DQA Platform

The most powerful Coding Assistance and Data Quality platform available

DQA uses world-class clinical Artificial Intelligence to streamline your medical coding process and detect data quality errors that impact hospital funding

The DQA Platform

DQA is a set of specialized software tools used by leading hospitals to optimize their clinical coding processes. This year, over 45% of all medical abstracts in Ontario will be processed by DQA.

DQA is implemented within a week and immediately increases efficiency and data quality during initial coding. It also provides an automated audit engine that identifies the potential problems that directly affect funding.

Uses industry leading AI to parse clinical text and help identify medical codes
Comprehensive access to both structured and semi-structured encounter data
Ability to easily integrate new data sources
Refined user interface designed to minimize review time and cognitive fatigue
Short implementation time and low risk
Automated abstract review with 100% case coverage
Prioritization of data quality issues by probability of error and CMI impact
Flexible data quality engine for adding new rules
Case-level detailed tracking of errors and corrections
Re-audits cases when data is added or modified
Detailed analytics including funding impact and DQ root cause analysis
Canadian and Provincial methodologies (HIG, QBPs) and rules built-in

Effectively introducing technology into the medical coding process requires a multifaceted approach. It’s important to know the different tools and techniques used to accomplish these goals.

Data integration

Without a data compilation strategy, it is simply not possible for clinical coders and automated systems to be fully effective.

Any robust coding solution needs to include a frictionless way of introducing new structured and unstructured data into the process without requiring substantial technical integration effort or customization from vendors. This includes automated EMR data feeds (HL7/FHIR), clinical note repositories, data warehouses, and even spreadsheets of manually compiled data.

Hospitals need to be able to easily bring in their own data without external vendor assistance, therefore DQA was designed from the outset with data integration in mind. The platform includes data interfaces that allow hospitals to import new data sources themselves.

Artificial Intelligence

The recent availability of world class clinical AI engines have opened up limitless new opportunities in healthcare. DQA utilizes sophisticated commercial clinical NLP engines to translate clinical text into a semi-structured data format. Improving the coding process is one of many practical applications for this AI interpreted clinical text.

In addition to integrating this world-class clinical NLP, we’ve spent over five years developing a library of machine learning algorithms and data quality rules to target specific coding issues where translated medical text is insufficient. Flexibility in creating new data quality rules has been a key driver of DQA’s success. We often say DQA was built by coders across the province because, in many ways, it was. The flexible rule engine has allowed us to integrate new intelligence rapidly based on techniques and approaches proven by Health Records departments across many hospitals. This also ensured that rules specific to Canadian and Ontario coding were properly represented in the platform.

Coding assistance tools

Coders need to access and digest a large amount of data from different information systems when coding patient encounters. It is often not even possible to gather the necessary information from all relevant data sources across the hospital. Without the proper tools, clinical coding can become a highly labor-intensive investigative exercise.

Compilation of data has always been a key part of the DQA data quality audit process, and this data is now available to the coders at the time of coding to improve baseline data quality.

To help improve the efficiency of your coding team, we provide a unified user interface of all structured and AI-interpreted clinical notes. These tools help you consume data faster as well as reduce cognitive fatigue through visualization techniques such as highlighting and color coding. The AI also immediately identifies and labels coded elements such as diagnostic and procedural codes to reduce lookup time.

Automated coding audits

Despite best efforts, mistakes are often made during the documentation and coding process. Given the impact to funding, research, and other initiatives that rely on clean coded data, hospitals must try to be as accurate as possible in their medical abstracts.

Automated case auditing has been a staple of the DQA platform since its first release in 2015. With the help of over 50 hospitals, we’ve designed case profiling logic that uses a variety of statistical and machine learning techniques to automatically detect potential errors within your coded abstracts.

The automated audit engine takes full advantage of all integrated data, Artificial Intelligence, and data quality rules within our platform. The data quality reports that are generated also prioritize case review that direct medical coders to the highest probability, highest value data quality errors. We know that coding resources are both valuable and limited so we’ve designed DQA to maximize the value of the audit review and correction process.

Regional factors

It is critical to account for factors pertaining to Canadian coding standards and provincial policies that affect hospital funding, quality improvement initiatives, and accountability agreements. In addition to national standards such as CIHI CMG+, there are policies that depend on provincial methodologies such as HIG and Quality Based Procedures (QBPs).

Certain data points within coded medical records have specific implications in terms of funding and performance indicators of key interest for hospitals. These regional specific rules and calculations are deeply integrated within DQA to ensure that proper attention is paid to the factors that have the most impact on your hospital.

Efficiency and insight

DQA includes a growing set of additional features within the platform:

Collaboration tools that support the case review process including centralized case notes and workflow assignment to team members involved in the review process.
Effectiveness monitoring that include the tracking of detailed statistics on coding efficiency and audit corrections. This allows hospitals to directly calculate the impact of their DQA investment.
Root cause analysis through the use of analytical reporting to identify repeated systematic issues that can be remedied by changes in process or coder/physician education.
Reports and analytics to help explain year-over-year variations in patient volume and CMI. Finance teams need to understand the underlying root causes for volume and weight change beyond data quality factors, including variation in long stay cases and aggregate complexity effects from changes to patient case mix.

DQA has been successfully used by leading Ontario hospitals to improve their data quality, using the best ideas from clinical coders across the province.

For more information about implementing the DQA platform, please contact us.