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

Abstract

Background: Life expectancy is one of the most important factors in end-of-life decision making. Good prognostication for example helps to determine the course of treatment and helps to anticipate the procurement of health care services and facilities, or more broadly: facilitates Advance Care Planning. Advance Care Planning improves the quality of the final phase of life by stimulating doctors to explore the preferences for end-of-life care with their patients, and people close to the patients. Physicians, however, tend to overestimate life expectancy, and miss the window of opportunity to initiate Advance Care Planning. This research tests the potential of using machine learning and natural language processing techniques for predicting life expectancy from electronic medical records.

Methods: We approached the task of predicting life expectancy as a supervised machine learning task. We trained and tested a long short-term memory recurrent neural network on the medical records of deceased patients. We developed the model with a ten-fold cross-validation procedure, and evaluated its performance on a held-out set of test data. We compared the performance of a model which does not use text features (baseline model) to the performance of a model which uses features extracted from the free texts of the medical records (keyword model), and to doctors' performance on a similar task as described in scientific literature.

Results: Both doctors and the baseline model were correct in 20% of the cases, taking a margin of 33% around the actual life expectancy as the target. The keyword model, in comparison, attained an accuracy of 29% with its prognoses. While doctors overestimated life expectancy in 63% of the incorrect prognoses, which harms anticipation to appropriate end-of-life care, the keyword model overestimated life expectancy in only 31% of the incorrect prognoses.

Conclusions: Prognostication of life expectancy is difficult for humans. Our research shows that machine learning and natural language processing techniques offer a feasible and promising approach to predicting life expectancy. The research has potential for real-life applications, such as supporting timely recognition of the right moment to start Advance Care Planning.

Keywords: Advance care planning; Clinical free-text; Life expectancy prediction; Long short-term memory.

Fig. 1

Simplified LSTM architecture. At final time step t, x_t represents the feature vector used as input to the hidden LSTM units, which activate output h_t. In each preceding time step, output h functions as an intermediate prediction of life expectancy. We are interested in final prediction h_t: a probability distribution for the next 50 months

Fig. 2

Probability distributions produced by the baseline model for one patient at different moments in time. From top to bottom, the corresponding actual number of months to death are 33 months, 11 months, and 3 months, respectively

Fig. 3

Absolute frequency counts for actual and predicted life expectancies, for each month in range 1–50

Fig. 4

Relative certainty as a function of predicted life expectancy