial equity in GOC documentation in other settings.

Shared Decision-Making and Patient Communication in Nephrology Practice.

Shared decision-making (SDM) is the standard of care for patient or surrogates and their clinicians to arrive at a medical decision. Evidence suggests that SDM increases patients' understanding of their illness and satisfaction with their decision-making process. Dialysis patients often report the perception that they were passive participants in the decision to start dialysis, suggesting further opportunities for enhancing the application of SDM in decision-making with patients with kidney disease. The hallmark feature of SDM is sensitive, culturally- and equity-informed communication and effective partnership between patient or surrogate and clinician. In the process, the patient's personal expertise in the realm of their values and priorities is elicited, and the clinician's medical expertise is shared. The integration of this shared expertise then leads to an informed treatment decision. Frameworks such as the Serious Illness Conversation Guide and REMAP are guides for the SDM process, and communication tools and mnemonics can help facilitate SDM conversations. This paper will address SDM in nephrology practice, reviewing underlying supportive evidence, context, and timing for employing SDM in the trajectory of chronic kidney disease and acute kidney injury, special considerations in vulnerable populations to promote health equity, and communication tools and frameworks to facilitate the SDM process. By learning and applying these frameworks and tools, nephrology providers will be able to employ SDM in the management of kidney disease.

Conservative kidney management and kidney supportive care: core components of integrated care for people with kidney failure.

Integrated kidney care requires synergistic linkage between preventative care for people at risk for chronic kidney disease and health services providing care for people with kidney disease, ensuring holistic and coordinated care as people transition between acute and chronic kidney disease and the 3 modalities of kidney failure management: conservative kidney management, transplantation, and dialysis. People with kidney failure have many supportive care needs throughout their illness, regardless of treatment modality. Kidney supportive care is therefore a vital part of this integrated framework, but is nonexistent, poorly developed, and/or poorly integrated with kidney care in many settings, especially in low- and middle-income countries. To address this, the International Society of Nephrology has (i) coordinated the development of consensus definitions of conservative kidney management and kidney supportive care to promote international understanding and awareness of these active treatments; and (ii) identified key considerations for the development and expansion of conservative kidney management and kidney supportive care programs, especially in low resource settings, where access to kidney replacement therapy is restricted or not available. This article presents the definitions for conservative kidney management and kidney supportive care; describes their core components with some illustrative examples to highlight key points; and describes some of the additional considerations for delivering conservative kidney management and kidney supportive care in low resource settings.

Concurrent Hospice and Dialysis Care: Considerations for Implementation.

IMPORTANCE: Hospice positively impacts care at the end of life for patients and their families. However, compared to the general Medicare population, patients on dialysis are half as likely to receive hospice. Concurrent hospice and dialysis care offers an opportunity to improve care for people living with end-stage kidney disease (ESKD). OBJECTIVE: We sought to (1) develop a conceptual model of the Program and (2) identify key components, resources, and considerations for further implementation. DESIGN: We conducted a template analysis of qualitative interviews and convened a community advisory panel (CAP) to get feedback on current concurrent care design and considerations for dissemination and implementation. PARTICIPANTS: Thirty-nine patients with late-stage chronic kidney disease (CKD), family caregivers, bereaved family caregivers, hospice clinicians, nephrology clinicians, administrators, and policy experts participated in interviews. A purposive subset of 19 interviewees composed the CAP. MAIN MEASURES: Qualitative feedback on concurrent care design refinements, implementation, and resources. KEY RESULTS: Participants identified four themes that define an effective model of concurrent hospice and dialysis: it requires (1) timely goals-of-care conversations and (2) an interdisciplinary approach; (3) clear guidelines ensure smooth transitions for patients and families; and (4) hospice payment policy must support concurrent care. CAP participants provided feedback on the phases of an effective model of concurrent hospice and dialysis, and resources, including written and interactive educational materials, communication tools, workflow processes, and order sets. CONCLUSIONS: We developed a conceptual model for concurrent hospice and dialysis care and a corresponding resource list. In addition to policy changes, clinical implementation and educational resources can facilitate scalable and equitable dissemination of concurrent care. Concurrent hospice and dialysis care must be systematically evaluated via a hybrid implementation-effectiveness trial that includes the resources outlined herein, based on our conceptual model of concurrent care delivery.

