Worklist Prioritization: The Critical Element in Today’s CDI Operations

Worklist Prioritization: The Critical Element in Today’s CDI Operations

The past few years have been transformative for healthcare in the truest sense. From the rise of virtual care to big techs crafting innovative care delivery models, the healthcare industry has been witnessing some interesting shifts. Prodded by new programs and practices, the shift from fee-for-service reimbursement to value-based care has resulted in improved outcomes for patients, providers, and payers alike.

There’s no denying – the opportunity to enhance patient outcomes while reducing cost is driving the industry forward and instigating healthcare providers to modernize legacy practices. The push for improved performance and financial health, however, is also putting clinical documentation improvement (CDI) programs under intense pressure to ensure accurate documentation rightly that justifies medical necessity.

The situation has influenced healthcare providers to redesign their CDI programs by implementing new, methodologies and technologies that can help them prioritize workflows and focus closely on cases that have greatest quality and financial impact. Worklist prioritization is a critical objective for healthcare providers, especially at a time when the importance of CDI is growing fast. It allows specialists to prioritize top cases, spend less time and resources, and move quickly towards larger patient populations.  

Prioritization – Why is it Challenging Healthcare Providers?

Accurately capturing and documenting the patient conditions require dedicated clinical documentation improvement specialists (CDIS) with coding and clinical knowledge. Additionally, hospitals need to implement a process that enables detailed evaluation of patient reports on a regular basis. With new documentation and clinical evidence being added every hour, regular evaluation of the data is required to ensure that the medical records are thorough and accurate. In order to achieve this goal, the majority of CDI programs will have to increase the number of employees involved. Unfortunately, most healthcare providers lack the necessary resources or budget to train a large pool of staff.

To enhance the existing staff’s capability in identifying records that require improvement, CDI programs often implement several methods to classify a specific set of records to evaluate every day. There are programs that even attempt to prioritize worklists on the basis of clinical experience. In this case, specialists end up guesstimating the records that are likely to have documentation integrity concerns. Their decisions are often based on factors such as length of stay (LOS), chief complaint, list of providers with the past record of poor documentation habits, and so on.

While these methods may help CDI specialists gain control over the documentation process to some extent, they don’t actually address the underlying issues. The end result is often countless accurate charts being repeatedly reviewed and records with real documentation integrity issues being passed without appropriate correction or review.

How can Technology Create a Difference?

A solution that accurately identifies the discrepancies between clinical evidence and documentation would effectively address documentation prioritization issues. Doing so, however, requires additional focus on separate clinical data to identify probable conditions. While rule-based methods have already been attempted to simplify the process of extracting the right data, they often suffer from the false-positive/negative dilemma. Thankfully, cognitive technologies such as artificial intelligence provide CDI specialists a solution to this problem.

For instance, machine learning algorithms can analyze real-time patient data to accurately predict potential medical conditions. By identifying gaps between documentation and clinical evidence ML can create a catalog of prioritized patient records for CDI staff to evaluate. With this approach, CDI specialists can address some of the most pressing documentation concerns.

Halifax Regional Medical Center’s (HRMC) initiative to improve its financials with an AI-based Clinical Documentation Improvement software serves as an excellent example in this regard. The organization implemented a CDI program in 2014 which included manual processes that involved handwritten queries and query-tracking spreadsheets. Another critical issue was the encoder which wasn’t ICD-10-ready. As a result, the teams were experiencing issues with encoder speed and responsiveness, unnecessary downtime and connectivity issues between the EHR and the encoder.

In order to resolve the issues, Halifax collaborated with ezDI to deploy our full suite of NLP-technologies including total coding workflow automation with ezDI’s integrated computer-assisted coding application (CAC). The solution helped Halifax enhance its clinical documentation process with customized worklists, automated case distribution for CDI coders, missing document workflow creation and compressed revenue cycle.

As demonstrated in the case of Halifax, ezDI’s AI-based, born-in-the-cloud, fully integrated CDI software – ezCDI helps specialists develop worklists with a scope of improvements in documentation. The software’s customizable features allow it to cater to diverse CDI program needs. The application extracts clinical data in real-time provides code suggestions with clinical evidence and evaluates health records to identify incomplete, conflicting, or non-specific provider documentation, thereby streamlining the CDI process.

As CDI programs mature and start playing greater roles in helping organizations enhance code quality and documentation, the need to automate worklist prioritization cannot be overruled. After all, in order to drive revenues and meet quality standards, CDI specialists will have to take that leap from not knowing what’s in the record to identify the highest value cases quickly and efficiently.

To learn more about ezDI’s AI-based mid-revenue cycle management solutions visit www.ezDI.com and to see the live product demo of our Clinical Documentation, Coding, Compliance/Auditing, Quality Measures, Encoder, and Enterprise Analytics request a live demo.

Devanshu Yadav

Devanshu Yadav

Devanshu Yadav is a corporate strategist at ezDI Inc. He works for continuous advancement in bringing ezDI’s award-winning natural language processing (NLP) technology and comprehensive medical knowledge base to the market. He is considered as a subject matter expert in an emerging Healthcare AI driven technologies for mid revenue cycle management. He has contributed to the literature of healthcare professionals by engaging in numerous publications with HFMA. He is trusted & accomplished expert in intersection of technology, HIM, CDI and Coding, with a mission to set others up for success.

Devanshu has earned his post graduate degree in Business Administration and graduate degree in Electronics engineering. He is a firm believer in the abilities of technology to change the world, making the world a better place for all of us.

Subscribe to our Newsletter