AI Case Study
Stanford University researchers plan to improve palliative care by predicting mortality of patient with deep learning
In order to allocate care staff and resources efficiently researchers at Stanford have developed a deep learning model which analyses EHR data and predicts mortality within the next year.
Healthcare Providers And Services
"The criteria for deciding which patients benefit from pal- liative care can be hard to state explicitly. Our approach uses deep learning to screen patients admitted to the hospital to identify those who are most likely to have palliative care needs. The algorithm addresses a proxy problem - to predict the mortality of a given patient within the next 12 months - and use that prediction for making recommendations for palliative care referral. This frees the palliative care team from manual chart review of every admission and helps counter the potential biases of treating physicians by providing an objective rec- ommendation based on the patient’s EHR.
The Palliative Performance Scale was developed as a modification of the Karnofsky Performance Status Scale (KPS) to the Palliative care setting, and is calculated based on observable factors such as: degree of ambulation, ability to do activities, ability to do self-care, food and fluid intake, and state of consciousness."
R And D
Core Research And Development
Data suggests that physicians tend to be over optimistic while assessing patients resulting in a mismatch between patients wishes and actual care at the end of life and inefficient usage of care resources.
"The model achieves an AP score of 0.69 (0.65 on admitted patients). Early recall is desirable, and therefore Recall at precision 0.9 is a metric of interest. The model achieves recall of 0.34 at 0.9 precision (0.32 on admitted patients). The model achieves an AUROC of 0.93 (0.87 for admitted patients). Both the ROC and Precision-Recall plots suggest that the model demonstrates strong early recall behavior."
"Our model is a Deep Neural Network (DNN)  compris- ing an input layer (of 13,654 dimensions), 18 hidden layers (each 512 dimensions) and a scalar output layer. We employ the logistic loss function at the output layer and use the Scaled Exponential Linear Unit (SeLU) activation function  at each layer. The model is optimized using the Adam optimizer , with a mini-batch size of 128 examples."
"The EHR data of approximately 2 million adult and pediatric patients cared for at either the Stanford Hospital or the Lucile Packard Children’s hospital between 1995 and 2014."