Abstract: This invention relates generally to the medical technology field, and more specifically to a new and useful method for aggregating data.

Abstract: Some embodiments provide a non-transitory machine-readable medium that stores a program. The program receives a plurality of documents. The program further uses a visual model to generate a vector representation for each document in the plurality of documents. The program also clusters the plurality of documents into a set of clusters based on the vector representations of the plurality of documents. The program further determines a sample set of documents from the plurality of documents based on the set of clusters.

Abstract: Techniques for analyzing patient health records are provided. Clinical documents may be received in response to a patient-initiated request, for example. In one embodiment, machine learning algorithms are used to sectionalize and extract data from clinical documents. The machine learning algorithms used may be more highly focused for analyzing text residing deeper in a clinical document hierarchy, for example. In one embodiment, extracted data is stored in a patient graph. Searches may be made against the graph to yield results to help save lives and/or improve patient outcomes.

Abstract: Some embodiments provide a program that receives a request to sectionize a document, uses a visual model to identify a set of candidate section headers in the document, and uses a language model to determine a type of section header for at least one candidate section header in the set of candidate section headers in the document. Some embodiments provide a program that receives a request to anonymize data in a document, uses a visual model to identify a set of candidate confidential sections in the document that are each predicted to include a collection of confidential data, uses a language model to identify terms in each candidate confidential section that are determined to be confidential data, analyzes the document to identify a set of terms in the document based on the identified terms in the set of candidate confidential sections, and redacts the set of terms in the document.

Abstract: Some embodiments provide a non-transitory machine-readable medium that stores a program. The program receives a set of words. The program further retrieves an entry from a knowledge base comprising a plurality of entries. Each entry includes a text description of a concept. The program also determines an embedding for the entry based on the text description of the concept. The program further iteratively determines an embedding for a word in the set of words, increasing a size of a window of words in the set of words, and calculating a confidence score for the entry with respect to the word based on the embedding for the entry and the embedding for the word until a successive calculated confidence score decreases below a previous calculated confidence score. The program also determines that a window of words in the set of words having a previous size represents an entity.

Abstract: Techniques for sectionalizing clinical documents are provided. In one set of embodiments, a computer system can, for each page of a clinical document: identify one or more section header candidates in the page and, for each section header candidate, attempt to classify the section header candidate as corresponding to one of a plurality of section types using a first classifier or a second classifier. The computer system can further partition the page into one or more sections based on corresponding section header candidates that have been successfully classified using either the first classifier or the second classifier, where the partitioning includes associating each section with a section type in the plurality of section types in accordance with the classification of the section's corresponding section header candidate. The computer system can then validate, for each section, the section's section type via an analysis of the body of the section.

Abstract: Some embodiments provide a program that receives a request to sectionize a document, uses a visual model to identify a set of candidate section headers in the document, and uses a language model to determine a type of section header for at least one candidate section header in the set of candidate section headers in the document. Some embodiments provide a program that receives a request to anonymize data in a document, uses a visual model to identify a set of candidate confidential sections in the document that are each predicted to include a collection of confidential data, uses a language model to identify terms in each candidate confidential section that are determined to be confidential data, analyzes the document to identify a set of terms in the document based on the identified terms in the set of candidate confidential sections, and redacts the set of terms in the document.

Abstract: Some embodiments provide a non-transitory machine-readable medium that stores a program. The program receives a plurality of sets of words. Each set of words in the plurality of sets of words includes a word annotated as being an entity having a same custom entity type. The program further determines a plurality of word embeddings in a word embedding space for the plurality of annotated words. The program also defines a region in the word embedding space based on the received plurality of word embeddings. The program further receives a set of words. The program also determines a word embedding for a subset of the set of words. The program further determines whether the word embedding falls within the defined region in the word embedding space. Upon determining that the word embedding falls within the defined region in the word embedding space, the program also determines that the subset of the set of words represents an entity having the custom entity type.

Abstract: Some embodiments provide a program that receives a request to sectionize a document, uses a visual model to identify a set of candidate section headers in the document, and uses a language model to determine a type of section header for at least one candidate section header in the set of candidate section headers in the document. Some embodiments provide a program that receives a request to anonymize data in a document, uses a visual model to identify a set of candidate confidential sections in the document that are each predicted to include a collection of confidential data, uses a language model to identify terms in each candidate confidential section that are determined to be confidential data, analyzes the document to identify a set of terms in the document based on the identified terms in the set of candidate confidential sections, and redacts the set of terms in the document.

Abstract: Some embodiments provide a program that receives a set of words. The program further determines an embedding for a word in the set of words. The program also accesses a knowledge base to retrieve a plurality of entries. Each entry includes a text description of a concept. The program further determines, for each entry in the plurality of entries in the knowledge base, an embedding for the entry based on the text description of the concept. The program also calculates, for each entry in the plurality of entries in the knowledge base, a distance value between the embedding for the word in the set of words and the embedding for the entry. The program further determines an entry in the plurality of entries in the knowledge base having a text description of a concept that best represents the set of words based on the plurality of distance values.