Therapie最新文献

{"title":"Language models in pharmacovigilance: Applications, promises and limits","authors":"Francesco Salvo ,&nbsp;Lelio Crupi ,&nbsp;Clément Cholle","doi":"10.1016/j.therap.2025.12.003","DOIUrl":"10.1016/j.therap.2025.12.003","url":null,"abstract":"<div><div>The integration of language models into pharmacovigilance offers a valuable opportunity to enhance quality and efficiency across workflows. With their rapid evolution, these techniques have found diverse applications in pharmacovigilance, revealing promising advances in time-consuming and low-added-value tasks; nevertheless, several practical constraints continue to hinder their adoption. This work examines the use of traditional natural language processing techniques and advanced language models across three major pharmacovigilance domains: (i) adverse drug reactions extraction from medical records, (ii) case processing, and (iii) evidence screening. A PubMed® search was conducted to identify potentially relevant studies. Subsequently, expert-based selection refined the core literature set, which was expanded through related-reference screening to capture highly cited or conceptually linked papers. Traditional natural language processing techniques, including rule-based systems, dictionaries, and statistical models, offer transparent and efficient mechanisms for structured information extraction, and have shown practical applications, particularly in adverse drug reaction identification and coding. However, they often struggle with the linguistic variability typical of clinical narratives. In contrast, advanced language models, including large pre-trained transformers and large language models, demonstrate superior contextual understanding and adaptability to unstructured and heterogeneous text sources. Yet, their regulatory acceptance remains limited by hallucination risks, reduced transparency/reproducibility, dependence on parameter tuning, and the continued need for human-in-the-loop validation to ensure reliability. Additionally, the substantial computational requirements of large language models impose significant environmental costs, emphasizing the importance of rational and sustainable implementation strategies. Overall, natural language processing and advanced language models should be regarded as complementary approaches. Their integration can augment human expertise and foster a scalable, trustworthy, and sustainable pharmacovigilance ecosystem. At present, an interdisciplinary approach, where pharmacovigilance professionals actively contribute to model design, validation, and oversight, remains essential to harness automation benefits while maintaining clinical integrity.</div></div>","PeriodicalId":23147,"journal":{"name":"Therapie","volume":"81 2","pages":"Pages 140-146"},"PeriodicalIF":1.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146228478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence in personalized prescription: A narrative review of promise, peril, and practicality","authors":"Guillaume L. Martin,&nbsp;Louis Létinier","doi":"10.1016/j.therap.2025.10.001","DOIUrl":"10.1016/j.therap.2025.10.001","url":null,"abstract":"<div><div>The integration of artificial intelligence (AI), particularly large language models (LLMs), into clinical prescription practices represents a transformative shift in healthcare, promising to offer enhanced therapeutic precision, reduced errors, and personalized care. However, rapid adoption is outpacing validation and governance. This narrative review critically examines the benefits, risks, and implementation challenges of AI in pharmacology, with an emphasis on prescribing use cases, highlighting the rapid adoption driven by physician constrained time and increasing complexity of medical knowledge, yet outpaced by validation frameworks. Key benefits include optimized decision support, as suggested by real-world systems like the Penda Health AI Copilot. However, inherent risks such as hallucinations, lack of explainability, spending inflation, and clinical de-skilling pose significant threats, potentially eroding trust and patient safety. We contrast regulatory philosophies [European Union (EU) precaution under the medical devices regulation (MDR) and AI Act vs U.S. flexibility via Food and Drug predetermined change control plans (FDA PCCP)] and spotlight a persistent grey zone in which general-purpose LLMs are used clinically without medical-device oversight. To operationalize trustworthy use, we foreground rigorous evaluation and outline an “architecture of trustworthy clinical AI” (retrieval-augmented generation, structured clinical prompting with abstention/uncertainty, and hybrid LLM–rule safety layers). Finally, we propose an outcomes-first paradigm adapted from French health technologies assessment (HTA) — service rendered by AI (SR-AI) and improvement of service rendered by AI (ISR-AI), with patient outcomes and system resilience as primary endpoints — and recommend a default stance that any generative AI used in health be treated as a medical device, with general-purpose LLMs permitted only via certified clinical wrappers that close the MDR-inconsistent gap.