Implementing a Serious Illness Risk Prediction Model: Impact on Goals of Care Documentation.

CONTEXT: Goals of care conversations can promote high value care for patients with serious illness, yet documented discussions infrequently occur in hospital settings. OBJECTIVES: We sought to develop a quality improvement initiative to improve goals of care documentation for hospitalized patients. METHODS: Implementation occurred at an academic medical center in Pittsburgh, Pennsylvania. Intervention included integration of a 90-day mortality prediction model grouping patients into low, intermediate, and high risk; a centralized goals of care note; and automated notifications and targeted palliative consults. We compared documented goals of care discussions by risk score before and after implementation. RESULTS: Of the 12,571 patients hospitalized preimplementation and 10,761 postimplementation, 1% were designated high risk and 11% intermediate risk of mortality. Postimplementation, goals of care documentation increased for high (17.6%-70.8%, P< 0.0001) and intermediate risk patients (9.6%-28.0%, P < 0.0001). For intermediate risk patients, the percentage of goals of care documentation performed by palliative medicine specialists increased from pre- to postimplementation (52.3%-71.2%, P = 0.0002). For high-risk patients, the percentage of goals of care documentation completed by the primary service increased from pre-to postimplementation (36.8%-47.1%, P = 0.5898, with documentation performed by palliative medicine specialists slightly decreasing from pre- to postimplementation (63.2%-52.9%, P = 0.5898). CONCLUSIONS: Implementation of a goals of care initiative using a mortality prediction model significantly increased goals of care documentation especially among high-risk patients. Further study to assess strategies to increase goals of care documentation for intermediate risk patients is needed especially by nonspecialty palliative care.

Hospice Care in Conservative Kidney Management.

Hospice care offers multidisciplinary expertise to optimize symptom management and quality of life for patients with limited life expectancy and help ensure that patients receive care that reflects their personal goals and values. Many patients receiving conservative kidney management (CKM) and their loved ones can benefit from the additional support that hospice provides, particularly as symptom burdens and functional status worsen over the last few months of life. We provide an overview of hospice services and how they may benefit patients receiving CKM, describe the evolution of optimal CKM strategies and collaboration between nephrology and hospice clinicians over the course of disease progression, and explore challenges to effective hospice care delivery for patients with chronic kidney disease and how to address them.

Delivery of Active Medical Management without Dialysis through an Embedded Kidney Palliative Care Model.

Background: Patients with CKD have high symptom burden, low rates of advance care planning (ACP), and frequently receive care that is not goal concordant. Improved integration of palliative care into nephrology and access to active medical management without dialysis (AMMWD) have the potential to improve outcomes through better symptom management and enhanced shared decision making. Methods: We describe the development of a kidney palliative care (KPC) clinic and how palliative care practices are integrated within an academic nephrology clinic. We performed a retrospective electronic health record (EHR) review for patients seen in this clinic between January 2015 and February 2019 to describe key clinical activities and delivery of AMMWD. Results: A total of 165 patients were seen in the KPC clinic (139 with CKD and 26 who were already receiving dialysis). Fatigue, mobility issues, and pain were the three most prevalent symptoms (85%, 66%, 58%, respectively). Ninety-one percent of patients had a surrogate decision maker documented in the EHR; 87% of patients had a goals-of-care conversation documented in the EHR. Of the 139 patients with CKD, 67 (48%) chose AMMWD as their disease progressed. Sixty-eight percent (41 of 60) of patients who died during the study were referred to hospice. Conclusions: Our findings suggest that the integration of palliative care into nephrology can assist in identification of symptoms, lead to high rates of ACP, and provide a mechanism for patients to choose and receive AMMWD. The percentage of patients choosing AMMWD in our study suggests that increased shared decision making may lower rates of dialysis initiation in the United States. Additional prospective research and registries for assessing the effects of AMMWD have the potential to improve care for people living with CKD.

