Search

e18618 Background: Cancer patients frequently utilize the Emergency Department (ED) for a variety of diagnoses, both related and unrelated to their cancer. Patients with cancer have unique risks related to their cancer and treatment which could influence ED-related outcomes. A better understanding of these risks could help improve risk-stratification for these patients and help inform future interventions. This study sought to define the increased risks cancer patients face for inpatient admission and hospital mortality among cancer patients presenting to the ED. Methods: From the National Emergency Department Sample (NEDS) we identified patients with and without a diagnosis of cancer presenting to the ED between 2016 and 2018. We used International Classification of Diseases, version 10 (ICD10-CM) codes to identify patients with cancer, and to identify patient’s presenting diagnosis. Multivariable mixed-effects logistic regression models assessed the influence of cancer diagnoses on two endpoints: hospital admission from the ED, and inpatient hospital mortality. Results: There were 340 million weighted ED visits, of which 8.3 million (2.3%) occurred in patients with a cancer diagnosis. Compared to non-cancer patients, patients with cancer had an increased risk of inpatient admission (64.7% vs. 14.8%; p < 0.0001) and hospital mortality (4.6% vs. 0.5%; p < 0.0001). Factors associated with both an increased risk of hospitalization and death included older age, male gender, lower income level, discharge quarter, and receipt of care in a teaching hospital. We identified the top 15 most common presenting diagnoses among cancer patients, and among each of these diagnoses, cancer patients had increased risks of hospitalization (odds ratio [OR] range 2.0-13.2; all p < 0.05) and death (OR range 2.1-14.4; all p < 0.05) compared to non-cancer patients with the same diagnosis. Within the cancer patient cohort, cancer site was the most robust individual predictor associated with risk of hospitalization or death, with highest risk among patients with metastatic cancer, liver and lung cancers compared to the reference group of prostate cancer patients. Conclusions: Cancer patients presenting to the ED have high risks for hospital admission and death when compared to patients without cancer. Cancer patients represent a distinct population and may benefit from cancer-specific risk stratification or focused interventions tailored to improve outcomes in the ED setting.

1512 Background: Elderly hospitalized cancer patients face high risks of inpatient hospital mortality. Identifying patients at high risk of hospital mortality could help with risk stratification, and potentially help inform future interventions aimed at improving outcomes. We evaluated the predictive capacity of a high-dimensional machine-learning prediction tool to predict inpatient mortality, and compared the performance of this new tool to existing prediction indices. Methods: We identified cancer patients 75 and over who presented to an emergency department (ED) and were subsequently hospitalized from the National Emergency Department Sample (NEDS) between 2016 and 2018. We used an extreme gradient boosting approach to predict the risk of death during hospitalization. Model covariates included patient demographics, hospital characteristics, and International Classification of Diseases, version 10 (ICD-10) diagnosis codes recorded during the ED visit. The data were split 75%/25% into training/testing datasets. We constructed the model with training data and evaluated performance within the test data using area under the curve (AUC), with an AUC of 1.0 indicating perfect prediction. We compared the performance of this risk prediction model to standard prediction indices including the Hospital Frailty Risk Score, modified 5-item frailty index, and Charlson comorbidity index. Results: We identified 1,892,690 weighted-hospitalizations among elderly cancer patients, of which 133,379 (7.0%) who died in the inpatient setting. Our final predictive model included 238 features, which contained 5 demographic variables, 3 hospital characteristics, and 230 ICD-10 diagnosis codes. The predictive model achieved an AUC of 0.92. Our comparator models including the Hospital Frailty Risk Score, modified 5-item frailty index, and Charlson comorbidity index achieved AUCs of 0.67, 0.56, and 0.60, respectively. Conclusions: Using a high-dimensional machine-learning model enabled a high level of precision in predicting hospital mortality among elderly cancer patients, substantially out-performing existing prediction indices. High-dimensional prediction models show promise in helping to identify patients at risk of severe adverse outcomes, though additional validation is needed as well as research studying how to implement these tools into practice.

e22019 Background: Pediatric cancer patients represent a vulnerable cohort at risk of adverse outcomes after presenting to the emergency department (ED). Given the severity of cancer-related complications and uniqueness of this population, approaches to better risk stratify this cohort could potentially help define future interventions geared towards improving outcomes. We used a high-dimensional machine learning approach to help define the risk of hospitalization after an ED visit among pediatric patients with cancer. Methods: A cohort of cancer patients under 18 was identified from the Nationwide Emergency Department Sample (NEDS) between 2016-2018. We used a lasso regression model to predict inpatient admission after an ED visit. Model covariates included patient demographics, hospital characteristics, and International Classification of Diseases, version 10 (ICD-10) diagnosis codes. The data were split 75%/25% into training/testing data. The model was constructed with training data, and performance assessed on the test data using the area under the curve (AUC), with an AUC of 1.0 indicating perfect prediction. Results: We identified 129,631 pediatric cancer patients who visited the ED, of which 54.5% were subsequently admitted. The final predictive model included 150 variables, including 9 demographic, 6 hospital, and 135 unique ICD-10 codes. The model demonstrated excellent ability to predict hospitalization with an AUC of 0.96. The top 5 most important variables associated with inpatient admission were diagnoses of paralytic ileus/intestinal obstruction, neutropenia, sepsis, aplastic anemia/bone marrow failure, and bacterial infection. Conclusions: Pediatric cancer patients frequently present to the ED with complications of their cancer or their treatment, and over half of these patients are admitted. This study demonstrates the capacity of high-dimensional prediction models to help identify pediatric patients at risk of hospitalization. Additional research is needed to determine how to implement these predictive models in clinical practice.