Machine learning system and method for pet health records

Abstract

A pet medical text recognizer may include one or more machine learning classifiers. The one or more machine learning classifiers may be trained using training data to associate raw text with pet clinical event codes. A performance metric may be provided, and the highest performing classifier according to the performance metric may be selected as the model for the pet medical text recognizer. The pet medical text recognizer may accept input text from a veterinary practice management system and generate a pet clinical event code for the text. A set of codes associated with a single pet may be aggregated into a pet health record.

What is claimed is: 
     
         1 . A computer-implemented method for generating a pet health record, the method comprising:
 providing a classification system of pet clinical events;   providing a pet medical text recognizer that includes one or more machine learning classifiers, the one or more machine learning classifiers comprising at least a neural network, LSTM, or BLSTM;   training one or more of the machine learning classifiers of the pet medical text recognizer to classify text according to the classification system using training data, the training data associating text and classifications;   providing a performance metric;   evaluating the performance of the one or more machine learning classifiers of the pet medical text recognizer using validation data and selecting the highest performing machine learning classifier according to the performance metric;   receiving text from a veterinary practice management system;   classifying the text from the veterinary practice management system using the selected machine learning classifier of the pet medical text recognizer to identify a pet clinical event classification.