Description and Outcomes of an Innovative Concurrent Hospice-Dialysis Program.

BACKGROUND: Compared with the general Medicare population, patients with ESKD have worse quality metrics for end-of-life care, including a higher percentage experiencing hospitalizations and in-hospital deaths and a lower percentage referred to hospice. We developed a Concurrent Hospice and Dialysis Program in which patients may receive palliative dialysis alongside hospice services. The Program aims to improve access to quality end-of-life care and, ultimately, improve the experiences of patients, caregivers, and clinicians. OBJECTIVES: We sought to describe (1) the Program and (2) enrollment and utilization characteristics of Program participants. METHODS: We conducted a quantitative description of demographics, patient characteristics, and utilization of Program enrollees. RESULTS: Of 43 total enrollees, 44% received at least one dialysis treatment, whereas 56% received no dialysis. The median (range) hospice length of stay was 9 (1-76) days for all participants and 13 (4-76) days for those who received at least one dialysis treatment. The average number of dialysis treatments was 3.5 (range 1-9) for hemodialysis and 19.2 (range 3-65) for peritoneal dialysis. Sixty-five percent of enrollees died at home, 23% in inpatient hospice, and 12% in a nursing facility; no patients died in the hospital. CONCLUSIONS: Our 3-year experience with the Program demonstrated that enrollees had a longer median hospice stay than the previously reported 5-day median for patients with ESKD. Most patients received no further dialysis treatments despite the option to continue dialysis. Our experience provides evidence to support future work testing the effectiveness of such clinical programs to improve patient and utilization outcomes.

Serious Illness Communication Skills Training during a Global Pandemic.

Background: Communication skills is a core competency for critical care fellowship training. The coronavirus disease (COVID-19) pandemic has made it increasingly difficult to teach these skills in graduate medical education. We developed and implemented a novel, hybrid version of the Critical Care Communication (C3) skills with virtual and in-person components for pulmonary and critical care fellows. Objective: To develop and implement a new hybrid virtual/in-person version of the traditional C3 serious illness communication skills course and to compare learner outcomes to prior courses. Methods: We modified the C3 course in 2020 in response to the COVID-19 pandemic by adapting large-group didactic content to an online format that included both virtual asynchronous and virtual live content. Small-group skills training remained in person with trained actors and facilitators. We administered self-assessments to the participants and compared with historical data from the traditional in-person courses beginning in 2012. After the 2020 course, we collected informal feedback from a portion of the learners. Results: Like the traditional in-person version, participants rated the hybrid version highly. Learners reported feeling well prepared or very well prepared over 90% of the time in most communication skills after both versions of the course. Over 90% of participants in both versions of the course rated the specific course components as effective or very effective. Feedback from the learners indicates that they prefer the virtual didactics over traditional in-person didactics. Conclusions: Pulmonary and critical care fellows rated a hybrid version of a communication skills training similarly to the traditional in-person version of the course. We have provided a scaffolding on how to implement such a course. We anticipate some of the virtual components of this training will outlive the current pandemic based on learner feedback.

Video Images about Decisions for Ethical Outcomes in Kidney Disease (VIDEO-KD): the study protocol for a multi-centre randomised controlled trial.

