Skip to main content

Table 4 Evaluation of the quality of the predictions

From: Predicting life expectancy with a long short-term memory recurrent neural network using electronic medical records

Assessor Accuracy Overly pessimistic Overly optimistic
Human EMR data + patient consultation 20% 17% 63%
Baseline model structured data features 20% 68% 12%
Keyword model structured data features + word2vec-based features 29% 52% 19%
  1. Predictions were considered accurate if they deviate less than 33% from the actual life expectancy. The human results were adopted from [15]. Note: the doctors in [15] estimated life expectancy for a different group of patients than our models do in this the current research