自然语言处理方法从电子健康记录中提取结石成分的性能
研究开发了StoneX模式匹配算法,从机构电子健康记录中提取肾结石成分信息,在草酸钙一水合物、草酸钙二水合物、羟基磷灰石、透钙磷石和鸟粪石上阳性预测值均超过90%,尿酸为87.5%;算法识别出对应11,585例患者的45,235条文本提及,并复现了结石类型与疾病的已知关联。
要点
- StoneX算法从电子健康记录中提取肾结石成分,多数成分阳性预测值超过90%。
- 算法识别出对应11,585例患者的45,235条文本提及。
- 尿酸结石成分的阳性预测值为87.5%。
核心结论
- 从大规模电子健康记录中自然语言处理提取肾结石成分是可行的且具有高精度,可实现肾结石疾病的高通量流行病学研究。
- 这些工具将使得从电子健康记录中进行高保真肾结石研究成为可能。
研究设计与样本
- 研究开发了StoneX,一种用于从临床笔记中提取肾结石成分信息的模式匹配方法。
- 在人工标注的草酸钙一水合物、草酸钙二水合物、羟基磷灰石、透钙磷石、尿酸和鸟粪石文本提及上训练提取算法。
- 对提取的患者进行分析,包括结石类型随时间的变化、从第二次结石手术开始的生存分析,以及按结石成分的疾病关联,以验证表型分析方法与已知关联的一致性。
主要发现
- 自然语言处理算法识别出45,235条文本提及,对应11,585例患者。
- 系统对草酸钙一水合物、草酸钙二水合物、羟基磷灰石、透钙磷石和鸟粪石的阳性预测值超过90%,尿酸除外(阳性预测值=87.5%)。
- 从第二次结石手术开始的生存分析显示结石类型间差异有统计学意义(P=0.03)。
- 发现尿酸-2型糖尿病(比值比,OR=2.69,95%置信区间,CI=1.91-3.79)、鸟粪石-神经源性膀胱(OR=12.27,95%CI=4.33-34.79)、鸟粪石-尿路感染(OR=7.36,95%CI=3.01-17.99)、羟基磷灰石-肺不张(OR=3.67,95%CI=2.10-6.42)、羟基磷灰石-神经源性膀胱(OR=5.23,95%CI=2.05-13.36)、透钙磷石-钙代谢紊乱(OR=4.59,95%CI=2.14-9.81)和透钙磷石-高钙血症(OR=4.09,95%CI=1.90-8.80)等表型关联。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVES: To demonstrate the utility of a natural language processing (NLP) algorithm for mining kidney stone composition in a large-scale electronic health records (EHR) repository. METHODS: We developed StoneX, a pattern-matching method for extracting kidney stone composition information from clinical notes. We trained the extraction algorithm on manually annotated text mentions of calcium oxalate monohydrate, calcium oxalate dihydrate, hydroxyapatite, brushite, uric acid, and struvite stones. We employed StoneX to identify patients with kidney stone composition data and mine >125 million notes from our institutional EHR. Analyses performed on the extracted patients included stone type conversions over time, survival analysis from a second stone surgery, and disease associations by stone composition to validate the phenotyping method against known associations. RESULTS: The NLP algorithm identified 45,235 text mentions corresponding to 11,585 patients. Overall, the system achieved positive predictive value >90% for calcium oxalate monohydrate, calcium oxalate dihydrate, hydroxyapatite, brushite, and struvite; except for uric acid (positive predictive value = 87.5%). Survival analysis from a second stone surgery showed statistically significant differences among stone types (P = .03). Several phenotype associations were found: uric acid-type 2 diabetes (odds ratio, OR = 2.69, 95% confidence intervals, CI = 1.91-3.79), struvite-neurogenic bladder (OR = 12.27, 95% CI = 4.33-34.79), struvite-urinary tract infection (OR = 7.36, 95% CI = 3.01-17.99), hydroxyapatite-pulmonary collapse (OR = 3.67, 95% CI = 2.10-6.42), hydroxyapatite-neurogenic bladder (OR = 5.23, 95% CI = 2.05-13.36), brushite-calcium metabolism disorder (OR = 4.59, 95% CI = 2.14-9.81), and brushite-hypercalcemia (OR = 4.09, 95% CI = 1.90-8.80). CONCLUSION: NLP extraction of kidney stone composition from large-scale EHRs is feasible with high precision, enabling high-throughput epidemiological studies of kidney stone disease. These tools will enable high fidelity kidney stone research from the EHR.
引用
- Bejan CA, Lee DJ, Xu Y, et al. Performance of a Natural Language Processing Method to Extract Stone Composition From the Electronic Health Record. Urology. 2019. PMID: 31310771. doi:10.1016/j.urology.2019.07.007
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。