Advanced Care Planning for Hospitalized Patients Following Clinician Notification of Patient Mortality by a Machine Learning Algorithm

"Postponing it Any Later Would not be so Great": A Cognitive Interview Study of How Physicians Decide to Initiate Goals of Care Discussions in the Hospital

BACKGROUND

There are missed opportunities to discuss goals and preferences for care with seriously ill patients in the acute care setting. It is unknown which factors most influence clinician decision-making about communication at the point of care.

OBJECTIVE

This study utilized a cognitive-interviewing technique to better understand what leads clinicians to decide to have a goals of care (GOC) discussion in the acute care setting.

METHODS

A convenience sample of 15 oncologists, intensivists and hospitalists were recruited from a single academic medical center in a large urban area. Participants completed a cognitive interview describing their thought process when deciding whether to engage in GOC discussions in clinical vignettes.

RESULTS

6 interconnected factors emerged as important in determining how likely the physician was to consider engaging in GOC at that time; (1) the participants' mental model of GOC, (2) timing of GOC related to stability, acuity and reversibility of the patient's condition, (3) clinical factors such as uncertainty, prognosis and recency of diagnosis, (4) patient factors including age and emotional state, (5) participants' role on the care team, and (6) clinician factors such as emotion and communication skill level.

CONCLUSION

Participants were hesitant to commit to the present moment as the right time for GOC discussions based on variations in clinical presentation. Clinical decision support systems that include more targeted information about risk of clinical deterioration and likelihood of reversal of the acute condition may prompt physicians to discuss GOC, but more support for managing discomfort with uncertainty is also needed.

Machine Learning for Targeted Advance Care Planning in Cancer Patients: A Quality Improvement Study

CONTEXT

Prognostication challenges contribute to delays in advance care planning (ACP) for patients with cancer near the end of life (EOL).

OBJECTIVES

Examine a quality improvement mortality prediction algorithm intervention's impact on ACP documentation and EOL care.

METHODS

We implemented a validated mortality risk prediction machine learning model for solid malignancy patients admitted from the emergency department (ED) to a dedicated solid malignancy unit at Duke University Hospital. Clinicians received an email when a patient was identified as high-risk. We compared ACP documentation and EOL care outcomes before and after the notification intervention. We excluded patients with intensive care unit (ICU) admission in the first 24 hours. Comparisons involved chi-square/Fisher's exact tests and Wilcoxon rank sum tests; comparisons stratified by physician specialty employ Cochran-Mantel-Haenszel tests.

RESULTS

Preintervention and postintervention cohorts comprised 88 and 77 patients, respectively. Most were White, non-Hispanic/Latino, and married. ACP conversations were documented for 2.3% of hospitalizations preintervention vs. 80.5% postintervention (P<0.001), and if the attending physician notified was a palliative care specialist (4.1% vs. 84.6%) or oncologist (0% vs. 76.3%) (P<0.001). There were no differences between groups in length of stay (LOS), hospice referral, code status change, ICU admissions or LOS, 30-day readmissions, 30-day ED visits, and inpatient and 30-day deaths.

CONCLUSION

Identifying patients with cancer and high mortality risk via machine learning elicited a substantial increase in documented ACP conversations but did not impact EOL care. Our intervention showed promise in changing clinician behavior. Further integration of this model in clinical practice is ongoing.

Clinician- and Patient-Directed Communication Strategies for Patients With Cancer at High Mortality Risk: A Cluster Randomized Trial

Importance

Serious illness conversations (SICs) that elicit patients' values, goals, and care preferences reduce anxiety and depression and improve quality of life, but occur infrequently for patients with cancer. Behavioral economic implementation strategies (nudges) directed at clinicians and/or patients may increase SIC completion.

Objective

To test the independent and combined effects of clinician and patient nudges on SIC completion.

Design, Setting, and Participants

A 2 × 2 factorial, cluster randomized trial was conducted from September 7, 2021, to March 11, 2022, at oncology clinics across 4 hospitals and 6 community sites within a large academic health system in Pennsylvania and New Jersey among 163 medical and gynecologic oncology clinicians and 4450 patients with cancer at high risk of mortality (≥10% risk of 180-day mortality).

Interventions

Clinician clusters and patients were independently randomized to receive usual care vs nudges, resulting in 4 arms: (1) active control, operating for 2 years prior to trial start, consisting of clinician text message reminders to complete SICs for patients at high mortality risk; (2) clinician nudge only, consisting of active control plus weekly peer comparisons of clinician-level SIC completion rates; (3) patient nudge only, consisting of active control plus a preclinic electronic communication designed to prime patients for SICs; and (4) combined clinician and patient nudges.

Main Outcomes and Measures

The primary outcome was a documented SIC in the electronic health record within 6 months of a participant's first clinic visit after randomization. Analysis was performed on an intent-to-treat basis at the patient level.

Results

The study accrued 4450 patients (median age, 67 years [IQR, 59-75 years]; 2352 women [52.9%]) seen by 163 clinicians, randomized to active control (n = 1004), clinician nudge (n = 1179), patient nudge (n = 997), or combined nudges (n = 1270). Overall patient-level rates of 6-month SIC completion were 11.2% for the active control arm (112 of 1004), 11.5% for the clinician nudge arm (136 of 1179), 11.5% for the patient nudge arm (115 of 997), and 14.1% for the combined nudge arm (179 of 1270). Compared with active control, the combined nudges were associated with an increase in SIC rates (ratio of hazard ratios [rHR], 1.55 [95% CI, 1.00-2.40]; P = .049), whereas the clinician nudge (HR, 0.95 [95% CI, 0.64-1.41; P = .79) and patient nudge (HR, 0.99 [95% CI, 0.73-1.33]; P = .93) were not.

