{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T13:08:57Z","timestamp":1773666537004,"version":"3.50.1"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006752","name":"Universidade do Porto","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006752","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Clin Pharm"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Artificial intelligence (AI), particularly machine learning (ML), is increasingly influencing pharmacovigilance (PV) by improving case triage and signal detection. Several studies have reported encouraging performance, with high F1 scores and alignment with expert assessments, suggesting that AI tools can help prioritize reports and identify potential safety issues faster than manual review. However, integrating these tools into PV raises concerns. Most models are designed for prediction, not explanation, and operate as \u201cblack boxes,\u201d offering limited insight into how decisions are made. This lack of transparency may undermine trust and clinical utility, especially in a domain where causality is central. Traditional ML relies on correlational patterns and may amplify biases inherent in spontaneous reporting systems, such as under-reporting, missing data, and confounding. Recent developments in explainable AI (XAI) and causal AI aim to address these issues by offering more interpretable and causally meaningful outputs, but their use in PV remains limited. These methods face challenges, including the need for robust data, the difficulty of defining ground truth for adverse drug reactions (ADRs), and the lack of standard validation frameworks. In this commentary, we explore the promise and pitfalls of AI in PV and argue for a shift toward causally informed, interpretable models grounded in epidemiological reasoning. We identify four priorities: incorporating causal inference into AI workflows; developing benchmark datasets to support transparent evaluation; ensuring model outputs align with clinical and regulatory logic; and upholding rigorous validation standards. The goal is not to replace expert judgment, but to enhance it with tools that are more transparent, reliable, and capable of separating true signals from noise. Moving toward explainable and causally robust AI is essential to ensure that its application in pharmacovigilance is both scientifically credible and ethically sound.<\/jats:p>","DOI":"10.1007\/s11096-025-02004-z","type":"journal-article","created":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T11:41:40Z","timestamp":1756726900000},"page":"677-681","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Beyond black boxes: using explainable causal artificial intelligence to separate signal from noise in pharmacovigilance"],"prefix":"10.1007","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6517-6021","authenticated-orcid":false,"given":"Renato","family":"Ferreira-da-Silva","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3764-5158","authenticated-orcid":false,"given":"Ricardo","family":"Cruz-Correia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3442-8158","authenticated-orcid":false,"given":"In\u00eas","family":"Ribeiro","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,1]]},"reference":[{"key":"2004_CR1","unstructured":"European European Medicines Agency. Guideline on good pharmacovigilance practices (GVP). Annex I \u2013 Definitions (Rev 4). London: EMA; 2017."},{"issue":"2","key":"2004_CR2","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1056\/NEJMsa2206117","volume":"388","author":"DW Bates","year":"2023","unstructured":"Bates DW, Levine DM, Salmasian H, et al. The safety of inpatient health care. N Engl J Med. 2023;388(2):142\u201353. https:\/\/doi.org\/10.1056\/NEJMsa2206117.","journal-title":"N Engl J Med"},{"issue":"5","key":"2004_CR3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0252161","volume":"16","author":"WN Insani","year":"2021","unstructured":"Insani WN, Whittlesea C, Alwafi H. Prevalence of adverse drug reactions in the primary care setting: a systematic review and meta-analysis. PLoS ONE. 2021;16(5): e0252161. https:\/\/doi.org\/10.1371\/journal.pone.0252161.","journal-title":"PLoS ONE"},{"issue":"4","key":"2004_CR4","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1001\/jama.1997.03540280039031","volume":"277","author":"DC