<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD with MathML3 v1.3 20210610//EN" "JATS-archivearticle1-3-mathml3.dtd"><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"
  dtd-version="1.3" xml:lang="en" article-type="research-article">
  <?DTDIdentifier.IdentifierValue -//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.2 20190208//EN?>
  <?DTDIdentifier.IdentifierType public?>
  <?SourceDTD.DTDName JATS-journalpublishing1.dtd?>
  <?SourceDTD.Version 1.2?>
  <?ConverterInfo.XSLTName jats2jats3.xsl?>
  <?ConverterInfo.Version 1?>
  <?properties open_access?>
  <front>
    <journal-meta>
      <journal-id journal-id-type="iso-abbrev">Arch Pharm Pract</journal-id>
      <journal-id journal-id-type="publisher-id">archivepp.com</journal-id>
      <journal-id journal-id-type="publisher-id">Arch Pharm Pract</journal-id>
      <journal-title-group>
        <journal-title>Archives of Pharmacy Practice</journal-title>
      </journal-title-group>
      <issn pub-type="epub">2320-5210</issn>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="publisher-id">archivepp.com-1278</article-id>
      <article-id pub-id-type="doi">10.51847/HSMLaWFbcN</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Original research</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Conversational Pharmacovigilance That Preserves the Patient’s Narrative</article-title>
      </title-group>
                    <contrib-group>
                      <contrib contrib-type="author">
              <name>
                <surname>Bennett</surname>
                <given-names>Olivia</given-names>
              </name>
                              <xref rid="aff1" ref-type="aff">1</xref>
                                                            <xref rid="cor1" ref-type="corresp" />
                          </contrib>
                      <contrib contrib-type="author">
              <name>
                <surname>Collins</surname>
                <given-names>Harry</given-names>
              </name>
                              <xref rid="aff2" ref-type="aff">2</xref>
                                        </contrib>
                      <contrib contrib-type="author">
              <name>
                <surname>Foster</surname>
                <given-names>Jack</given-names>
              </name>
                              <xref rid="aff1" ref-type="aff">1</xref>
                                        </contrib>
                      <contrib contrib-type="author">
              <name>
                <surname>Wright</surname>
                <given-names>Ethan</given-names>
              </name>
                              <xref rid="aff3" ref-type="aff">3</xref>
                                        </contrib>
                  </contrib-group>
                  <aff id="aff1">
            <label>1</label>Department of Conversational AI and Pharmacovigilance, Faculty of Pharmacy, University of Nottingham, Nottingham, United Kingdom.
          </aff>
                  <aff id="aff2">
            <label>2</label>Department of Patient Narrative in Drug Safety, Faculty of Pharmacy, University of Southampton, Southampton, United Kingdom.
          </aff>
                  <aff id="aff3">
            <label>3</label>Department of AI and Patient Voice in Pharmacy, Faculty of Pharmacy, Newcastle University, Newcastle, United Kingdom.
          </aff>
                          <author-notes>
            <corresp id="cor1">
              <bold>Address for correspondence:</bold> Prof. Wael Abu Dayyih, Department of
              Pharmaceutical Chemistry, Faculty of Pharmacy, Mutah University, Al-Karak 61710, Jordan.
                              E-mail: <email xlink:href="olivia.bennett@nottingham.ac.uk">olivia.bennett@nottingham.ac.uk</email>
                          </corresp>
          </author-notes>
                    <pub-date pub-type="epub">
        <day>30</day>
        <month>06</month>
        <year>2026</year>
      </pub-date>
      <volume>17</volume>
      <issue>2</issue>
      <fpage>4</fpage>
      <lpage>12</lpage>
      <permissions>
        <copyright-statement>
          Copyright: &#x000a9; 2026 Archives of Pharmacy Practice
        </copyright-statement>
        <copyright-year>2026</copyright-year>
        <license>
          <ali:license_ref xmlns:ali="http://www.niso.org/schemas/ali/1.0/"
            specific-use="textmining" content-type="ccbyncsalicense">
            https://creativecommons.org/licenses/by-nc-sa/4.0/</ali:license_ref>
          <license-p>This is an open access journal, and articles are distributed under the terms of
            the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 License, which allows
            others to remix, tweak, and build upon the work non-commercially, as long as appropriate
            credit is given and the new creations are licensed under the identical terms.</license-p>
        </license>
      </permissions>
      <abstract>
        <title>A<sc>BSTRACT</sc></title>
        <p>Structured adverse-event reporting supports coding, aggregation, and regulatory review, but it can compress the patient’s account into fields that omit chronology, uncertainty, functional consequences, perceived causality, and the language through which harm is understood. This article proposes a non-empirical conversational pharmacovigilance architecture designed to preserve patient narrative while supporting structured extraction, triage, and signal work. The architecture uses a dual-representation contract: an append-preserving narrative ledger remains the source record, while a separate structured safety object contains derived medication, event, timing, seriousness, outcome, action, and uncertainty fields linked to supporting narrative spans. A bounded clarification controller may request missing safety-relevant information without silently rewriting previous statements. The preserved narrative and structured derivative are combined in a paired triage packet and passed through explicit human review gates before case assessment or signal work. Governance spans consent, privacy, accessibility, patient correction, provenance, auditability, subgroup evaluation, incident response, change control, and withdrawal authority. Evaluation must distinguish narrative completeness and fidelity from coding accuracy, triage safety, workflow consequence, patient experience, equity, and organizational readiness. The architecture does not determine causality, replace professional assessment, provide medication advice, validate safety signals, or establish regulatory compliance. Its original contribution is a provenance-preserving relationship between patient dialogue and pharmacovigilance operations that treats structured data as a useful derivative rather than a superior replacement for the patient’s account. Empirical validation is required across languages, populations, reporting channels, and medication-safety workflows.</p>
      </abstract>
      <kwd-group>
                <kwd>Digital pharmacy</kwd>
                <kwd>Artificial intelligence</kwd>
                <kwd>Pharmacy practice</kwd>
                <kwd>Medication safety</kwd>
                <kwd>Human–AI collaboration</kwd>
                <kwd>Clinical decision support</kwd>
              </kwd-group>
    </article-meta>
  </front>
</article>