1
|
Piscitello GM, Rogal S, Schell J, Schenker Y, Arnold RM. Equity in Using Artificial Intelligence Mortality Predictions to Target Goals of Care Documentation. J Gen Intern Med 2024:10.1007/s11606-024-08849-w. [PMID: 38858343 DOI: 10.1007/s11606-024-08849-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Accepted: 05/31/2024] [Indexed: 06/12/2024]
Abstract
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.
Collapse
Affiliation(s)
- Gina M Piscitello
- Division of General Internal Medicine, Section of Palliative Care and Medical Ethics, University of Pittsburgh, Pittsburgh, PA, USA.
- Palliative Research Center, University of Pittsburgh, Pittsburgh, PA, USA.
| | - Shari Rogal
- Departments of Medicine and Surgery, University of Pittsburgh, Pittsburgh, PA, USA
- Center for Health Equity Research and Promotion, VA Pittsburgh Healthcare Center, Pittsburgh, PA, USA
| | - Jane Schell
- Division of General Internal Medicine, Section of Palliative Care and Medical Ethics, University of Pittsburgh, Pittsburgh, PA, USA
- Palliative Research Center, University of Pittsburgh, Pittsburgh, PA, USA
| | - Yael Schenker
- Division of General Internal Medicine, Section of Palliative Care and Medical Ethics, University of Pittsburgh, Pittsburgh, PA, USA
- Palliative Research Center, University of Pittsburgh, Pittsburgh, PA, USA
| | - Robert M Arnold
- Department of Geriatrics and Palliative Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| |
Collapse
|
2
|
Kim KM, Muench U, Maki JE, Yefimova M, Oh A, Jopling JK, Rinaldo F, Shah NR, Giannitrapani KF, Williams MY, Lorenz KA. 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. HEALTH AFFAIRS SCHOLAR 2023; 1:qxad026. [PMID: 38756238 PMCID: PMC10986263 DOI: 10.1093/haschl/qxad026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/23/2023] [Revised: 06/21/2023] [Accepted: 07/11/2023] [Indexed: 05/18/2024]
Abstract
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.
Collapse
Affiliation(s)
- Kyung Mi Kim
- Office of Research Patient Care Services, Stanford Health Care,Menlo Park, CA 94025, United States
- Clinical Excellence Research Center, School of Medicine, Stanford University,Palo Alto, CA 94304, United States
- Department of Social and Behavioral Sciences, School of Nursing, University of California, San Francisco, San Francisco, CA 94143, United States
| | - Ulrike Muench
- Department of Social and Behavioral Sciences, School of Nursing, University of California, San Francisco, San Francisco, CA 94143, United States
- Philip R. Lee Institute for Health Policy Studies, School of Medicine, University of California, San Francisco, San Francisco, CA 94143, United States
| | - John E Maki
- Saint Francis Memorial Hospital, San Francisco, CA 94109, United States
| | - Maria Yefimova
- Center for Nursing Excellence and Innovation, UCSF Health,San Francisco, CA 94143, United States
- Department of Physiological Nursing, School of Nursing, University of California, San Francisco, San Francisco, CA 94143, United States
| | - Anna Oh
- Office of Research Patient Care Services, Stanford Health Care,Menlo Park, CA 94025, United States
| | - Jeffrey K Jopling
- Clinical Excellence Research Center, School of Medicine, Stanford University,Palo Alto, CA 94304, United States
- Department of Surgery, School of Medicine, Johns Hopkins University, Baltimore, MD 21287, United States
| | - Francesca Rinaldo
- Clinical Excellence Research Center, School of Medicine, Stanford University,Palo Alto, CA 94304, United States
| | - Nirav R Shah
- Clinical Excellence Research Center, School of Medicine, Stanford University,Palo Alto, CA 94304, United States
| | - Karleen Frances Giannitrapani
- Center for Innovation to Implementation (Ci2i), Veterans Affairs Palo Alto Health Care System, US Department of Veterans Affairs,Palo Alto, CA 94304, United States
- Quality Improvement Resource Center for Palliative Care, Stanford University,Stanford, CA 94305, United States
- Primary Care and Population Health, School of Medicine, Stanford University,Stanford, CA 94305, United States
| | - Michelle Y Williams
- Office of Research Patient Care Services, Stanford Health Care,Menlo Park, CA 94025, United States
- Primary Care and Population Health, School of Medicine, Stanford University,Stanford, CA 94305, United States
| | - Karl A Lorenz
- Center for Innovation to Implementation (Ci2i), Veterans Affairs Palo Alto Health Care System, US Department of Veterans Affairs,Palo Alto, CA 94304, United States
- Quality Improvement Resource Center for Palliative Care, Stanford University,Stanford, CA 94305, United States
- Primary Care and Population Health, School of Medicine, Stanford University,Stanford, CA 94305, United States
| |
Collapse
|
3
|
Koffman J, Bajwah S, Davies JM, Hussain JA. Researching minoritised communities in palliative care: An agenda for change. Palliat Med 2022; 37:530-542. [PMID: 36271636 DOI: 10.1177/02692163221132091] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
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.
Collapse
Affiliation(s)
- Jonathan Koffman
- University of Hull, Hull York Medical School, Wolfson Palliative Care Research Centre, Hull, UK
| | - Sabrina Bajwah
- King's College London, Cicely Saunders Institute, London, UK
| | - Joanna M Davies
- King's College London, Cicely Saunders Institute, London, UK
| | - Jamilla Akhter Hussain
- Bradford Institute for Health Research, Bradford Teaching Hospital NHS Foundation Trust, Bradford, UK
| |
Collapse
|