</div></div>","PeriodicalId":23147,"journal":{"name":"Therapie","volume":"81 2","pages":"Pages 132-139"},"PeriodicalIF":1.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147555106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital pharmacological twins: Bridging multi-scale modelling and artificial intelligence for precision medicine: The DIGPHAT consortium","authors":"Jean-Baptiste Woillard ,&nbsp;Sébastien Benzekry ,&nbsp;Julie Josse ,&nbsp;Mélanie White-Koning ,&nbsp;Etienne Chatelut ,&nbsp;Emmanuelle Comets ,&nbsp;Florian Lemaitre ,&nbsp;Bénédicte Franck ,&nbsp;Matthieu Gregoire ,&nbsp;Françoise Stanke-Labesque ,&nbsp;Sarah Zohar ,&nbsp;Moreno Ursino ,&nbsp;Christophe Battail ,&nbsp;on behalf of the DIGPHAT consortium","doi":"10.1016/j.therap.2025.09.006","DOIUrl":"10.1016/j.therap.2025.09.006","url":null,"abstract":"<div><div>The advent of digital twins in pharmacology presents transformative potential for precision medicine, enabling personalized treatment optimization through dynamic computational simulations of drug interactions at molecular, cellular, and patient levels. These advanced virtual replicas of a patient's biological system are designed to predict individual therapeutic responses with high fidelity, thereby moving beyond the one-size-fits-all paradigm. This paper explores the concept of digital pharmacological twins, detailing how they can integrate heterogeneous data, including multi-omic, pharmacokinetic, pharmacodynamic, clinical, and environmental information, and employing a synergy of advanced mechanistic and machine learning models. Using illustrative examples from ongoing international initiatives, this work highlights the methodological frameworks necessary for developing and validating such comprehensive predictive tools. We underscore the critical importance of model interoperability, robust data integration strategies, and rigorous validation to ensure clinical utility. Ultimately, digital pharmacological twins promise to enhance therapeutic efficacy, minimize adverse drug reactions, and accelerate the translation of pharmacological science into tangible patient benefits.</div></div>","PeriodicalId":23147,"journal":{"name":"Therapie","volume":"81 2","pages":"Pages 147-158"},"PeriodicalIF":1.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145275979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A new chapter in pharmacology: Artificial intelligence's expanding role in pharmacokinetics, pharmacodynamics, and pharmacovigilance","authors":"Alexandre O. Gérard ,&nbsp;Romain Lombardi ,&nbsp;Diane Merino ,&nbsp;Charles Bouveyron ,&nbsp;Jean Dellamonica ,&nbsp;Milou-Daniel Drici ,&nbsp;Thibaud Lavrut ,&nbsp;Alexandre Destere","doi":"10.1016/j.therap.2025.09.002","DOIUrl":"10.1016/j.therap.2025.09.002","url":null,"abstract":"<div><div>In recent years, artificial intelligence (AI) has emerged as a powerful tool in healthcare and is becoming increasingly prevalent across all medical and paramedical disciplines. AI has numerous applications in pharmacology. This narrative review explores the increasing importance of AI in three key areas of pharmacology: pharmacokinetics (PK), pharmacodynamics (PD), and pharmacovigilance (PV), as well as pharmacology education. We conducted a literature review enhanced by the ARTIREV hybrid bibliometric tool to identify and analyze key advances, applications, and challenges with AI integration in this field. In PK, machine learning and hybrid approaches improve the prediction of individualized drug exposure, support model-informed precision dosing and handle irregular and sparse data through architectures such as recurrent neural networks and NeuralODEs. In PD, AI facilitates a shift towards an era of precision and personalized medicine by enabling the development of drug effect models and considering interindividual variability. It also makes it easier to implement adaptive dosing regimens that are tailored to various constraints. Regarding PV, AI enhances the detection of adverse drug reactions, the identification of safety signals at the population level and the assessment of preclinical toxicities through the analysis of unstructured data, particularly from electronic health records. Despite their potential, AI models face several significant limitations. These include the quality of training data, limited explainability due to the “black box” effect and a lack of external validation of the models developed. Altogether, this review emphasizes the role of AI in pharmacology and the necessity of training future professionals to ensure the safe and validated use of AI in personalized medical applications.