Recent healthcare applications of natural language processing involve multi-label classification of health records using the International Classification of Diseases (ICD). While prior research highlights intricate te...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
Recent healthcare applications of natural language processing involve multi-label classification of health records using the International Classification of Diseases (ICD). While prior research highlights intricate text models and explores external knowledge like hierarchical ICD ontology, fewer studies integrate code relationships from whole datasets to enhance ICD coding accuracy. This study presents a modular approach, sequentially combining graph-based integration of ICD code co-occurrence with a hard-coded hierarchical-enriched text representation drawn from the ICD ontology. Findings reveal: 1) significant performance gains in the combined model, aside from the significant performance gain in each enhancement module in isolation, 2) graph-based module's efficacy is more pronounced when applied to enhanced features using the hierarchical ICD ontology, and 3) experiments demonstrate hierarchy depth's impact on performance, concluding the deepest level's enrichment.
Background: Information technology has the potential to streamline processes in healthcare for improved efficiency, quality and safety, while reducing costs. Computer-assisted clinicalcoding (CAC) has made it possibl...
详细信息
Background: Information technology has the potential to streamline processes in healthcare for improved efficiency, quality and safety, while reducing costs. Computer-assisted clinicalcoding (CAC) has made it possible to automate the clinicalcoding process by assigning diagnoses and procedures from electronic sources of clinical documentation. Implementation of CAC requires both investigation of the clinicalcoding workflow and exploration of how the clinicalcoding professional's role might change and evolve as a result of this technology. Objective: To examine the benefits and limitations of CAC technology;best practices for CAC adoption;the impact of CAC on traditional coding practices and roles in the inpatient setting. Method: This narrative review explores the current literature available on CAC. Literature indexed in ProQuest, Medline and other relevant sources between January 2006 and June 2017 was considered. Results: A total of 38 journal articles, published dissertations and case studies revealed that CAC has demonstrated value in improving clinicalcoding accuracy and quality, which can be missed during the manual clinicalcoding process. Conclusion: clinicalcoding professionals should view CAC as an opportunity not a threat. CAC will allow clinicalcoding professionals to further develop their clinicalcoding skills and knowledge for future career progression into new roles such as clinicalcoding editors and clinicalcoding analysts. Sound change management strategies are essential for successful restructuring of the clinicalcoding workflows during the implementation of CAC.
暂无评论