The effort combines data automation technologies, human-centered design, and behavioral economics factors to drive more efficient and cost-effective processes to advance hospitals’ healthcare quality reporting capabilities.
CHICAGO, September 11, 2018 – Q-Centrix, a leading healthcare quality data solutions provider, is launching a new initiative focused on helping hospitals and their clinicians better manage the increasing demands associated with quality data reporting.
“As leaders in the quality data management market, we are acutely aware of the multi-dimensional challenges hospitals face with the increasing demands and burdens of quality data reporting,” said Brian Foy, Q-Centrix Chief Product Officer. “Hospitals are under tremendous cost and labor constraints as the industry transitions to a value-based care environment.”
Beyond the reporting requirements mandated by the Federal government and accrediting bodies, many hospitals are choosing to participate in quality initiatives that positively impact outcomes, patient safety, operational performance and reputation management. Compounding their quality data reporting challenges is the fact that unstructured clinical data is strewn across multiple information systems and that larger and more complex data sets are being required for quality reporting.
“This confluence of challenges is what we are attacking with our multi-pronged data management initiative,” said Foy. “Technology alone cannot solve this problem. Nor can one exclusively depend on clinical labor. In turn, we believe a holistic approach leveraging innovation across data automation, human design, and human behavior is the necessary breakthrough to help hospitals surmount these challenges and get ahead of meeting their quality reporting demands.”
The new initiative features the following solutions:
- Natural Language Processing
Q-Centrix is employing Natural Language Processing in its clinical data registry reporting solutions. By bundling the ability to process unstructured data, like clinical notes, with the human clinical expertise of more than 800 nurse-educated quality information specialists, the abstraction process will evolve to a more efficient, accurate and scalable process. Hospitals will have better data and be able to participate in more programs with fewer resources than before. NLP is a form of machine learning technology – meaning it is designed to understand human language and information patterns versus requiring data to be stored in a structured manner. Leveraging NLP in healthcare quality can dramatically reduce abstraction time since up to 80% of data in electronic medical records (EMRs) can be in unstructured formats. Initial results show collective improvements in data abstraction times. Q-Centrix is currently using NLP in its American College of Cardiology National Cardiovascular Data Registry solution with plans to expand to others if testing continues to show success.
- Behavioral Economics
The Q-Centrix data abstraction process now includes real-time prompts and messages for abstractors to improve accuracy and efficiency in data preparation. The approach is based on the emerging science of behavioral economics (BE). BE acknowledges that peoples’ decisions are subject to a variety of influences and biases. Guidance and encouragement can lead to making choices that best align with the desired outcome. Quality data abstraction is the process of collecting information from a patient’s medical record relevant to specific quality measures. Individuals who do this abstraction are continuously faced with decisions about what information to pull and how to organize it for submission. Thus, integrating BE factors into quality data management creates an opportunity to reach previously unattainable levels of efficiency and accuracy through continuous guidance and direction.
- Advanced User Interface
Q-Centrix has built an innovative user interface that provides abstractors with case-relevant information to guide data collection and preparation for quality program submission. This information appears in real time as a prompt or side pane within Q-Apps – the Q-Centrix quality reporting workflow management system. The approach provides abstractors with valuable information in a tool built exclusively for quality reporting and to mitigate the challenges of the process.
“Because we have spent the time and resources necessary to truly understand the barriers to modern quality reporting, we are able to address each of them in a strategic and systematic fashion,” said Foy. “Our approach started with building a technology platform that would be easy for hospital staffs to interface with but also could be supported by our team of experts. Then we focused on ensuring the process would be insusceptible to the common healthcare data interoperability issues. Finally, we introduced data automation via machine learning and NLP to advance efficiency beyond what anyone previously thought possible. The result has given us the confidence that we’re providing our hospital partners with the best possible opportunity to meet the ever-increasing challenges of quality improvement.”
Q-Centrix aims to measurably improve the quality and safety of patient care in the U.S. through the use of its market-leading technology platform, Q-Apps, that augments the clinical intelligence and efficiency of the industry’s largest and broadest team of nurse-educated, Quality Information Specialists. Processing in excess of 2 million quality data transactions annually, Q‑Centrix is a comprehensive quality partner to hundreds of hospitals, providing quality data management solutions, including quality data capture, surveillance, measure calculations, analysis, reporting, and improvement solutions. For more information about Q‑Centrix, visit www.q‑centrix.com.