INTRODUCTION: Older patients with advanced chronic kidney disease (CKD) often are inadequately prepared to make informed decisions about treatments including dialysis and cardiopulmonary resuscitation. Further, evidence shows that patients with advanced CKD do not commonly engage in advance care planning (ACP), may suffer from poor quality of life, and may be exposed to end-of-life care that is not concordant with their goals. We aim to study the effectiveness of a video intervention on ACP, treatment preferences and other patient-reported outcomes. METHODS AND ANALYSIS: The Video Images about Decisions for Ethical Outcomes in Kidney Disease trial is a multi-centre randomised controlled trial that will test the effectiveness of an intervention that includes a CKD-related video decision aid followed by recording personal video declarations about goals of care and treatment preferences in older adults with advancing CKD. We aim to enrol 600 patients over 5 years at 10 sites. ETHICS AND DISSEMINATION: Regulatory and ethical aspects of this trial include a single Institutional Review Board mechanism for approval, data use agreements among sites, and a Data Safety and Monitoring Board. We intend to disseminate findings at national meetings and publish our results. TRIAL REGISTRATION NUMBER: NCT04347629.

Clinicians' Perceptions of Collaborative Palliative Care Delivery in Chronic Kidney Disease.

CONTEXT: Guidelines recommend palliative care for patients with chronic kidney disease (CKD), who experience a high pain and symptom burden, and receive intensive treatments that often do not align with their values. A lack of scalable specialty palliative care services has prompted calls for attention to primary palliative care, delivered in primary care and nephrology settings. OBJECTIVES: The objectives of this study were to 1) describe expectations for care to meet the palliative care needs of people living with CKD, and limitations to meeting those expectations in the current model, and 2) identify potential interventions to meet patients' palliative care needs. METHODS: We conducted semi-structured interviews with clinicians from primary care, nephrology, and palliative care to assess 1) reasonable expectations for meeting palliative needs, 2) barriers to integrating primary palliative care, and 3) potential intervention points. RESULTS: Clinicians discussed their expectations for high-quality communication (e.g., discussing disease understanding, assessing goals of care) and better integration of palliative care services. Clinicians expressed barriers to delivering that care, including poor inter-clinician communication. To address barriers, clinicians outlined potential intervention points, such as building collaborative models of care, and structural triggers to identify patients who may be appropriate for palliative care. CONCLUSION: Interventions to address gaps in palliative care delivery for people living with CKD should incorporate systematic identification of patients with palliative care needs and structural mechanisms to meeting those needs via specialty and primary palliative care.

Advance Care Planning Coaching in CKD Clinics: A Pragmatic Randomized Clinical Trial.

RATIONALE & OBJECTIVE: Although guidelines recommend more and earlier advance care planning (ACP) for patients with chronic kidney disease (CKD), scant evidence exists to guide incorporation of ACP into clinical practice for patients with stages of CKD prior to kidney failure. Involving nephrology team members in addition to primary care providers in this important patient-centered process may increase its accessibility. Our study examined the effect of coaching implemented in CKD clinics on patient engagement with ACP. STUDY DESIGN: Multicenter, pragmatic randomized controlled trial. SETTING & PARTICIPANTS: Three CKD clinics in different states participated: 273 patients consented to participate, 254 were included in analysis. Eligible patients were 55 years or older, had stage 3-5 CKD, and were English speaking. INTERVENTION: Nurses or social workers with experience in nephrology or palliative care delivered individualized in-person ACP sessions. The enhanced control group was given Make Your Wishes About You (MY WAY) education materials and was verbally encouraged to bring their completed advance directives to the clinic. OUTCOME: Primary outcome measures were scores on a 45-point ACP engagement scale at 14 weeks and a documented advance directive or portable medical order at 16 weeks after enrollment. RESULTS: Among 254 participants analyzed, 46.5% were 65-74 years of age, and 54% had CKD stage 3. The coached patients scored 1.9 points higher at 14 weeks on the ACP engagement scale (ß = 1.87 [95% CI, 0.13-3.64]) adjusted for baseline score and site. Overall, 32.8% of intervention patients (41 of 125) had an advance directive compared with 17.8% (23 of 129) of patients in the control group. In a site-adjusted multivariable model, coached patients were 79% more likely to have a documented advance directive or portable medical order (adjusted risk ratio, 1.79 [95% CI, 1.18-2.72]), with the impact principally evident at only 1 study site. LIMITATIONS: Small number of study sites and possible unrepresentativeness of the broader CKD population by study participants. CONCLUSIONS: Individualized coaching may be effective in enhancing ACP, but its impact may be influenced by the health care environment where it is delivered. FUNDING: The Patrick and Catherine Weldon Donaghue Medical Research Foundation, via the Greater Value Portfolio. TRIAL REGISTRATION: Registered at ClinicalTrials.gov with study number NCT03506087.

