Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.
Currently value based care reporting is a very manual process where a human has to extract information from the EHRs manually and organize the data in a specified format and submit to the registry. Human processing is typically 5 charts an hour. The financial explorer with its automated processing does the same work at 500 charts / minute. This is an exponentially faster turn around time than human processing. This is a very tedious manual labor which is best suited for an automated tool rather than using highly accomplished humans. These workers are also hard to find as typically nurses like to work at the top of their license. The tool allows healthcare organizations to expand their coverage with no additional resources. It also allows organizations to analyze data from unstructured notes - which otherwise is not in a form that can be used for data analytics or machine learning.
Financial Explorer recently processed up to one million healthcare records in less than 24 hours. It would usually take hundreds of people weeks of work to achieve the same result. Speed of processing the records, accuracy and integration with EHRs are our superpowers. A study by UCSF a few years ago demonstrated 96.3% NLP accuracy of this tool - which has improved significantly over the years. https://online.boneandjoint.org.uk/doi/full/10.1302/0301-620X.102B7.BJJ-2019-1574.R1
STUDY BY USCF OF THE UNDERLYING TECHNOLOGY: A group of 1,000 randomly selected clinical and hospital notes from eight different surgeons were collected for patients undergoing primary arthroplasty between 2012 and 2018. In all, 19 preoperative, 17 operative, and two postoperative variables of interest were manually extracted from these notes. CloudMedx's NLP algorithm automatically extracted these variables from a training sample of these notes, and the algorithm was tested on a random test sample of notes. Results The NLP algorithm performed well at extracting variables from unstructured data in our random test dataset (accuracy = 96.3%, sensitivity = 95.2%, and specificity = 97.4%). It performed better at extracting data that were in a structured, templated format such as range of movement (ROM) (accuracy = 98%) and implant brand (accuracy = 98%) than data that were entered with variation depending on the author of the note such as the presence of deep-vein thrombosis (DVT) (accuracy = 90%). FINANCIAL EXPLORER DEPLOYMENT FOR MIPS REPORTING Case Study: CloudMedx deployed Financial Explorer to a healthcare group with over 5 locations. Their team was processing close to 1M patient records manually and it took them months to process. They wanted to expand their coverage to more locations but limited resources were limiting their capability to expand. CloudMedx processed those records in under a day (Human processing was 5 charts an hour, CloudMedx automated processing was 500 charts / minute). Turn-around documentation within 1 day and reporting within 3 days. This allows the organization to expand their coverage with no additional resources.