Ontology-driven and weakly supervised rare disease identification from clinical notes.
Ontology-driven and weakly supervised rare disease identification from clinical notes.
复制标题
DOI：
10.1186/s12911-023-02181-9
复制
发表时间：
2023-05-05
影响因子：
3.5
通讯作者：
中科院分区：
文献类型：
--
作者：
计算文本表型是从临床记录中识别具有某些疾病和特征的患者的实践。罕见疾病的识别具有挑战性，因为可用于机器学习的病例很少，并且需要领域专家的数据注释。我们提出了一种使用本体和弱监督的方法，使用来自双向变压器（例如BERT）的最近预训练的上下文表示。本体驱动的框架包括两个步骤：（i）文本到UMLS，通过上下文链接提及到统一医学语言系统（UMLS）中的概念来提取表型，使用命名实体识别和链接（NER+L）工具SemEHR，以及具有自定义规则和上下文提及表示的弱监督;（ii）UMLS到ORDO，将UMLS概念与Orphanet Rare Disease Ontology（ORDO）中的罕见疾病匹配。弱监督的方法被提出来学习一个表型确认模型，以改善文本到UMLS的链接，没有来自领域专家的注释数据。我们评估了三个临床数据集，MIMIC-III出院总结，MIMIC-III放射学报告，NHS泰赛德脑成像报告，从美国和英国的两个机构，注释的方法。精确度的提高是显著的（文本到UMLS链接的绝对得分超过30%到50%），与现有的NER+L工具SemEHR相比，几乎没有召回损失。MIMIC-III和NHS Tayside的放射学报告结果与出院总结一致。处理临床记录的整个管道可以提取罕见疾病病例，这些病例大多未在结构化数据（手动分配的ICD代码）中捕获。该研究通过在临床笔记上应用弱监督NLP管道为任务提供了经验证据。所提出的弱监督深度学习方法不需要人工注释，除了验证和测试，通过利用本体，NER+L工具和上下文表示。该研究还表明，自然语言处理（NLP）可以补充传统的基于ICD的方法，以更好地估计临床记录中的罕见疾病。我们讨论了弱监督方法的有用性和局限性，并提出了未来研究的方向。在线版本包含补充材料，可通过10.1186/s12911-023-02181-9获得。
Computational text phenotyping is the practice of identifying patients with certain disorders and traits from clinical notes. Rare diseases are challenging to be identified due to few cases available for machine learning and the need for data annotation from domain experts. We propose a method using ontologies and weak supervision, with recent pre-trained contextual representations from Bi-directional Transformers (e.g. BERT). The ontology-driven framework includes two steps: (i) Text-to-UMLS, extracting phenotypes by contextually linking mentions to concepts in Unified Medical Language System (UMLS), with a Named Entity Recognition and Linking (NER+L) tool, SemEHR, and weak supervision with customised rules and contextual mention representation; (ii) UMLS-to-ORDO, matching UMLS concepts to rare diseases in Orphanet Rare Disease Ontology (ORDO). The weakly supervised approach is proposed to learn a phenotype confirmation model to improve Text-to-UMLS linking, without annotated data from domain experts. We evaluated the approach on three clinical datasets, MIMIC-III discharge summaries, MIMIC-III radiology reports, and NHS Tayside brain imaging reports from two institutions in the US and the UK, with annotations. The improvements in the precision were pronounced (by over 30% to 50% absolute score for Text-to-UMLS linking), with almost no loss of recall compared to the existing NER+L tool, SemEHR. Results on radiology reports from MIMIC-III and NHS Tayside were consistent with the discharge summaries. The overall pipeline processing clinical notes can extract rare disease cases, mostly uncaptured in structured data (manually assigned ICD codes). The study provides empirical evidence for the task by applying a weakly supervised NLP pipeline on clinical notes. The proposed weak supervised deep learning approach requires no human annotation except for validation and testing, by leveraging ontologies, NER+L tools, and contextual representations. The study also demonstrates that Natural Language Processing (NLP) can complement traditional ICD-based approaches to better estimate rare diseases in clinical notes. We discuss the usefulness and limitations of the weak supervision approach and propose directions for future studies. The online version contains supplementary material available at 10.1186/s12911-023-02181-9.
登录
查看更多内容
DOI：
10.1136/amiajnl-2013-001945
发表时间：
2013-12-01
影响因子：
6.4
作者：
Chen, Yukun;Carroll, Robert J.;Xu, Hua
通讯作者：
Xu, Hua
影响因子：
4.8
作者：
Cusick M;Adekkanattu P;Campion TR Jr;Sholle ET;Myers A;Banerjee S;Alexopoulos G;Wang Y;Pathak J
通讯作者：
Pathak J
影响因子：
16.6
作者：
Gibaja, Eva;Ventura, Sebastian
通讯作者：
Ventura, Sebastian
影响因子：
9.8
作者：
Johnson AE;Pollard TJ;Shen L;Lehman LW;Feng M;Ghassemi M;Moody B;Szolovits P;Celi LA;Mark RG
通讯作者：
Mark RG
影响因子：
1.9
作者：
Kersloot MG;van Putten FJP;Abu-Hanna A;Cornet R;Arts DL
通讯作者：
Arts DL