Conclusions and Relevance

In this cluster randomized trial, nudges combining clinician peer comparisons with patient priming questionnaires were associated with a marginal increase in documented SICs compared with an active control. Combining clinician- and patient-directed nudges may help to promote SICs in routine cancer care.

Trial Registration

ClinicalTrials.gov Identifier: NCT04867850.

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.

Looking Beyond Mortality Prediction: Primary Care Physician Views of Patients' Palliative Care Needs Predicted by a Machine Learning Tool

OBJECTIVES

 To assess primary care physicians' (PCPs) perception of the need for serious illness conversations (SIC) or other palliative care interventions in patients flagged by a machine learning tool for high 1-year mortality risk.

METHODS

 We surveyed PCPs from four Brigham and Women's Hospital primary care practice sites. Multiple mortality prediction algorithms were ensembled to assess adult patients of these PCPs who were either enrolled in the hospital's integrated care management program or had one of several chronic conditions. The patients were classified as high or low risk of 1-year mortality. A blinded survey had PCPs evaluate these patients for palliative care needs. We measured PCP and machine learning tool agreement regarding patients' need for an SIC/elevated risk of mortality.

RESULTS

 Of 66 PCPs, 20 (30.3%) participated in the survey. Out of 312 patients evaluated, 60.6% were female, with a mean (standard deviation [SD]) age of 69.3 (17.5) years, and a mean (SD) Charlson Comorbidity Index of 2.80 (2.89). The machine learning tool identified 162 (51.9%) patients as high risk. Excluding deceased or unfamiliar patients, PCPs felt that an SIC was appropriate for 179 patients; the machine learning tool flagged 123 of these patients as high risk (68.7% concordance). For 105 patients whom PCPs deemed SIC unnecessary, the tool classified 83 as low risk (79.1% concordance). There was substantial agreement between PCPs and the tool (Gwet's agreement coefficient of 0.640).

CONCLUSIONS

 A machine learning mortality prediction tool offers promise as a clinical decision aid, helping clinicians pinpoint patients needing palliative care interventions.

INNOVATIONS IN DIGITAL HEALTH TO IMPROVE CARE DELIVERY: THE BJC HEALTHCARE/WASHINGTON UNIVERSITY SCHOOL OF MEDICINE HEALTHCARE INNOVATION LAB

The Healthcare Innovation Lab, established by BJC HealthCare and Washington University School of Medicine, has catalyzed care delivery innovations since 2017. Focusing on digital health to enhance care delivery and patient outcomes, the Lab emphasizes predictive analytics, digital point-of-care tools, and remote patient monitoring. The Lab identifies innovative ideas that align with the health system mission and deliver empiric value to its patients and care teams. Since its inception, the Lab has vetted 507 ideas, piloting 98, with a success rate of 40%. Examples include a predictive model to improve palliative care referrals and goal-of-care discussions, a digital approach to non-emergent medical transportation that enhances access and equity, and a COVID-19 home monitoring program that proved essential during the pandemic. These initiatives underscore the importance of integrating digital technology with health care, balancing innovation with practical application, and using a data-informed approach to innovation selection and assessment.

Rural Hospital Disparities in Goals of Care Documentation

CONTEXT

Goals of care conversations for seriously ill hospitalized patients are associated with high-quality patient-centered care.

OBJECTIVES

We aimed to assess the prevalence of documented goals of care conversations for rural hospitalized patients compared to nonrural hospitalized patients.

METHODS

We retrospectively assessed goals of care documentation using a template note for adult patients with predicted 90-day mortality greater than 30% admitted to eight rural and nine nonrural community hospitals between July 2021 and April 2023. We compared predictors and prevalence of goals of care documentation among rural and nonrural hospitals.

RESULTS

Of the 31,098 patients admitted during the study period, 21% were admitted to a rural hospital. Rural patients were more likely than nonrural patients to be >65 years old (89% vs. 86%, P = <.0001), more likely to live in a neighborhood classified in the highest quintile of socioeconomic disadvantage (40% vs. 16%, P = <.0001), and less likely to receive a palliative care consult (8% vs. 18%, P = <.0001). Goals of care documentation occurred less often for patients admitted to rural vs. nonrural community hospitals (2% vs. 7%, P < .0001). In the base multivariable logistic regression model adjusting for patient characteristics, the odds of goals care documentation were lower in rural vs. nonrural community hospitals (aOR 0.4, P = .0232). In a second multivariable logistic regression model including both patient characteristics and severity of illness, the odds of goals of care documentation in rural community hospitals were no longer statistically different than nonrural community hospitals (aOR 0.5, P = .1080). Patients who received a palliative care consult had a lower prevalence of goals of care documentation in rural vs. nonrural hospitals (16% vs. 37%, P = <.0001).

CONCLUSION

In this study of 17 rural and nonrural community hospitals, we found low overall prevalence of goals of care documentation with particularly infrequent documentation occurring within rural hospitals. Future study is needed to assess barriers to goals of care documentation contributing to low prevalence of goals of care conversations in rural hospital settings.