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

Importance: Goal-concordant care is an ongoing challenge in hospital settings. Identification of high mortality risk within 30 days may call attention to the need to have serious illness conversations, including the documentation of patient goals of care. Objective: To examine goals of care discussions (GOCDs) in a community hospital setting with patients identified as having a high risk of mortality by a machine learning mortality prediction algorithm. Design, Setting, and Participants: This cohort study took place at community hospitals within 1 health care system. Participants included adult patients with a high risk of 30-day mortality who were admitted to 1 of 4 hospitals between January 2 and July 15, 2021. Patient encounters of inpatients in the intervention hospital where physicians were notified of the computed high risk mortality score were compared with patient encounters of inpatients in 3 community hospitals without the intervention (ie, matched control). Intervention: Physicians of patients with a high risk of mortality within 30 days received notification and were encouraged to arrange for GOCDs. Main Outcomes and Measures: The primary outcome was the percentage change of documented GOCDs prior to discharge. Propensity-score matching was completed on a preintervention and postintervention period using age, sex, race, COVID-19 status, and machine learning-predicted mortality risk scores. A difference-in-difference analysis validated the results. Results: Overall, 537 patients were included in this study with 201 in the preintervention period (94 in the intervention group; 104 in the control group) and 336 patients in the postintervention period. The intervention and control groups included 168 patients per group and were well-balanced in age (mean [SD], 79.3 [9.60] vs 79.6 [9.21] years; standardized mean difference [SMD], 0.03), sex (female, 85 [51%] vs 85 [51%]; SMD, 0), race (White patients, 145 [86%] vs 144 [86%]; SMD 0.006), and Charlson comorbidities (median [range], 8.00 [2.00-15.0] vs 9.00 [2.00 to 19.0]; SMD, 0.34). Patients in the intervention group from preintervention to postintervention period were associated with being 5 times more likely to have documented GOCDs (OR, 5.11 [95% CI, 1.93 to 13.42]; P = .001) by discharge compared with matched controls, and GOCD occurred significantly earlier in the hospitalization in the intervention patients as compared with matched controls (median, 4 [95% CI, 3 to 6] days vs 16 [95% CI, 15 to not applicable] days; P < .001). Similar findings were observed for Black patient and White patient subgroups. Conclusions and Relevance: In this cohort study, patients whose physicians had knowledge of high-risk predictions from machine learning mortality algorithms were associated with being 5 times more likely to have documented GOCDs than matched controls. Additional external validation is needed to determine if similar interventions would be helpful at other institutions.

Development and Structure of an Accurate Machine Learning Algorithm to Predict Inpatient Mortality and Hospice Outcomes in the Coronavirus Disease 2019 Era.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic has challenged the accuracy and racial biases present in traditional mortality scores. An accurate prognostic model that can be applied to hospitalized patients irrespective of race or COVID-19 status may benefit patient care. RESEARCH DESIGN: This cohort study utilized historical and ongoing electronic health record features to develop and validate a deep-learning model applied on the second day of admission predicting a composite outcome of in-hospital mortality, discharge to hospice, or death within 30 days of admission. Model features included patient demographics, diagnoses, procedures, inpatient medications, laboratory values, vital signs, and substance use history. Conventional performance metrics were assessed, and subgroup analysis was performed based on race, COVID-19 status, and intensive care unit admission. SUBJECTS: A total of 35,521 patients hospitalized between April 2020 and October 2020 at a single health care system including a tertiary academic referral center and 9 community hospitals. RESULTS: Of 35,521 patients, including 9831 non-White patients and 2020 COVID-19 patients, 2838 (8.0%) met the composite outcome. Patients who experienced the composite outcome were older (73 vs. 61 y old) with similar sex and race distributions between groups. The model achieved an area under the receiver operating characteristic curve of 0.89 (95% confidence interval: 0.88, 0.91) and an average positive predictive value of 0.46 (0.40, 0.52). Model performance did not differ significantly in White (0.89) and non-White (0.90) subgroups or when grouping by COVID-19 status and intensive care unit admission. CONCLUSION: A deep-learning model using large-volume, structured electronic health record data can effectively predict short-term mortality or hospice outcomes on the second day of admission in the general inpatient population without significant racial bias.

Early Palliative Care Consultation in the Medical ICU: A Cluster Randomized Crossover Trial.

OBJECTIVES: To assess the impact of early triggered palliative care consultation on the outcomes of high-risk ICU patients. DESIGN: Single-center cluster randomized crossover trial. SETTING: Two medical ICUs at Barnes Jewish Hospital. PATIENTS: Patients (n = 199) admitted to the medical ICUs from August 2017 to May 2018 with a positive palliative care screen indicating high risk for morbidity or mortality. INTERVENTIONS: The medical ICUs were randomized to intervention or usual care followed by washout and crossover, with independent assignment of patients to each ICU at admission. Intervention arm patients received a palliative care consultation from an interprofessional team led by board-certified palliative care providers within 48 hours of ICU admission. MEASUREMENTS AND MAIN RESULTS: Ninety-seven patients (48.7%) were assigned to the intervention and 102 (51.3%) to usual care. Transition to do-not-resuscitate/do-not-intubate occurred earlier and significantly more often in the intervention group than the control group (50.5% vs 23.4%; p < 0.0001). The intervention group had significantly more transfers to hospice care (18.6% vs 4.9%; p < 0.01) with fewer ventilator days (median 4 vs 6 d; p < 0.05), tracheostomies performed (1% vs 7.8%; p < 0.05), and postdischarge emergency department visits and/or readmissions (17.3% vs 38.9%; p < 0.01). Although total operating cost was not significantly different, medical ICU (p < 0.01) and pharmacy (p < 0.05) operating costs were significantly lower in the intervention group. There was no significant difference in ICU length of stay (median 5 vs 5.5 d), hospital length of stay (median 10 vs 11 d), in-hospital mortality (22.6% vs 29.4%), or 30-day mortality between groups (35.1% vs 36.3%) (p > 0.05). CONCLUSIONS: Early triggered palliative care consultation was associated with greater transition to do-not-resuscitate/do-not-intubate and to hospice care, as well as decreased ICU and post-ICU healthcare resource utilization. Our study suggests that routine palliative care consultation may positively impact the care of high risk, critically ill patients.