Use Coding Clinic for ICD-10 insight

Coding tasks involving complex reasoning, such as those in which disparate pieces of information must be connected, are a difficult challenge for current NLP systems.—Kukafka et al.43, and also quoted in Stanfill et al.8. The coding hierarchy is clearly defined by the Official Guidelines for Coding and Reporting and within Coding Clinic (Fourth Quarter 2018, pages 90-91). However, it becomes confusing when Coding Clinic advice deviates from the Alphabetic Index and Tabular List. For example, the ICD-10-CM Index presumes a link between sepsis and organ dysfunction by the “with” sub-entry but this appears to conflict with Coding Clinic advice from Fourth Quarter 2017, pages , which instructs the link must be noted. +Due to the nature of the content being reviewed, we do not have an exact date that the on-demand session will be available.

• Clinical coding is a hospital or practice administration function that involves translating written clinical statements into coded data.
• The coding hierarchy is clearly defined by the Official Guidelines for Coding and Reporting and within Coding Clinic (Fourth Quarter 2018, pages 90-91).
• Even so, there is usually a backlog of cases to be coded, which can take several months or more (e.g., over a year14).
• Future deep learning-based systems need to integrate knowledge reasoning with rules and ontologies to achieve improved and more explainable results.
• Gloryanne Bryant reviews the guidance and updates coders on information in the AHA’s third quarter 2022 ICD-10-CM/PCS Coding Clinic in an easy to access on-demand webcast.
• This new guidance is illustrated with scenarios adapted to the home health and hospice setting.

Only since around ,32, deep learning has been applied to automated coding and there are abundant studies in this area (reflected in recent surveys11,12,13 and curation of papers in automated medical coding33). Unlike rule-based and traditional machine learning methods, pure deep learning methods do not require expert rules and hand-crafted textual features, thus easily applicable, while achieving better overall performance by learning from a sufficient amount of data32. Most of the studies formulate the task as a multi-label classification problem34, while some studies formulate the task as a concept extraction or a Named Entity Recognition and Linking (NER + L) problem35,36. Coding standard and guidelines have also not been leveraged to enhance deep learning, where a challenge would be the need to extract and represent the knowledge from them, which varies by locations and requires input from coding experts.

HCC Transition from V24 to V28 Webinar

We list the technical challenges from our work in clinical coding and suggest relevant references below. Some of the challenges are also presented in a different way in a recent, concurrent review in Teng et al.13. The challenges of explainability and few- and zero-shot learning are more relevant to the multi-label classification approach but may be alleviated by the NER + L approach. An empirical fact is that https://traderoom.info/how-to-use-gann-indicators/ the current BERT-based approaches still do not achieve better performance than CNN-based methods for multi-label classification applied to clinical coding44,60,61, except for the study52. The limitation of BERT may be due to its inefficiency in modelling concept-level information (usually represented in a few keywords or phrases instead of complex relations of tokens in the context) and long documents60.

Accuracy and consistency in morbidity coding are important in both clinical research and practice. However,Health Information Managers (HIMs) sometimes face difficulties in assigning morbidity codes. To assist them,the Korean Medical Record Association operates an online coding clinic bulletin board, on which HIMs can post questions and receive answers. Frequency analysis and Fisher’s exact testing were performed to identify differences among the types of questions posted and the characteristics of the HIMs who posted them. Through statistical analysis, it was found that HIMs working at hospitals with fewer than 500 beds and those with more than 10 years of work experience were found to post more questions than other HIMs.

Clinical Coding

Sign up for our monthly newsletter to download the reference sheet. Get timely coding industry updates, webinar notices, product discounts and special offers. Reviewing and understanding how to apply the newest codes ensures accurate reimbursement for the healthcare organization. Using an outdated code could result in a claim being denied and/or delayed payment. The corporatization of healthcare has changed the practice of medicine, causing many physicians to feel alienated from their work. MedTech company specializing in healthcare administration; mixing cutting edge technology and first-class service delivery.

Automated clinical coding systems also need to be tailored for different purposes (e.g., billing vs. health-related research) and contexts (e.g., countries). NER + L systems with rule-based inference can help improve the phenotyping when data are scarce to be used for supervised learning67,80. Automated coding systems can also be jointly designed with clinical outcome predictions (e.g., readmission and mortality) using deep learning in an end-to-end manner81. Also, case detection in some health-related research may favour precision (PPV) than recall (sensitivity) for evaluation82, which needs to be considered in building and tuning the automated coding system. In terms of other country-related factors, a known issue mentioned earlier in the US is “Note Bloat”, where content-importing shortcuts like copy-and-paste are used, which may reduce the time of documentation58. The “Note Bloat” phenomenon exacerbates the redundant entry of data in notes that is pulled in or copy-and-pasted from discrete places (e.g., various charts) in the Electronic Health Record (EHR).

Get the latest on healthcare leadership in your inbox.

None of the new procedures are identified as a diagnosis-related group operating room procedure under the Inpatient Prospective Payment System (IPPS) for hospital inpatient coding. Documentation is linked to clinical coding and understanding the coding rules will assist in knowing when to query. View our updated FAQ webpage to see if your webinar question has already been answered. I encourage you to read the Coding Clinic yourself, to discuss this with your peers, and to engage your compliance departments to assure that this official advice is followed.

• Coders should not be coding directly from the past medical history, past surgical history, family history, social history, or medication lists.
• A downside of NER + L-based coding is that it requires contextual understanding, i.e., the negation, temporality, and experiencer of the extracted concept or code35,65, which are not needed using the multi-label classification approach.
• This coding tip is intended to clear up any confusion regarding coding and reporting of secondary diagnoses on outpatient encounters.
• Reviewing and understanding how to apply the newest codes ensures accurate reimbursement for the healthcare organization.
• Ms. Bryant continues to advocate for compliant clinical documentation and data quality.
• With the growing number of studies and projects in academia and the industry, we look forward to seeing more advances in AI-assisted clinical coding in the next five years and beyond and its application into practice in the near future.

In 2019, data officially became more valuable than both oil and gas. Therefore, having an organised medical data library adds a value to both the data owner and the consumer. As clinical coding has gained more popularity during the COVID-19 pandemic in 2020, this field of medical science is set to bring more value to global health management systems.

Create a file for external citation management software

Training a model to fill codes to the charts needs to remove information from the notes (e.g., ICD codes) that is already present in the charts in the EHR. Also, it is shown that de-duplication of clinical notes improves the performance of prediction tasks, including predicting codes in the DRGs for billing58. More country related factors, e.g., billing and insurance, may also affect the system design and would warrant future studies.

How far are we from automated clinical coding that is human-centred, explainable, intelligent, and robust to complex real-world scenarios? We cannot give a concrete estimation, but it seems we now have a clearer path and a list of challenges to address. With the growing number of studies and projects in academia and the industry, we look forward to seeing more advances in AI-assisted clinical coding in the next five years and beyond and its application into practice in the near future.