Natural Language Processing to extract SNOMED-CT codes from pathological reports.

IF 4.4 Q1 PATHOLOGY PATHOLOGICA Pub Date : 2023-12-01 DOI:10.32074/1591-951X-952
Giorgio Cazzaniga, Albino Eccher, Enrico Munari, Stefano Marletta, Emanuela Bonoldi, Vincenzo Della Mea, Moris Cadei, Marta Sbaraglia, Angela Guerriero, Angelo Paolo Dei Tos, Fabio Pagni, Vincenzo L'Imperio
{"title":"Natural Language Processing to extract SNOMED-CT codes from pathological reports.","authors":"Giorgio Cazzaniga, Albino Eccher, Enrico Munari, Stefano Marletta, Emanuela Bonoldi, Vincenzo Della Mea, Moris Cadei, Marta Sbaraglia, Angela Guerriero, Angelo Paolo Dei Tos, Fabio Pagni, Vincenzo L'Imperio","doi":"10.32074/1591-951X-952","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>The use of standardized structured reports (SSR) and suitable terminologies like SNOMED-CT can enhance data retrieval and analysis, fostering large-scale studies and collaboration. However, the still large prevalence of narrative reports in our laboratories warrants alternative and automated labeling approaches. In this project, natural language processing (NLP) methods were used to associate SNOMED-CT codes to structured and unstructured reports from an Italian Digital Pathology Department.</p><p><strong>Methods: </strong>Two NLP-based automatic coding systems (support vector machine, SVM, and long-short term memory, LSTM) were trained and applied to a series of narrative reports.</p><p><strong>Results: </strong>The 1163 cases were tested with both algorithms, showing good performances in terms of accuracy, precision, recall, and F1 score, with SVM showing slightly better performances as compared to LSTM (0.84, 0.87, 0.83, 0.82 vs 0.83, 0.85, 0.83, 0.82, respectively). The integration of an explainability allowed identification of terms and groups of words of importance, enabling fine-tuning, balancing semantic meaning and model performance.</p><p><strong>Conclusions: </strong>AI tools allow the automatic SNOMED-CT labeling of the pathology archives, providing a retrospective fix to the large lack of organization of narrative reports.</p>","PeriodicalId":45893,"journal":{"name":"PATHOLOGICA","volume":null,"pages":null},"PeriodicalIF":4.4000,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10767798/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"PATHOLOGICA","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.32074/1591-951X-952","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PATHOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Objective: The use of standardized structured reports (SSR) and suitable terminologies like SNOMED-CT can enhance data retrieval and analysis, fostering large-scale studies and collaboration. However, the still large prevalence of narrative reports in our laboratories warrants alternative and automated labeling approaches. In this project, natural language processing (NLP) methods were used to associate SNOMED-CT codes to structured and unstructured reports from an Italian Digital Pathology Department.

Methods: Two NLP-based automatic coding systems (support vector machine, SVM, and long-short term memory, LSTM) were trained and applied to a series of narrative reports.

Results: The 1163 cases were tested with both algorithms, showing good performances in terms of accuracy, precision, recall, and F1 score, with SVM showing slightly better performances as compared to LSTM (0.84, 0.87, 0.83, 0.82 vs 0.83, 0.85, 0.83, 0.82, respectively). The integration of an explainability allowed identification of terms and groups of words of importance, enabling fine-tuning, balancing semantic meaning and model performance.

Conclusions: AI tools allow the automatic SNOMED-CT labeling of the pathology archives, providing a retrospective fix to the large lack of organization of narrative reports.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用自然语言处理技术从病理报告中提取 SNOMED-CT 代码。
目的:使用标准化结构化报告(SSR)和 SNOMED-CT 等合适的术语可以加强数据检索和分析,促进大规模研究和合作。然而,在我们的实验室中,叙述性报告仍然非常普遍,因此需要采用替代性的自动标注方法。在这个项目中,我们使用自然语言处理(NLP)方法将 SNOMED-CT 代码与意大利数字病理部门的结构化和非结构化报告联系起来:对两个基于 NLP 的自动编码系统(支持向量机 SVM 和长短期记忆 LSTM)进行了训练,并将其应用于一系列叙述性报告:这两种算法对 1163 个案例进行了测试,在准确度、精确度、召回率和 F1 分数方面均表现良好,其中 SVM 的表现略优于 LSTM(分别为 0.84、0.87、0.83、0.82 vs 0.83、0.85、0.83、0.82)。通过整合可解释性,可以识别重要的术语和词组,从而进行微调,平衡语义和模型性能:人工智能工具可以对病理档案进行 SNOMED-CT 自动标注,从而解决了叙述性报告缺乏条理的问题。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
PATHOLOGICA
PATHOLOGICA PATHOLOGY-
CiteScore
5.90
自引率
5.70%
发文量
108
期刊最新文献
A case series of chorioangiomas in placentas with clinical indication for histological examination. A preliminary study on the diagnostic performance of the uPath PD-L1 (SP263) artificial intelligence (AI) algorithm in patients with NSCLC treated with PD-1/PD-L1 checkpoint blockade. Asbestos exposure diagnosis in pulmonary tissues. Colitis cystica profunda associated with diverticulosis and calcification mimicking colorectal carcinoma: a case report and a brief literature review. Digital transition in pathology lab: a survey from the Lombardy region.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1