The goal of this study was to investigate the application of machine learning models capable of capturing multiplicative and temporal clinical risk factors for outcome prediction in patients with aneurysmal subarachnoid hemorrhage (aSAH). We examined a cohort of 575 aSAH patients from Emory Healthcare, identified via digital subtraction angiography. The outcome measure was the modified Ranking Scale (mRS) after 90 days. Predictions were performed with longitudinal clinical and imaging risk factors as inputs into a regularized Logistic Regression, a feedforward Neural Network and a multivariate time-series prediction model known as the long short-term memory (LSTM) architecture. Through extraction of higher-order risk factors, the LSTM model achieved an AUC of 0.89 eight days into hospitalization, outperforming other techniques. Our preliminary findings indicate the proposed model has the potential to aid treatment decisions and effective imaging resource utilization in high-risk patients by providing actionable predictions prior to the development of neurological deterioration.
Learning Objective: 1- Understand the current challenges in outcome prediction for patient with Aneurysmal Subarachnoid Hemorrhage (aSAH).
2- Learn that patient information during each day of hospitalization should be considered as a sequential data.
3- Understand the importance of considering temporal information in predicting an outcome for a sequential data.
Azade Tabaie (Presenter)
Shamim Nemati, Emory University
Jason Allen, Emory University
Charlotte Chung, Emory University
Flavia Firmino de Queiroga, Emory University
Won-Jun Kuk, Emory University
Adam Prater, Emory University