Gérardin Christel, Mageau Arthur, Mékinian Arsène, Tannier Xavier, Carrat Fabrice
Institute Pierre Louis Epidemiology and Public Health, Institut National de la Santé et de la Recherche Médicale, Sorbonne Université, Paris, France.
Institut National de la Santé et de la Recherche Médicale, Unité Mixte de Recherche 1137 Infection Antimicrobials Modelling Evolution, Team Decision Sciences in Infectious Diseases, Université Paris Cité, Paris, France.
JMIR Med Inform. 2022 Dec 19;10(12):e42379. doi: 10.2196/42379.
Reliable and interpretable automatic extraction of clinical phenotypes from large electronic medical record databases remains a challenge, especially in a language other than English.
We aimed to provide an automated end-to-end extraction of cohorts of similar patients from electronic health records for systemic diseases.
Our multistep algorithm includes a named-entity recognition step, a multilabel classification using medical subject headings ontology, and the computation of patient similarity. A selection of cohorts of similar patients on a priori annotated phenotypes was performed. Six phenotypes were selected for their clinical significance: P1, osteoporosis; P2, nephritis in systemic erythematosus lupus; P3, interstitial lung disease in systemic sclerosis; P4, lung infection; P5, obstetric antiphospholipid syndrome; and P6, Takayasu arteritis. We used a training set of 151 clinical notes and an independent validation set of 256 clinical notes, with annotated phenotypes, both extracted from the Assistance Publique-Hôpitaux de Paris data warehouse. We evaluated the precision of the 3 patients closest to the index patient for each phenotype with precision-at-3 and recall and average precision.
For P1-P4, the precision-at-3 ranged from 0.85 (95% CI 0.75-0.95) to 0.99 (95% CI 0.98-1), the recall ranged from 0.53 (95% CI 0.50-0.55) to 0.83 (95% CI 0.81-0.84), and the average precision ranged from 0.58 (95% CI 0.54-0.62) to 0.88 (95% CI 0.85-0.90). P5-P6 phenotypes could not be analyzed due to the limited number of phenotypes.
Using a method close to clinical reasoning, we built a scalable and interpretable end-to-end algorithm for extracting cohorts of similar patients.
从大型电子病历数据库中可靠且可解释地自动提取临床表型仍然是一项挑战，尤其是在非英语语言环境中。
我们旨在从电子健康记录中为系统性疾病自动进行端到端的相似患者队列提取。
我们的多步骤算法包括一个命名实体识别步骤、使用医学主题词本体的多标签分类以及患者相似度计算。在预先注释的表型上进行相似患者队列的选择。选择了六种具有临床意义的表型：P1，骨质疏松症；P2，系统性红斑狼疮性肾炎；P3，系统性硬化症中的间质性肺疾病；P4，肺部感染；P5，产科抗磷脂综合征；以及P6，高安动脉炎。我们使用了一组包含151份临床记录的训练集和一组包含256份临床记录的独立验证集，两者均带有注释表型，这些数据均从巴黎公共救助医院数据仓库中提取。我们使用精确率@3、召回率和平均精确率评估了每种表型中最接近索引患者的3名患者的精确率。
对于P1 - P4，精确率@3范围为0.85（95%置信区间0.75 - 0.95）至0.99（95%置信区间0.98 - 1），召回率范围为0.53（95%置信区间0.50 - 0.55）至0.83（95%置信区间0.81 - 0.84），平均精确率范围为0.58（95%置信区间0.54 - 0.62）至0.88（95%置信区间0.85 - 0.90）。由于表型数量有限，P5 - P6表型无法进行分析。
通过使用一种接近临床推理的方法，我们构建了一种可扩展且可解释的端到端算法，用于提取相似患者队列。
