US 11,742,087 B2
Processing clinical notes using recurrent neural networks
Jonas Beachey Kemp, Sunnyvale, CA (US); Andrew M. Dai, San Francisco, CA (US); and Alvin Rishi Rajkomar, San Jose, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Aug. 11, 2020, as Appl. No. 16/990,172.
Application 16/990,172 is a continuation of application No. 16/712,947, filed on Dec. 12, 2019, granted, now 10,770,180.
Claims priority of provisional application 62/778,833, filed on Dec. 12, 2018.
Prior Publication US 2021/0125721 A1, Apr. 29, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G16H 50/20 (2018.01); G06N 3/049 (2023.01); G16H 10/60 (2018.01); G16H 50/30 (2018.01)
CPC G16H 50/20 (2018.01) [G06N 3/049 (2013.01); G16H 10/60 (2018.01); G16H 50/30 (2018.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising one or more computers and one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
receiving electronic health record data for a patient,
the electronic health record data comprising one or more observations of each of a plurality of different feature types, and
the plurality of different feature types including a clinical note feature type, wherein each observation of the clinical note feature type is a clinical note comprising a respective sequence of text tokens;
generating a respective observation embedding for each of the observations, comprising, for each clinical note:
processing the sequence of text tokens in the clinical note using a clinical note embedding long short-term memory (LSTM) neural network to generate a respective token embedding for each of the text tokens; and
generating the observation embedding for the clinical note from the token embeddings for the text tokens in the clinical note;
generating an embedded representation of the electronic health record data, wherein the embedded representation comprises a respective patient record embedding corresponding to each of a plurality of time windows, and wherein generating the embedded representation comprises, for each time window:
combining the observation embeddings of observations occurring during the time window to generate the patient record embedding corresponding to the time window; and
processing the embedded representation of the electronic health record data using a prediction recurrent neural network to generate a neural network output that characterizes a future health status of the patient after the last time window in the embedded representation,
wherein the clinical note embedding LSTM neural network and the prediction recurrent neural network have been jointly trained on electronic health record training data.