Improving Palliative Care with Deep Learning
This addresses the challenge of improving palliative care access for hospitalized patients by reducing reliance on physician referrals, though it is incremental as it applies existing deep learning techniques to a specific healthcare domain.
The paper tackles the problem of mismatched end-of-life care by developing a deep learning algorithm that predicts patient mortality from EHR data to proactively identify those needing palliative care, with the method currently being piloted at a medical center.
Improving the quality of end-of-life care for hospitalized patients is a priority for healthcare organizations. Studies have shown that physicians tend to over-estimate prognoses, which in combination with treatment inertia results in a mismatch between patients wishes and actual care at the end of life. We describe a method to address this problem using Deep Learning and Electronic Health Record (EHR) data, which is currently being piloted, with Institutional Review Board approval, at an academic medical center. The EHR data of admitted patients are automatically evaluated by an algorithm, which brings patients who are likely to benefit from palliative care services to the attention of the Palliative Care team. The algorithm is a Deep Neural Network trained on the EHR data from previous years, to predict all-cause 3-12 month mortality of patients as a proxy for patients that could benefit from palliative care. Our predictions enable the Palliative Care team to take a proactive approach in reaching out to such patients, rather than relying on referrals from treating physicians, or conduct time consuming chart reviews of all patients. We also present a novel interpretation technique which we use to provide explanations of the model's predictions.