Pulse8 unveils machine learning for ICD-10
Healthcare analytics company Pulse8 is offering a tool to identify and code patient conditions by accessing content from their clinical data and converting it to XML schema for integration with a variety of systems.
Called Popul8, the software leverages machine learning, natural language processing as well as optical character and pattern recognition technologies to create what the company described as a data-driven view of healthcare processes.
"The goal is to reduce waste, eliminate unnecessary interventions, and improve patient and provider visibility by easily extracting clinical information from both structured and unstructured data," Pulse8 CEO John Criswell said.
Popul8 parses and processes XML schema with a 2-stage coding engine.
The first stage uses an ICD parser to discover conditions present in or implied by the chart and physician notes. The second stage uses natural language processing for heightened detection accuracy, while minimizing false-positive conditions.
As a result, the solution can identify, document and code conditions for which patients have been treated.
Popul8’s coding engine pre-populates charts for staff, and an “easy-flow” code entry screen integrates with automatic chart queuing to produce an efficient workflow, the company added.