重新定义上市后监控：人工智能如何改变质量、安全和全球合规

MIKE KING, Senior Director, Product & Strategy, IQVIA Table of contents Introduction1Strengthening complaint handling: Volume, quality, andtimeliness2Improving Adverse Event Reporting (AER): Consistency and report quality2Expanding data gathering: Structured and unstructuredsources3Understanding new failure modes and human factorinsights4Process optimization: Efficiency, consistency, andcompliance5The IQVIA SmartSolve®difference6Conclusion6About the author6 Introduction Post-Market Surveillance (PMS) has become one of thefastest-evolving areas within the medical technology andpharmaceutical industries. Global regulatory authoritiesexpect timely visibility into emerging risks, clearerevidence linking real-world data to a product’s clinicalperformance and risk profile, and stronger connectivityfrom PMS activities back into mandatory quality andsafety activities. At the same time, companies faceunprecedented volumes of structured and unstructureddata from sources that include customer call-centerrecordings, social media insights, an expanding scientificliterature base, technical service records, and more.Gathering the right data at the right time, and thenmoving from data capture to actionable insight, is at theheart of successful PMS. AI can be a significant enabler for quality, regulatory,and safety professionals working in PMS, helping teamstransform data into information and action. A range ofAI solutions deployed to support activities mandatedby global regulation can amplify the human-in-the-loop professional, enabling teams to keep pace withcomplexity, identify signals earlier, and operate withgreater consistency and compliance across globalmarkets. When integrated into PMS processes, AIsupports complaint handling, enhances Adverse EventReporting (AER), expands organizations’ ability toingest data across formats, uncovers new failure modesand human-factor insights, and drives overall processoptimization. Ultimately, these improvements helpcompanies better understand product quality and theimpact of these products on patient populations globally. Agentic AI refers toautonomousAI agents able to understand, build, andperform complex workflows and business processes with limited direct humansupervision. Agents don’t replace point solutions; agents can orchestrate andoperate point solutions in place of human capital. vary by organization, division, and product type. Humanoversight remains essential, but the time requiredfor initial drafting decreases substantially, increasingthroughput while supporting data quality and compliance. Strengthening complainthandling: Volume, quality,andtimeliness Complaint handling remains central to PMS, butthe volume and variability of incoming informationcan overwhelm even well-structured, experiencedteams. AI can directly increase complaint-handlingcapacity of global teams by automating repetitivetasks and improving the quality and consistency ofproceduraloutputs. Improving Adverse EventReporting (AER): Consistencyand report quality Adverse event reporting demands consistency, clarity,and timeliness in submissions to global authorities.Variability in narrative text and coded fields acrosssimilar complaints can extend dialogues with regulatorsand undermine confidence in the robustness of anorganization’s PMS operations. Automated intake and normalization AI tools can parse free text narratives from call-centerinteractions, emails, social media, and technical servicereports and automatically map them to standardizedcomplaint categories specific to the range of productsmarketed by a given company. This improves thequality and timeliness of initial case data and reducesdownstream investigation rework. Consistent coding AI can recommend appropriate problem codes andpatient-impact descriptors based on historical patterns.Reviewers retain full decision authority, while automatedrecommendations help reduce variability acrossreviewers and sites. Language translation capabilities When organizations use language-translation capabilities,cases can be captured in a local language while allowingan investigator to review the information in anotherlanguage, while retaining the integrity of the originalrecord. By enabling intake in a native language, both thequality and timeliness of case information can improve. Enhanced drafting with GenAI GenAI can prepopulate key sections of AER reports usingapproved templates and established precedents. Thisimproves consistency, reduces administrative burden,and helps global teams maintain alignment in structureand language when reporting to regulatory authorities.GenAI-driven first drafts also allow human-in-the-loopexperts to spend more time assessing clinical contextand focusing on higher-value professional judgment. Case triage and clustering Machine-learning techniques can identify similar cases,group related events, and prioritize those likely to havethe greatest safety relevance. This allows teams to focuson the most critical