Development of a text mining algorithm for identifying adverse drug reactions in electronic health records

Objective 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.Materials and Methods 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.Results 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.Discussion and Conclusion 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. The study addressed the challenge of identifying adverse drug reactions (ADRs) in the free-text notes of Dutch electronic health records (EHRs). ADRs are crucial to monitor because they can harm patients and increase healthcare costs. However, they are often documented in an unstructured manner, making it difficult for clinical decision support systems (CDSS) to detect them effectively. To address this, a text mining (TM) algorithm was developed using R programming to identify possible ADRs from these free-text notes. In the first phase, we improved and recoded the existing CDSS algorithm into the TM algorithm and tested it on a large dataset of 35 000 EHR notes. This new algorithm showed better performance in identifying ADRs compared to the old one, with a sensitivity of 86% and a positive predictive value (PPV) of 10%. In the second phase, additional text-mining scripts were used, which significantly improved the algorithm's accuracy. The final results showed a PPV of 70% and a sensitivity of 73%, indicating a substantial improvement in the algorithm's ability to detect ADRs. The study concludes that the new algorithm is effective in identifying ADRs from Dutch EHRs, highlighting its potential to enhance patient safety.