Using Pattern Recognition to Detect Implicit Bias in Hospital Triaging
Latest News:
08/26/2022 - Our work has been accepted for presentation at the 2022 Southern California Conferences for Undergraduate Research at Pepperdine University
Abstract:
In light of the COVID-19 pandemic and the health crisis left in its wake, our goal is to develop and utilize extensive machine learning techniques to provide a clear picture of the treatment, and possible mistreatment, of specific demographics of patients during hospital triaging. We aim to reveal whether a patient’s treatment and hospital disposition is related to the following attributes - Emergency Severity Index (ESI), gender, employment status, insurance status, race, or ethnicity. Our work is separated into two parts - the classification task and data analysis. As part of the classification task, we train a model using neural networks to classify patients as either “Admitted” or “Discharged” given the aforementioned attributes. We then analyze the data using SHapley Additive exPlanations (SHAP) values to determine the impact of each attribute on a patient’s treatment and hospital disposition. Our findings show that importance levels vary for each attribute. Notably, we found that patients with private insurance programs receive significantly better treatment compared to patients with federal-run healthcare programs (e.g. Medicaid, Medicare). Furthermore, a patient’s ethnicity has a greater impact on treatment for patients under 40 years of age for any given ESI level. Surprisingly, our findings show language is not a barrier during treatment. For future works, we hope to aggregate additional patient data from hospitals to find whether specific demographics of patients receive better healthcare in different parts of the United States.