</div></div>","PeriodicalId":23147,"journal":{"name":"Therapie","volume":"81 2","pages":"Pages 159-170"},"PeriodicalIF":1.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145303627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hyperprolactinemia following a single dose of risperidone: A case report.","authors":"Aurélie Bobet, Gael Galliot, Johann Hassan, Emmanuelle Bougon, Virginie Rouch, Romain Barus, Tanguy Taillefer de Laportaliere","doi":"10.1016/j.therap.2026.02.003","DOIUrl":"https://doi.org/10.1016/j.therap.2026.02.003","url":null,"abstract":"","PeriodicalId":23147,"journal":{"name":"Therapie","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147487368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Med-Timeline: Case-based evaluation of a digital tool for drug-induced skin eruption causality assessment.","authors":"Clement Svabek, Sophie Gautier, Johana Béné, Delphine Staumont-Sallé, Sophie Darras, Marie Chaveron, Marion Douxami, Frederic Dezoteux","doi":"10.1016/j.therap.2026.02.001","DOIUrl":"https://doi.org/10.1016/j.therap.2026.02.001","url":null,"abstract":"","PeriodicalId":23147,"journal":{"name":"Therapie","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147445264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Antipsychotics switching, a specific risk of thromboembolic events? A case report.","authors":"Anna Roger, Chloé Sablé, Lucie Bidouze, Valentine Piquet, Julien Li, Jacques Hamard","doi":"10.1016/j.therap.2026.02.002","DOIUrl":"https://doi.org/10.1016/j.therap.2026.02.002","url":null,"abstract":"","PeriodicalId":23147,"journal":{"name":"Therapie","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147616732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"[Erosive cystitis associated with chronic ketamine use: A case report].","authors":"Louise Bernet, Ahmed Hichem Elnedjar, Célian Bertin","doi":"10.1016/j.therap.2026.01.007","DOIUrl":"https://doi.org/10.1016/j.therap.2026.01.007","url":null,"abstract":"","PeriodicalId":23147,"journal":{"name":"Therapie","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146259302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quetiapine induced global aphasia: A case report.","authors":"Mohamed Zouari, Borhen Elloumi, Rabeb Jbir, Fatma Guermazi, Jihen Ketata, Yosr Hentati, Mohamed Ben Jmeaa, Kamilia Ksouda, Hichem Ammar, Jihène Ben Thabet","doi":"10.1016/j.therap.2026.01.005","DOIUrl":"https://doi.org/10.1016/j.therap.2026.01.005","url":null,"abstract":"","PeriodicalId":23147,"journal":{"name":"Therapie","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146776664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Angioedema reported with tissue plasminogen activators: A need to communicate on bradykinin- and histamine-mediated mechanisms.","authors":"Anaïs Maurier, Frédérique Beau-Salinas, Bérenger Largeau, Sophie Gautier, Elisabeth Polard, Annie-Pierre Jonville-Bera","doi":"10.1016/j.therap.2025.12.004","DOIUrl":"https://doi.org/10.1016/j.therap.2025.12.004","url":null,"abstract":"<p><strong>Aim of the study: </strong>Angioedema (AE) is a potentially life-threatening adverse effect. The mechanism can be either bradykinin- (BK-AE) or histamine-mediated (Hi-AE), each requiring different management. AE are reported with recombinant tissue plasminogen activators (alteplase and tenecteplase), for which an immunoallergic or bradykinic mechanism is suggested. The aim of this study was to describe the characteristics of cases of AE (BK or Hi) reported with rt-PA to the French Regional Pharmacovigilance Centers in order to optimize their identification and management.</p><p><strong>Methods: </strong>All cases of AE reported with alteplase or tenecteplase until 30 November, 2023 were analyzed and classified as Hi-AE or BK-AE using the clinical manifestations, the management and the allergological workup.</p><p><strong>Results: </strong>We analyzed 151 cases of AE, with a median time to onset of 1h (IQR=1-2h), all localized at the head. From them, 150 were with alteplase use for acute ischemic stroke (98%) or myocardial infarction (2%), and 1 with tenecteplase. Of them 107 (71%) could be clearly categorized and were classified as 98 (92%) cases of BK-AE and 9 (8%) cases of Hi-AE. When the use of icatibant or C1 esterase inhibitor is specified, it was the 1st-line treatment for 32/47 (68%) patients.</p><p><strong>Conclusion: </strong>The majority of cases of AE reported with rt-PA, are BK-AE involving alteplase. This is consistent with the effects of rt-PA, which activates the kinin pathway by hydrolyzing plasminogen to plasmin, resulting in the formation of bradykinin. Clinicians need to be informed of this mechanism, in order to early prescribe the appropriate treatment, as we detect that it was not systematically used as 1st-line therapy for a lot of cases.</p>","PeriodicalId":23147,"journal":{"name":"Therapie","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}