Medical system interface apparatus and methods to classify and provide medical data using artificial intelligence
Apparatus, systems, devices, other articles of manufacture and associated methods are disclosed and described herein to process medical data to generate a classification of the medical data using artificial intelligence. An example apparatus includes a processor to execute instructions to implement a history of past illness (HPI) receiver to receive an HPI formatted as a string, the string including one or more words, the words organized in sentences, a natural language processor to tokenize the one or more words into tokens based on a context associated with at least one of the one or more words and a tensor generator to convert the tokens into hashes, each of the hashes forming a dimension of a tensor based on the context. The apparatus further includes a neural network to embed each of the hashes into vectors, process the vectors to classify the HPI as extended or brief based on a similarity to a set of classified HPIs and output a classification for the HPI. The apparatus further includes an electronic medical record modifier to modify an electronic medical record with the HPI and the classification and to trigger an action with respect to the electronic medical record based on the classification.
1. An apparatus comprising:
a processor to execute instructions to implement at least:
a history of past illness (HPI) receiver to receive an HPI formatted as a string, the string including one or more words, the words organized in an order of sentences;
a natural language processor to tokenize the one or more words into tokens based on a context associated with at least one of the one or more words;
a tensor generator to convert the tokens into hashes, each of the hashes forming a dimension of a tensor based on the context;
a neural network to:
embed each of the hashes into vectors;
process the vectors to classify the HPI as extended or brief based on a similarity to a set of classified HPIs; and
output a classification for the HPI; and
a medical system interface to modify a medical support system with the HPI and the classification and to trigger an action with respect to the medical support system based on the classification.
2. The apparatus of claim 1 , wherein the natural language processor is further to:
randomize the order of the sentences of the HPI;
lemmatize the words into lemmas; and
replace the tokens of named entities with predefined tags associated with each type of named entities.
3. The apparatus of claim 2 , where the types of the named entities include at least one of dates, locations, times, quantities, people or out-of-vocabulary words.
4. The apparatus of claim 1 , wherein the neural network is a three-layer recurrent neural network including an embedding layer, a long short-term memory (LSTM) layer and a fully connected layer.
5. The apparatus of claim 4 , wherein the fully connected layer generates a binary output using a sigmoid activation function, the binary output indicating the classification of the HPI.
6. The apparatus of claim 1 , wherein each HPI of the set of classified HPIs is classified based on an identification of four or more HPI criteria, the HPI criteria including (2) quality of problem, (3) severity of problem, (4) duration of problem, (5) context of problem, (6) modifying factors, and (7) associated signs and symptoms.
7. The apparatus of claim 1 , wherein the hashes are integers based on a sparse vector generated via one hot encoding.
8. The apparatus of claim 1 , wherein the neural network is to further identify a bodily system described in the HPI.
9. The apparatus of claim 1 , wherein the medical support system includes at least one of an electronic medical record, medical billing system or computer-aided diagnosis system.
10. A method comprising:
receiving an HPI formatted as a string, the string including one or more words, the words organized in an order of sentences;
tokenizing the one or more words into tokens based on a context associated with at least one of the one or more words;
converting the tokens into hashes, each of the hashes forming a dimension of a tensor based on the context;
embedding each of the hashes into vectors;
processing the vectors to classify the HPI as extended or brief based on a similarity to a set of classified HPIs;
outputting a classification for the HPI; and
modifying a medical support system with the HPI and the classification and to trigger an action with respect to the medical support system based on the classification.
11. The method of claim 10 further including:
randomizing the order of the sentences of the HPI;
lemmatizing the words into lemmas; and
replacing the tokens of named entities with predefined tags associated with each type of the named entities.
12. The method of claim 11 , where the types of the named entities include at least one of dates, locations, times, quantities, people or out-of-vocabulary words.
13. The method of claim 10 , further including generating a binary output using a sigmoid activation function, the binary output indicating the classification of the HPI.
14. The method of claim 10 , further including identifying a bodily system described in the HPI.
15. The method of claim 10 , wherein each HPI of the set of classified HPIs is classified based on an identification of four or more HPI criteria, the HPI criteria including (2) quality of problem, (3) severity of problem, (4) duration of problem, (5) context of problem, (6) modifying factors, and (7) associated signs and symptoms.
16. A tangible machine readable medium comprising instructions, which when executed, cause a processor to at least:
receive an HPI formatted as a string, the string including one or more words, the words organized in an order of sentences;
tokenize the one or more words into tokens based on a context associated with at least one of the one or more words;
convert the tokens into hashes, each of the hashes forming a dimension of a tensor based on the context;
embed each of the hashes into vectors;
process the vectors to classify the HPI as extended or brief based on a similarity to a set of classified HPIs;
output a classification for the HPI; and
modify a medical support system with the HPI and the classification and to trigger an action with respect to the medical support system based on the classification.
17. The tangible machine readable medium of claim 16 , further including instructions, which when executed, cause the processor to:
randomize the order of the sentences of the HPI;
lemmatize the words into lemmas; and
replace the tokens of named entities with predefined tags associated with each type of the named entities.
18. The tangible machine readable medium of claim 17 , wherein the types of the named entities include at least one of dates, locations, times, quantities, people or out-of-vocabulary words.
19. The tangible machine readable medium of claim 16 , further including instructions, which when executed, cause the processor to generate a binary output using a sigmoid activation function, the binary output indicating the classification of the HPI.
20. The tangible machine readable medium of claim 16 , further including instructions, which when executed, cause the processor to identify a bodily system described in the HPI.