AI Integration in EHR-Based Pharmacovigilance: A Comparative Study of Germany and Egypt
Main Article Content
Keywords
pharmacovigilance, electronic healthcare records, electronic healthcare records-based pharmacovigilance, adverse drug reactions, artificial intelligence
Abstract
Introduction: Pharmacovigilance (PV) depends mainly on traditional reporting as a main source of data. This research will focus on another source, namely EHRs (electronic healthcare records). As we deal with big data from EHRs, AI (artificial intelligence) tools will be indispensable for the processing, and analysis of data and the early detection of ADRs (adverse drug reactions) from EHRs. In this research, we will explore the knowledge, attitudes and practices (KAPs) of the experts regarding the current application of AI in EHR-based PV, the potential benefits of implementing these technologies in PV, and the challenges toward their implementation in Germany and Egypt.
Methodology: A semi-structured survey of 30 questions that targeted the attitudes, knowledge and experience from PV experts (172 responses) was conducted.
Results: The results revealed that most PV companies in Egypt or Germany do not use EHRs as a main data source. This can be attributed to the lack of the application of EHRs in Germany and Egypt (e.g. EHRs in Germany is in a very early phase). Most of the PV organizations in both companies do not use AI as well in their PV activities. There is also a lack of proper adherence to data protection regulations in Egypt. However, the participants in both countries show a very positive attitude toward the adoption of AI and EHRs in the PV.
Conclusion: AI technologies and EHRS in the domain of PV are very rarely applied either separately or collectively in both countries, there is also a lack of knowledge among PV specialists about Digital Health but there are positive attitudes toward its adoption.
References
[2] Centers for Disease Control and Prevention (CDC). Adverse Drug Events in Adults | Medication Safety Program | CDC. CDC. 2023. https://www.cdc.gov/medication-safety/data-research/facts-stats/index.html. Accessed April 6, 2024.
[3] European Commission. Pharmacovigilance ‒ European Commission. European Union. 2024. https://health.ec.europa.eu/medicinal-products/pharmacovigilance_en. Accessed April 5, 2024.
[4] Cliniskills. Data Sources in Pharmacovigilance ‒ ClinSkill. Cliniskills Digital Learning Academy. 2023. https://www.clinskill.com/docs/data-sources-in-pharmacovigilance/. Accessed April 6, 2024.
[5] Trifirò G, Sultana J, Bate A. From Big Data to Smart Data for Pharmacovigilance: The Role of Healthcare Databases and Other Emerging Sources. Drug Safety. 2018;41(2):143‒149. https://doi.org/10.1007/S40264-017-0592-4/METRICS.
[6] Analytics P. Sources of data ‒ Pharmacovigilance Analytics. PHARMACOVIGILANCE ANALYTICS. 2018. https://www.pharmacovigilanceanalytics.com/pharmacovigilance-analytics/sources-of-data/. Accessed April 6, 2024.
[7] European Medicines Agency (EMA). Launch of new HMA-EMA catalogues of real-world data sources and studies | European Medicines Agency. EMA. 2024. https://www.ema.europa.eu/en/news/launch-new-hma-ema-catalogues-real-world-data-sources-studies. Accessed April 6, 2024.
[8] Yu Y, Ruddy KJ, Hong N, et al. ADEpedia-on-OHDSI: A next generation pharmacovigilance signal detection platform using the OHDSI common data model. Journal of Biomedical Informatics. 2019;91:103119. https://doi.org/10.1016/J.JBI.2019.103119.
[9] Salgado CM, Azevedo C, Proença H, Vieira SM. Noise versus outliers. InMIT Critical Data. Secondary Analysis of Electronic Health Records. Published online 2016:163-183.
[10] Sauzet O, Cornelius V. Generalised weibull model-based approaches to detect non-constant hazard to signal adverse drug reactions in longitudinal data. Frontiers in Pharmacology. 2022;13:13:889088. https://doi.org/10.3389/FPHAR.2022.889088.
[11] Davis SE, Zabotka L, Desai RJ, et al. Use of Electronic Health Record Data for Drug Safety Signal Identification: A Scoping Review. Drug Safety. 2023;46(8):725‒742. https://doi.org/10.1007/S40264-023-01325-0.
[12] Schuster N. Datenberge mit KI bewältigen. Pharmazeutische Zeitung. 2024;(6):18.
[13] Son N, Kim B, Chung S, Han S. Korean pharmacovigilance system based on EHR-CDM. Studies in Health Technology and Informatics. 2019;264:1592‒1593. https://doi.org/10.3233/SHTI190550.
[14] Bonomi S. The electronic health record: A comparison of some European countries. Lecture Notes in Information Systems and Organisation. 2016;15:33‒50. https://doi.org/10.1007/978-3-319-28907-6_3/COVER.