Communication Skills Training for Nurses and Social Workers: An Initiative to Promote Interdisciplinary Advance Care Planning and Palliative Care in Patients on Dialysis.

Palliative care initiatives are needed in nephrology, yet implementation is lacking. We created a 6-hour workshop to teach the skills of active listening, responding to emotion, and exploring goals and values to nurses and social workers working in dialysis units. The workshop consisted of interactive didactics and structured role play with trained simulated patients. We assessed preparedness using a Likert scale and utilized paired t tests to measure the impact using a self-assessment survey following the training. Ten nurses and two social workers from six dialysis units completed the training. Mean scores improved in all domains: demonstrating empathic behaviors, responding to emotion and end-of-life concerns, eliciting family's concerns at end-of-life and patient's goals, and discussing spiritual concerns. Further testing in larger samples may help to confirm these results.

Top Ten Tips Palliative Care Clinicians Should Know About Prognostication in Critical Illness and Heart, Kidney, and Liver Diseases.

Specialty palliative care (PC) clinicians are frequently asked to discuss prognosis with patients and their families. When conveying information about prognosis, PC clinicians need also to discuss the likelihood of prolonged hospitalization, cognitive and functional disabilities, and death. As PC moves further and further upstream, it is crucial that PC providers have a broad understanding of curative and palliative treatments for serious diseases and can collaborate in prognostication with specialists. In this article, we present 10 tips for PC clinicians to consider when caring and discussing prognosis for the seriously ill patients along with their caregivers and care teams. This is the second in a three-part series around prognostication in adult and pediatric PC.

Patient experiences of sleep in dialysis: systematic review of qualitative studies.

RATIONALE AND OBJECTIVE: Sleep problems affect more than half of patients receiving dialysis and are associated with increased risk of mortality, cardiovascular events, depression and impaired functioning and quality of life. Symptoms such as fatigue and exhaustion may be attributed to sleep problems or sleep disorders, as well as the burden of kidney disease and treatment. This study aims to describe the patient perspectives on the reasons, impact and management of sleep problems in dialysis. STUDY DESIGN: Systematic review and thematic synthesis of qualitative studies that report patient experience and perspectives on sleep in dialysis. SETTING AND POPULATION: Patients receiving dialysis. SEARCH STRATEGY AND SOURCES: MEDLINE, Embase, PsycINFO, CINAHL, reference lists and PhD dissertations were searched from inception to August 2019. DATA EXTRACTION: All text from the results/conclusion of the primary studies. ANALYTICAL APPROACH: Thematic synthesis. RESULTS: We included 48 studies involving 1156 participants from 16 countries. We identified six themes: dominating demands of treatment (with subthemes of: demanding and relentless schedule, regret for wasted time); scheduling and control (managing sleep routines, napping and nocturnal sleep disruption, meditative aids); disruptions due to dialysis (unsettled sleep, hypervigilance and worry); symptoms depriving sleep (difficulty falling asleep, constant waking); overwhelmed and without choice (futility of sleep, uncontrollable exhaustion, restlessness is irrepressible); and as a coping mechanism (avoiding anxiety, alleviating symptoms, combating boredom). LIMITATIONS: Most studies were conducted in high-income, English-speaking countries. CONCLUSION: The treatment and symptom burden of dialysis disrupts and deprives patients of sleep, which leads to overwhelming and uncontrollable exhaustion. Better management of symptoms and effective strategies to manage sleep routines may improve sleep quality for better overall health in patients receiving dialysis.