Method for extracting problem list section from unstructured data in medical record document, and outputting portion of problem list section by processors

A system for identifying a problem list section, the system comprising:

• one or more processors;
• and
• one or more non-transitory computer-readable media storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations including:
• receiving an electronic document;
• generating, based on applying an optical character recognition algorithm to the electronic document, unstructured text;
• identifying one or more problem list words in the unstructured text, the one or more problem list words belonging in a dataset for identifying a presence of a problem list section;
• associating a portion of the unstructured text that corresponds to the one or more problem list words in the unstructured text with the problem list section;
• removing one or more irrelevant portions of the unstructured text that are not associated with the one or more problem list words, the one or more irrelevant portions being identified according to one or more criteria that include:
• the presence of text following a heading that is not associated with a problem list word, or
• the presence of text on one or more pages following a predetermined maximum number of pages after the one or more problem list words;
• and
• outputting at least a portion of the problem list section.

A computer-implemented method for generating a list of problem list headings, the method comprising:

• receiving, by one or more processors, an electronic document;
• recognizing, by the one or more processors, characters present in the electronic document by implementing an optical character recognition algorithm that receives the electronic document as an input and produces unstructured text as an output;
• identifying, by the one or more processors, characters forming words and/or phrases of one or more headings that each indicate a presence of a problem list in the unstructured text output from the electronic document, each of the one or more headings being a potential problem list heading;
• and
• generating, by the one or more processors, a list of words and/or phrases that include the one or more potential problem list headings, the list of words and/or phrases forming a list of problem list headings,
• wherein one or more additional electronic documents are processed based on the list of problem list headings, including removing one or more irrelevant portions of unstructured text in the one or more additional electronic documents that are not associated with the list of words and/or phrases, the one or more irrelevant portions being identified according to one or more criteria that include:
• the presence of text following a heading that is not associated with the list of words and/or phrases, or
• the presence of text on one or more pages following a predetermined maximum number of pages after the list of words and/or phrases.