Characterizing uncertainty in goals-of-care discussions among black and white patients: a qualitative study

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.

Racial disparities in inpatient palliative care consultation among frail older patients undergoing high-risk elective surgical procedures in the United States: a cross-sectional study of the national inpatient sample

Surgical interventions are common among seriously ill older patients, with nearly one-third of older Americans facing surgery in their last year of life. Despite the potential benefits of palliative care among older surgical patients undergoing high-risk surgical procedures, palliative care in this population is underutilized and little is known about potential disparities by race/ethnicity and how frailty my affect such disparities. The aim of this study was to examine disparities in palliative care consultations by race/ethnicity and assess whether patients' frailty moderated this association. Drawing on a retrospective cross-sectional study of inpatient surgical episodes using the National Inpatient Sample of the Healthcare Cost and Utilization Project from 2005 to 2019, we found that frail Black patients received palliative care consultations least often, with the largest between-group adjusted difference represented by Black-Asian/Pacific Islander frail patients of 1.6 percentage points, controlling for sociodemographic, comorbidities, hospital characteristics, procedure type, and year. No racial/ethnic difference in the receipt of palliative care consultations was observed among nonfrail patients. These findings suggest that, in order to improve racial/ethnic disparities in frail older patients undergoing high-risk surgical procedures, palliative care consultations should be included as the standard of care in clinical care guidelines.

Researching minoritised communities in palliative care: An agenda for change

BACKGROUND

Palliative care access, experiences and outcomes of care disadvantage those from ethnically diverse, Indigenous, First nation and First people communities. Research into this field of inquiry raises unique theoretical, methodological, and moral issues. Without the critical reflection of methods of study and reporting of findings, researchers may inadvertently compromise their contribution to reducing injustices and perpetuating racism.

AIM

To examine key evidence of the place of minoritised communities in palliative care research to devise recommendations that improve the precision and rigour of research and reporting of findings.

METHODS

Narrative review of articles identified from PubMed, CINAHL and Google Scholar for 10 years augmented with supplementary searches.

RESULTS

We identified and appraised 109 relevant articles. Four main themes were identified (i) Lack of precision when working with a difference; (ii) 'black box epidemiology' and its presence in palliative care research; (iii) the inclusion of minoritised communities in palliative care research; and (iv) the potential to cause harm. All stymie opportunities to 'level up' health experiences and outcomes across the palliative care spectrum.

CONCLUSIONS

Based on the findings of this review palliative care research must reflect on and justify the classification of minoritised communities, explore and understand intersectionality, optimise data quality, decolonise research teams and methods, and focus on reducing inequities to level up end-of-life care experiences and outcomes. Palliative care research must be forthright in explicitly indentifying instances of structural and systemic racism in palliative care research and engaging in non-judgemental debate on changes required.