[15] Organisation for Economic Co-operation and Development (OECD). Digital health | Health at a Glance 2021 : OECD Indicators | OECD iLibrary. OECD iLibrary. 2019. https://www.oecd-ilibrary.org/sites/08cffda7-en/index.html?itemId=/content/component/08cffda7-en. Accessed March 23, 2024.
[16] Yu Y, Ruddy KJ, Wen A, et al. Integrating Electronic Health Record Data into the ADEpedia-on-OHDSI Platform for Improved Signal Detection: A Case Study of Immune-related Adverse Events. 2020;2020:710‒719.
[17] Food and Drug Administration (FDA). Questions and Answers on FDA’s Adverse Event Reporting System (FAERS) | FDA. FDA. 2019. https://www.fda.gov/drugs/surveillance/questions-and-answers-fdas-adverse-event-reporting-system-faers. Accessed December 3, 2023.
[18] Food and Drug Administration (FDA). FDA’s Sentinel Initiative | FDA. FDA. 2023. https://www.fda.gov/safety/fdas-sentinel-initiative. Accessed December 3, 2023.
[19] Douros A, Schaefer C, Kreutz R, Garbe E. Pharmakovigilanz in Deutschland: Es wird langsam Zeit. Internist. 2016;57(6):616‒623. https://doi.org/10.1007/S00108-016-0068-0.
[20] Gahr M, Eller J, Connemann BJ, Schönfeldt-Lecuona C. Underreporting of adverse drug reactions: Results from a survey among physicians. European Psychiatry. 2017;41(S1):S369. https://doi.org/10.1016/J.EURPSY.2017.02.377.
[21] ELkhwsky FS, El Sayed I, Yassine OGM, Abdelmonem S, Salama MM. Healthcare professionals’ knowledge and practice of and attitudes towards pharmacovigilance in Alexandria, Egypt: a cross-sectional survey. Drugs and Therapy Perspectives. 2021;37(3):124‒136. https://doi.org/10.1007/S40267-020-00798-8.
[22] Aziz AA, Rogers S, Hassanien O, Shalaby L, Nagy M. Knowledge, attitudes and practice regarding pharmacovigilance and adverse drug reaction reporting among physicians and pharmacists in Egypt: a step toward personalized medicine implementation. 2022;19(6):495‒507. https://doi.org/10.2217/PME-2022-0030.
[23] Kaeding M, Schmälter J, Klika C. Pharmacovigilance in the European Union. Practical Implementation across Member States; 2017. https://doi.org/10.1007/978-3-658-17276-3.
[24] Good Calculators. Sample Size Calculator | Good Calculators. Good Calculators. 2024. Accessed May 16, 2024. https://goodcalculators.com/sample-size-calculator/.
[25] Shah C. A Hands-on Introduction to Data Science. Cambridge University Press; 2020.
[26] Collingridge D. Validating a Questionnaire — Methodspace. Methodspace. 2022. https://www.methodspace.com/blog/validating-a-questionnaire. Accessed November 30, 2023.
[27] Bundesgesundheitsministerium (BGM). Driving the digital transformation of Germany’s healthcare system for the good of patients. BGM. 2020. https://www.bundesgesundheitsministerium.de/en/digital-healthcare-act. Accessed April 23, 2024.
[28] ALL About Pharma Covigilance. Understanding E2B | Pharmacovigilance. allaboutpharmacovigilance. 2021. https://allaboutpharmacovigilance.org/understanding-e2b/. Accessed April 1, 2024.
[29] CIOMS. Pharmacovigilance ‒ CIOMS. CIOMS. 2017. https://cioms.ch/pharmacovigilance/. Accessed April 1, 2024.
[30] Jagannatha AN, Yu H. Bidirectional RNN for medical event detection in electronic health records. 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 ‒ Proceedings of the Conference. Published online 2016:473‒482. https://doi.org/10.18653/v1/n16-1056.
[31] Lee S, Han J, Park RW, et al. Development of a Controlled Vocabulary-Based Adverse Drug Reaction Signal Dictionary for Multicenter Electronic Health Record-Based Pharmacovigilance. Drug Safety. 2019;42(5):657‒670. https://doi.org/10.1007/S40264-018-0767-7.
[32] Bundesgesundheitsministerium (BGM). Digital together. Germany’s Digitalisation Strategy for Health and Care. Federal Ministry of Health. 2022;2022(4):12-13.
[33] Mishra R, Ramesh D, Edla DR, Qi L. DS-Chain: A secure and auditable multi-cloud assisted EHR storage model on efficient deletable blockchain. Journal of Industrial Information Integration. 2022;26. https://doi.org/10.1016/j.jii.2021.100315.
[34] Hasan QH, Yassin AA, ATA O. Electronic Health Records System Using Blockchain Technology. Webology. 2021;18(Special Issue):580‒593. https://doi.org/10.14704/WEB/V18SI05/WEB18248.
[35] Evans J. EU stärkt EMA und Datenaustausch. Pharmazeutische Zeitung. 2023;(51‒52):16.
