Bhardwaj Aarti, Ramoni Rachel, Kalenderian Elsbeth, Neumann Ana, Hebballi Nutan B, White Joel M, McClellan Lyle, Walji Muhammad F
J Am Dent Assoc. 2016 Jan;147(1):35-40. doi: 10.1016/j.adaj.2015.06.023. Epub 2015 Nov 6.
Quality improvement requires using quality measures that can be implemented in a valid manner. Using guidelines set forth by the Meaningful Use portion of the Health Information Technology for Economic and Clinical Health Act, the authors assessed the feasibility and performance of an automated electronic Meaningful Use dental clinical quality measure to determine the percentage of children who received fluoride varnish.
The authors defined how to implement the automated measure queries in a dental electronic health record. Within records identified through automated query, the authors manually reviewed a subsample to assess the performance of the query.
The automated query results revealed that 71.0% of patients had fluoride varnish compared with the manual chart review results that indicated 77.6% of patients had fluoride varnish. The automated quality measure performance results indicated 90.5% sensitivity, 90.8% specificity, 96.9% positive predictive value, and 75.2% negative predictive value.
The authors' findings support the feasibility of using automated dental quality measure queries in the context of sufficient structured data. Information noted only in free text rather than in structured data would require using natural language processing approaches to effectively query electronic health records.
To participate in self-directed quality improvement, dental clinicians must embrace the accountability era. Commitment to quality will require enhanced documentation to support near-term automated calculation of quality measures.
质量改进需要采用能够有效实施的质量指标。作者依据《经济和临床健康的健康信息技术法案》中“有意义使用”部分所设定的指南,评估了一项自动化电子有意义使用牙科临床质量指标的可行性和性能,以确定接受氟化物涂漆的儿童比例。
作者定义了如何在牙科电子健康记录中实施自动化指标查询。在通过自动查询识别出的记录中,作者手动审查了一个子样本,以评估查询的性能。
自动查询结果显示,71.0%的患者接受了氟化物涂漆,而人工图表审查结果表明77.6%的患者接受了氟化物涂漆。自动化质量指标性能结果显示敏感性为90.5%,特异性为90.8%,阳性预测值为96.9%,阴性预测值为75.2%。
作者的研究结果支持在有足够结构化数据的情况下使用自动化牙科质量指标查询的可行性。仅在自由文本而非结构化数据中记录的信息,将需要使用自然语言处理方法来有效查询电子健康记录。
为了参与自主质量改进,牙科临床医生必须迎接问责时代。对质量的承诺将需要加强文档记录,以支持近期质量指标的自动化计算。