Lexalytics Makes First Foray into Document Data Extraction Market
Lexalytics has launched the Lexalytics Data Extraction Services, data extraction software and services that combine Lexalytics’ AI-based natural language processing (NLP) technologies with the ability to classify both structured and unstructured content to gain more insights and value from corporate documents.
According to the company, the services reduce the time and labor costs of document data analysis and extraction, while improving the accuracy and insights available within the data.
While there are companies that currently offer software capable of “scraping” documents such as PDFs and Microsoft Word files containing structured data in tables such as dates, billing codes, payment timeframes, support requirements, subscription details, reaction ratios, and statistical tests, many documents are a hybrid containing not just that structured content, but also free, unstructured text.
Traditionally, analysts in the fields of law, market research, insurance, healthcare, real estate, financial services and others have lacked an effective way of melding the structured and unstructured data from their documents into a coherent database to properly access, view and analyze it all in one place.
Lexalytics Data Extraction Services leverages its Salience text analytics engine to provide greater insights and automatically organize data into a format that includes features such as summarization, sentiment analysis, intentions, named entity extraction, categories and themes.
According to Lexalytics, an industry example of the benefits of Lexalytics Data Extraction Services is in healthcare. Medical coding and billing is an expensive and error-prone process. The ICD-10 (the latest revision of the International Statistical Classification of Diseases and Related Health Problems, a medical classification system from the World Health Organization) contains more than 70,000 codes, not to mention the thousands of codes in other mainstream systems. The actual coding processes are complicated, too, involving half a dozen or more codeable components where each component has to be translated into an electronic health record (EHR) code from the doctor’s notes, which can be hard to read.
Faulty claims get denied by the payor, creating delays and leading to lost revenue for the provider, and in cases involving Medicare, the Office of the Inspector General may fight back against over-billing with lawsuits. Additionally, the American Medical Association issues hundreds of updates per year to their coding systems. Hiring a group of people to receive these documents and make updates to the EHR system or data warehouse by hand can cost hundreds of thousands of dollars and lead to denied or delayed claims and repayments.
Lexalytics Data Extraction Services solves these problems by automatically extracting, indexing and categorizing the complex coding data, enabling it to be inputted into the organization's EHR system or database.
Moreover, Lexalytics can go beyond just extraction and categorization. Lexalytics’ understanding of the underlying text through AI-based NLP allows it to analyze the newly-structured data, and do things such as create an intelligent recommendation system to help physicians prescribe the right treatments and give staff content-rich details about where a particular treatment code is applicable, when it’s reimbursable and how to bill for it.
Lexalytics Data Extraction Services can analyze and structure documents from formats including PDF, TXT, XML, HTML and Word, with export into standard ERP systems and Excel.
For more information, go to www.lexalytics.com/contact.