M*Modal featured AnyModal CDS Live speech recognition software that captures and comprehends clinical information from dictation, during the 2008 HIMSS conference in Orlando, Fla.
AnyModal CDS Live works with existing hardware, on any computer and its ease of deployment enables small institutions, as well as large hospitals, to take advantage of increased productivity and control through physician self editing of more accurate, complete documents, Joel Fontaine, business development, M*Modal, told Health Imaging News.
“The overall goal of healthcare IT is to be able to get accurate information that is easily accessible and shareable from a patient physician exchange,” said Fontaine. “There has been progress made toward that and our technology allows the capturing of accurate and discrete data from structured narrative and the ability to deliver that into a variety of outputs including populating the medical record.”
Physicians can elect to self-edit and use the real-time service or via a back-end approach and send the drafts for editing by a medical language specialist. AnyModal CDS facilitates increased productivity and control through physician self-editing of more accurate, complete documents. M*Modal uses the software-as-a-service application delivery model, independently hosting, operating and maintaining its software application in an offsite data center for customer use over the internet. Additionally, the company uses modular, service-oriented architecture, which enables customers to build an infrastructure around AnyModal CDS Live for deep integration into existing healthcare IT.
Our goal is to be able to provide a process that would facilitate information from dictation to a variety of uses for the healthcare providers, he added. AnyModal CDS is a conversational documentation service that includes speech recognition and natural language processing and documentation process technology that captures a physician’s dictation and structures and encodes the content within the dictation and delivers that into a medical document or report.
“We do not just look at word accuracy but we are applying a comprehensive set of technologies to deliver a more accurate and complete document that understands the meaning and intent of the physician during dictation,” he said. “The physician does not change their speaking behavior and the technology adapts to them.” Fontaine added that the ability of the technology to structure and encode the data enables the delivery and validation of the content to a variety of modalities which can be provided in real-time.
M*Modal is not competing with any other vendors at the end-user level but instead is configuring in different ways with each of their partners, Fontaine said. “Our business model is to deeply integrate the technology with our partners, such as medical transcription companies and PACS/RIS companies, to offer an augmentation of their services based on our technology,” he said. “It is more about what they are delivering to the market with our technology inside.”
“We are kind of the off-ramp to the EMR because our ability to structure and encode the data flowing into an EMR,” he said.
Fontaine added that there was a general consensus during the show that direct data entry alone to deliver information to an EMR is not sufficient. “This hybrid of including a narrative or dictation to deliver some component of the information better conveys some of the subtleties of the patient-physician exchange since some content just can’t be delivered easily by direct data entry alone,” he said.
Over the next few years, Fontaine said the hope is to see structured narrative become an integral part of the clinician exchange of information through a multitude of devices including handhelds, PDAs and telephony, to ultimately help drive patient care and better healthcare practice.