van de Burgt Britt W M, Wasylewicz Arthur T M, Dullemond Bjorn, Jessurun Naomi T, Grouls Rene J E, Bouwman R Arthur, Korsten Erik H M, Egberts Toine C G
Division of Clinical Pharmacy, Catharina Hospital Eindhoven, 5623 EJ Eindhoven, The Netherlands.
Division Healthcare Intelligence, Catharina Hospital Eindhoven, 5623 EJ Eindhoven, The Netherlands.
JAMIA Open. 2024 Aug 16;7(3):ooae070. doi: 10.1093/jamiaopen/ooae070. eCollection 2024 Oct.
Adverse drug reactions (ADRs) are a significant healthcare concern. They are often documented as free text in electronic health records (EHRs), making them challenging to use in clinical decision support systems (CDSS). The study aimed to develop a text mining algorithm to identify ADRs in free text of Dutch EHRs.
In Phase I, our previously developed CDSS algorithm was recoded and improved upon with the same relatively large dataset of 35 000 notes (Step A), using R to identify possible ADRs with Medical Dictionary for Regulatory Activities (MedDRA) terms and the related Systematized Nomenclature of Medicine Clinical Terms (SNOMED-CT) (Step B). In Phase II, 6 existing text-mining R-scripts were used to detect and present unique ADRs, and positive predictive value (PPV) and sensitivity were observed.
In Phase IA, the recoded algorithm performed better than the previously developed CDSS algorithm, resulting in a PPV of 13% and a sensitivity of 93%. For The sensitivity for serious ADRs was 95%. The algorithm identified 58 additional possible ADRs. In Phase IB, the algorithm achieved a PPV of 10%, a sensitivity of 86%, and an F-measure of 0.18. In Phase II, four R-scripts enhanced the sensitivity and PPV of the algorithm, resulting in a PPV of 70%, a sensitivity of 73%, an F-measure of 0.71, and a 63% sensitivity for serious ADRs.
The recoded Dutch algorithm effectively identifies ADRs from free-text Dutch EHRs using R-scripts and MedDRA/SNOMED-CT. The study details its limitations, highlighting the algorithm's potential and significant improvements.
药物不良反应（ADR）是医疗保健领域的一个重大问题。它们在电子健康记录（EHR）中通常以自由文本形式记录，这使得它们在临床决策支持系统（CDSS）中难以使用。本研究旨在开发一种文本挖掘算法，以识别荷兰EHR自由文本中的ADR。
在第一阶段，我们使用相同的包含35000条记录的相对较大的数据集，对之前开发的CDSS算法进行重新编码和改进（步骤A），使用R语言通过《药品监管活动医学词典》（MedDRA）术语和相关的《医学临床术语系统命名法》（SNOMED-CT）来识别可能的ADR（步骤B）。在第二阶段，使用6个现有的文本挖掘R脚本检测并呈现独特的ADR，并观察阳性预测值（PPV）和敏感性。
在第一阶段A，重新编码的算法比之前开发的CDSS算法表现更好，PPV为13%，敏感性为93%。严重ADR的敏感性为95%。该算法识别出另外58个可能的ADR。在第一阶段B，该算法的PPV为10%，敏感性为86%，F值为0.18。在第二阶段，四个R脚本提高了算法的敏感性和PPV，PPV为70%，敏感性为73%，F值为0.71，严重ADR的敏感性为63%。
重新编码的荷兰算法使用R脚本和MedDRA/SNOMED-CT有效地从荷兰EHR自由文本中识别ADR。该研究详细说明了其局限性，突出了算法的潜力和显著改进。