Classen","year":"1997","unstructured":"Classen DC, Pestotnik SL, Evans RS, et al. Adverse drug events in hospitalized patients. Excess length of stay, extra costs, and attributable mortality. JAMA. 1997;277(4):301\u20136.","journal-title":"JAMA"},{"issue":"1","key":"2004_CR5","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1002\/cpt.1689","volume":"107","author":"P Arlett","year":"2020","unstructured":"Arlett P, Straus S, Rasi G. Pharmacovigilance 2030: Invited commentary for the January 2020 \u201cfutures\u201d edition of clinical pharmacology and therapeutics. Clin Pharmacol Ther. 2020;107(1):89\u201391. https:\/\/doi.org\/10.1002\/cpt.1689.","journal-title":"Clin Pharmacol Ther"},{"issue":"10","key":"2004_CR6","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/s40264-017-0571-9","volume":"40","author":"IR Edwards","year":"2017","unstructured":"Edwards IR. A new erice report considering the safety of medicines in the 21st century. Drug Saf. 2017;40(10):845\u20139. https:\/\/doi.org\/10.1007\/s40264-017-0571-9.","journal-title":"Drug Saf"},{"issue":"1","key":"2004_CR7","doi-asserted-by":"publisher","first-page":"21","DOI":"10.2165\/00002018-200831010-00003","volume":"31","author":"TB Agbabiaka","year":"2008","unstructured":"Agbabiaka TB, Savovic J, Ernst E. Methods for causality assessment of adverse drug reactions: a systematic review. Drug Saf. 2008;31(1):21\u201337. https:\/\/doi.org\/10.2165\/00002018-200831010-00003.","journal-title":"Drug Saf"},{"issue":"2","key":"2004_CR8","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1038\/clpt.1981.154","volume":"30","author":"CA Naranjo","year":"1981","unstructured":"Naranjo CA, Busto U, Sellers EM, et al. A method for estimating the probability of adverse drug reactions. Clin Pharmacol Ther. 1981;30(2):239\u201345. https:\/\/doi.org\/10.1038\/clpt.1981.154.","journal-title":"Clin Pharmacol Ther"},{"issue":"5","key":"2004_CR9","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1177\/003591576505800503","volume":"58","author":"AB Hill","year":"1965","unstructured":"Hill AB. The environment and disease: association or causation? Proc R Soc Med. 1965;58(5):295\u2013300. https:\/\/doi.org\/10.1177\/003591576505800503.","journal-title":"Proc R Soc Med"},{"key":"2004_CR10","doi-asserted-by":"publisher","DOI":"10.51126\/revsalus.v4i2.466","author":"R Ferreira da Silva","year":"2022","unstructured":"Ferreira da Silva R. Causality assessment in pharmacovigilance: principles and fundamentals of causal inference. RevSALUS - Revista Cient\u00edfica da Rede Acad\u00e9mica das Ci\u00eancias da Sa\u00fade da Lusofonia. 2022. https:\/\/doi.org\/10.51126\/revsalus.v4i2.466.","journal-title":"RevSALUS - Revista Cient\u00edfica da Rede Acad\u00e9mica das Ci\u00eancias da Sa\u00fade da Lusofonia"},{"key":"2004_CR11","doi-asserted-by":"publisher","DOI":"10.2196\/57824","volume":"26","author":"S Dimitsaki","year":"2024","unstructured":"Dimitsaki S, Natsiavas P, Jaulent MC. Applying AI to structured real-world data for pharmacovigilance purposes: scoping review. J Med Internet Res. 2024;26: e57824. https:\/\/doi.org\/10.2196\/57824.","journal-title":"J Med Internet Res"},{"key":"2004_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104517","volume":"135","author":"K Kreimeyer","year":"2021","unstructured":"Kreimeyer K, Dang O, Spiker J, et al. Feature engineering and machine learning for causality assessment in pharmacovigilance: lessons learned from application to the FDA Adverse Event Reporting System. Comput Biol Med. 2021;135: 104517. https:\/\/doi.org\/10.1016\/j.compbiomed.2021.104517.","journal-title":"Comput Biol Med"},{"issue":"5","key":"2004_CR13","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1007\/s40264-022-01163-6","volume":"45","author":"Y Cherkas","year":"2022","unstructured":"Cherkas Y, Ide J, van Stekelenborg J. Leveraging machine learning to facilitate individual case causality assessment of adverse drug reactions. Drug Saf. 2022;45(5):571\u201382. https:\/\/doi.org\/10.1007\/s40264-022-01163-6.","journal-title":"Drug Saf"},{"issue":"5","key":"2004_CR14","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/s40264-022-01155-6","volume":"45","author":"Y Zhao","year":"2022","unstructured":"Zhao Y, Yu Y, Wang H, et al. Machine learning in causal inference: application in pharmacovigilance. Drug Saf. 2022;45(5):459\u201376. https:\/\/doi.org\/10.1007\/s40264-022-01155-6.","journal-title":"Drug Saf"},{"issue":"4","key":"2004_CR15","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s002280050466","volume":"54","author":"A Bate","year":"1998","unstructured":"Bate A, Lindquist M, Edwards IR, et al. A Bayesian neural network method for adverse drug reaction signal generation. Eur J Clin Pharmacol. 