Generating clinical forms
A machine learning system may be used to predict clinical questions to ask on a clinical form. A first encoder may encode first information and a second encoder may encoder second information from a medical record of a past appointment. The first and second encoded information and additional encoded information may be used to predict a clinical question to ask by using a reinforcement learning system. The reinforcement learning system may be trained by receiving ratings of questions from users.
1. A computer-implemented method for generating questions for a clinical form, the method comprising:
training a first neural network autoencoder to encode information of a first type into a first vector representation, the first autoencoder comprising a first encoder that maps a first input vector to the first vector representation and a first decoder that maps the first vector representation to a first output vector, where the first decoder is trained to reduce the distance between the first output vector and the first input vector;
training a second neural network autoencoder to encode information of a second type into a second vector representation, the second autoencoder comprising a second encoder that maps a second input vector to the second vector representation and a second decoder that maps the second vector representation to a second output vector, where the second decoder is trained to reduce the distance between the second output vector and the second input vector;
providing a medical record of a past appointment of a patient;
extracting from the medical record a first portion of information of the first type and a second portion of information of the second type;
inputting the first portion of information to the first neural network autoencoder to output first encoded information;
inputting the second portion of information to the second neural network autoencoder to output second encoded information;
providing a database of clinical questions;
inputting the first encoded information and second encoded information into a third neural network encoder to generate an aggregate encoding;
predicting, by a question predictor, a clinical question to ask from the database of clinical questions based on the aggregate encoding.
2. The computer-implemented method of claim 1 , wherein the first neural network autoencoder is a variational autoencoder.
3. The computer-implemented method of claim 1 , wherein the first neural network autoencoder uses Kullback-Leibler divergence.
4. The computer-implemented method of claim 1 , wherein the second neural network autoencoder is a variational autoencoder.
5. The computer-implemented method of claim 1 , wherein the question predictor comprises a Q-learning system.
6. The computer-implemented method of claim 1 , wherein the question predictor comprises a Deep Q-learning system.
7. The computer-implemented method of claim 1 , wherein the first portion of information comprises information about one or more medications and the second portion of information comprises information about a diagnosis.
8. A non-transitory computer-readable medium, the non-transitory computer-readable medium comprising instructions for:
training a first neural network autoencoder to encode information of a first type into a first vector representation, the first autoencoder comprising a first encoder that maps a first input vector to the first vector representation and a first decoder that maps the first vector representation to a first output vector, where the first decoder is trained to reduce the distance between the first output vector and the first input vector;
training a second neural network autoencoder to encode information of a second type into a second vector representation, the second autoencoder comprising a second encoder that maps a second input vector to the second vector representation and a second decoder that maps the second vector representation to a second output vector, where the second decoder is trained to reduce the distance between the second output vector and the second input vector;
providing a medical record of a past appointment of a patient;
extracting from the medical record a first portion of information of the first type and a second portion of information of the second type;
inputting the first portion of information to the first neural network autoencoder to output first encoded information;
inputting the second portion of information to the second neural network autoencoder to output second encoded information;
providing a database of clinical questions;
inputting the first encoded information and second encoded information into a third neural network encoder to generate an aggregate encoding;
predicting, by a question predictor, a clinical question to ask from the database of clinical questions based on the aggregate encoding.
9. The non-transitory computer-readable medium of claim 8 , wherein the first neural network autoencoder is a variational autoencoder.
10. The non-transitory computer-readable medium of claim 8 , wherein the first neural network autoencoder uses Kullback-Leibler divergence.
11. The non-transitory computer-readable medium of claim 8 , wherein the second neural network autoencoder is a variational autoencoder.
12. The non-transitory computer-readable medium of claim 8 , wherein the question predictor comprises a Q-learning system.
13. The non-transitory computer-readable medium of claim 8 , wherein the question predictor comprises a Deep Q-learning system.
14. The non-transitory computer-readable medium of claim 8 , wherein the first portion of information comprises information about one or more medications and the second portion of information comprises information about a diagnosis.
15. A computer-implemented method for generating questions for a clinical form, the method comprising:
training a first neural network encoder to encode information of a first type into a first vector representation;
training a second neural network encoder to encode information of a second type into a second vector representation;
providing a medical record of a past appointment of a patient;
extracting from the medical record a first portion of information of the first type and a second portion of information of the second type;
inputting the first portion of information to the first neural network encoder to output first encoded information;
inputting the second portion of information to the second neural network encoder to output second encoded information;
providing a database of clinical questions;
predicting, by a question predictor, a clinical question to ask from the database of clinical questions based on the first encoded information and second encoded information.
16. The computer-implemented method of claim 15 , wherein the first neural network encoder is a variational autoencoder.
17. The computer-implemented method of claim 15 , wherein the first neural network encoder uses Kullback-Leibler divergence.
18. The computer-implemented method of claim 15 , wherein the second neural network encoder is a variational autoencoder.
19. The computer-implemented method of claim 15 , wherein the question predictor comprises a Q-learning system.
20. The computer-implemented method of claim 15 , wherein the question predictor comprises a Deep Q-learning system.
21. The computer-implemented method of claim 15 , wherein the first portion of information comprises information about one or more medications and the second portion of information comprises information about a diagnosis.
22. A non-transitory computer-readable medium, the non-transitory computer-readable medium comprising instructions for:
training a first neural network encoder to encode information of a first type into a first vector representation;
training a second neural network encoder to encode information of a second type into a second vector representation;
providing a medical record of a past appointment of a patient;
extracting from the medical record a first portion of information of the first type and a second portion of information of the second type;
inputting the first portion of information to the first neural network encoder to output first encoded information;
inputting the second portion of information to the second neural network encoder to output second encoded information;
providing a database of clinical questions;
predicting, by a question predictor, a clinical question to ask from the database of clinical questions based on the first encoded information and second encoded information.
23. The non-transitory computer-readable medium of claim 22 , wherein the first neural network encoder is a variational autoencoder.
24. The non-transitory computer-readable medium of claim 22 , wherein the first neural network encoder uses Kullback-Leibler divergence.
25. The non-transitory computer-readable medium of claim 22 , wherein the second neural network encoder is a variational autoencoder.
26. The non-transitory computer-readable medium of claim 22 , wherein the question predictor comprises a Q-learning system.
27. The non-transitory computer-readable medium of claim 22 , wherein the question predictor comprises a Deep Q-learning system.
28. The non-transitory computer-readable medium of claim 22 , wherein the first portion of information comprises information about one or more medications and the second portion of information comprises information about a diagnosis.