Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN.
Department of Health Sciences Research, Mayo Clinic, Rochester, MN.
J Arthroplasty. 2019 Oct;34(10):2216-2219. doi: 10.1016/j.arth.2019.07.025. Epub 2019 Jul 24.
Manual chart review is labor-intensive and requires specialized knowledge possessed by highly trained medical professionals. The cost and infrastructure challenges required to implement this is prohibitive for most hospitals. Natural language processing (NLP) tools are distinctive in their ability to extract critical information from unstructured text in the electronic health records. As a simple proof-of-concept for the potential application of NLP technology in total hip arthroplasty (THA), we examined its ability to identify periprosthetic femur fractures (PPFFx) followed by more complex Vancouver classification.
PPFFx were identified among all THAs performed at a single academic institution between 1998 and 2016. A randomly selected training cohort (1538 THAs with 89 PPFFx cases) was used to develop the prototype NLP algorithm and an additional randomly selected cohort (2982 THAs with 84 PPFFx cases) was used to further validate the algorithm. Keywords to identify, and subsequently classify, Vancouver type PPFFx about THA were defined. The gold standard was confirmed by experienced orthopedic surgeons using chart and radiographic review. The algorithm was applied to consult and operative notes to evaluate language used by surgeons as a means to predict the correct pathology in the absence of a listed, precise diagnosis. Given the variability inherent to fracture descriptions by different surgeons, an iterative process was used to improve the algorithm during the training phase following error identification. Validation statistics were calculated using manual chart review as the gold standard.
In distinguishing PPFFx, the NLP algorithm demonstrated 100% sensitivity and 99.8% specificity. Among 84 PPFFx test cases, the algorithm demonstrated 78.6% sensitivity and 94.8% specificity in determining the correct Vancouver classification.
NLP-enabled algorithms are a promising alternative to manual chart review for identifying THA outcomes. NLP algorithms applied to surgeon notes demonstrated excellent accuracy in delineating PPFFx, but accuracy was low for Vancouver classification subtype. This proof-of-concept study supports the use of NLP technology to extract THA-specific data elements from the unstructured text in electronic health records in an expeditious and cost-effective manner.
Level III.
人工图表审查是一项劳动密集型工作，需要由高度训练有素的医疗专业人员掌握专业知识。对于大多数医院来说，实施这一工作所需的成本和基础设施都是难以承受的。自然语言处理（NLP）工具在从电子健康记录中的非结构化文本中提取关键信息方面具有独特的优势。作为 NLP 技术在全髋关节置换术（THA）中应用的简单概念验证，我们研究了其识别假体周围股骨骨折（PPFFx）的能力，然后对更复杂的温哥华分类进行了研究。
在 1998 年至 2016 年期间，在一家学术机构中对所有进行的 THA 进行了 PPFFx 识别。一个随机选择的训练队列（1538 例 THA 中有 89 例 PPFFx 病例）用于开发原型 NLP 算法，另外一个随机选择的队列（2982 例 THA 中有 84 例 PPFFx 病例）用于进一步验证算法。定义了用于识别和随后分类 THA 相关温哥华类型 PPFFx 的关键字。通过经验丰富的骨科医生使用图表和放射学检查来确认金标准。该算法应用于会诊和手术记录，以评估外科医生使用的语言，以便在没有列出精确诊断的情况下预测正确的病理学。鉴于不同外科医生对骨折描述的固有差异，在训练阶段中使用迭代过程来识别错误，从而改进算法。使用手动图表审查作为金标准来计算验证统计数据。
在区分 PPFFx 方面，NLP 算法的灵敏度为 100%，特异性为 99.8%。在 84 例 PPFFx 测试病例中，该算法在确定正确的温哥华分类方面的灵敏度为 78.6%，特异性为 94.8%。
NLP 支持的算法是替代人工图表审查识别 THA 结果的有前途的方法。应用于外科医生记录的 NLP 算法在划定 PPFFx 方面具有出色的准确性，但在温哥华分类亚型方面准确性较低。这项概念验证研究支持使用 NLP 技术从电子健康记录中的非结构化文本中以快速且具有成本效益的方式提取特定于 THA 的数据元素。
III 级。