1998;54(4):315\u201321. https:\/\/doi.org\/10.1007\/s002280050466.","journal-title":"Eur J Clin Pharmacol"},{"issue":"3","key":"2004_CR16","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/s10618-009-0152-3","volume":"20","author":"GN Nor\u00e9n","year":"2009","unstructured":"Nor\u00e9n GN, Hopstadius J, Bate A, et al. Temporal pattern discovery in longitudinal electronic patient records. Data Min Knowl Discovery. 2009;20(3):361\u201387. https:\/\/doi.org\/10.1007\/s10618-009-0152-3.","journal-title":"Data Min Knowl Discovery"},{"key":"2004_CR17","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"A Barredo Arrieta","year":"2020","unstructured":"Barredo Arrieta A, D\u00edaz-Rodr\u00edguez N, Del Ser J, et al. Explainable Artificial Intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inform Fusion. 2020;58:82\u2013115. https:\/\/doi.org\/10.1016\/j.inffus.2019.12.012.","journal-title":"Inform Fusion"},{"issue":"2","key":"2004_CR18","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/s13218-020-00636-z","volume":"34","author":"A Holzinger","year":"2020","unstructured":"Holzinger A, Carrington A, Muller H. Measuring the quality of explanations: the system causability scale (SCS): comparing human and machine explanations. Kunstliche Intell (Oldenbourg). 2020;34(2):193\u20138. https:\/\/doi.org\/10.1007\/s13218-020-00636-z.","journal-title":"Kunstliche Intell (Oldenbourg)"},{"issue":"4","key":"2004_CR19","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1312","volume":"9","author":"A Holzinger","year":"2019","unstructured":"Holzinger A, Langs G, Denk H, et al. Causability and explainability of artificial intelligence in medicine. WIREs Data Min Knowl Discov. 2019;9(4):e1312. https:\/\/doi.org\/10.1002\/widm.1312.","journal-title":"WIREs Data Min Knowl Discov"},{"issue":"11","key":"2004_CR20","doi-asserted-by":"publisher","first-page":"e745","DOI":"10.1016\/S2589-7500(21)00208-9","volume":"3","author":"M Ghassemi","year":"2021","unstructured":"Ghassemi M, Oakden-Rayner L, Beam AL. The false hope of current approaches to explainable artificial intelligence in health care. Lancet Digit Health. 2021;3(11):e745\u201350. https:\/\/doi.org\/10.1016\/S2589-7500(21)00208-9.","journal-title":"Lancet Digit Health"},{"key":"2004_CR21","doi-asserted-by":"publisher","first-page":"659622","DOI":"10.3389\/frai.2021.659622","volume":"4","author":"X Wang","year":"2021","unstructured":"Wang X, Xu X, Tong W, et al. InferBERT: A transformer-based causal inference framework for enhancing pharmacovigilance. Front Artif Intell. 2021;4:659622. https:\/\/doi.org\/10.3389\/frai.2021.659622.","journal-title":"Front Artif Intell."},{"key":"2004_CR22","doi-asserted-by":"publisher","first-page":"803","DOI":"10.3233\/SHTI240533","volume":"316","author":"S Dimitsaki","year":"2024","unstructured":"Dimitsaki S, Natsiavas P, Jaulent MC. Causal deep learning for the detection of adverse drug reactions: drug-induced acute kidney injury as a case study. Stud Health Technol Inform. 2024;316:803\u20137. https:\/\/doi.org\/10.3233\/SHTI240533.","journal-title":"Stud Health Technol Inform"}],"container-title":["International Journal of Clinical Pharmacy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11096-025-02004-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11096-025-02004-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11096-025-02004-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T12:05:00Z","timestamp":1773662700000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11096-025-02004-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,1]]},"references-count":22,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["2004"],"URL":"https:\/\/doi.org\/10.1007\/s11096-025-02004-z","relation":{},"ISSN":["2210-7711"],"issn-type":[{"value":"2210-7711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,1]]},"assertion":[{"value":"12 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}