Scholarlink

<p>Many high-stakes artificial intelligence (AI) applications target&#xa0;low-prevalence events, where apparent accuracy can conceal limited real-world value. Relevant AI models range from expert-defined rules and traditional machine learning to generative large language models (LLMs) constrained for classification. As the effort and expertise required to develop modern AI decrease, there is a risk that organizations devote too little time to understanding their limitations and sources of error. We outline key dimensions for critical appraisal of AI in rare-event recognition, including problem framing and test set design, prevalence-aware statistical evaluation, robustness assessment, and integration into human workflows. In addition, we propose an approach to structured case-level examination (SCLE), to complement statistical performance evaluation, and a set of considerations to guide procurement or development of AI models for rare-event recognition. We&#xa0;instantiate&#xa0;the framework in&#xa0;pharmacovigilance, drawing on three studies: rule-based retrieval of pregnancy-related reports, duplicate detection combining machine learning with probabilistic record linkage, and automated redaction of person names using an LLM. We highlight pitfalls specific to the rare-event setting including optimism from unrealistic class balance and lack of difficult positive controls in test sets—and show how cost-sensitive targets align model performance with operational value. While grounded in pharmacovigilance practice, the principles generalize to domains where&#xa0;positives are scarce,&#xa0;and&#xa0;error costs may be asymmetric.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Critical Appraisal of Artificial Intelligence for Rare-Event Recognition: Principles and Pharmacovigilance Case Studies

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月11日

查看全文
  • G. Niklas Norén,
  • Eva-Lisa Meldau,
  • Johan Ellenius

摘要

Many high-stakes artificial intelligence (AI) applications target low-prevalence events, where apparent accuracy can conceal limited real-world value. Relevant AI models range from expert-defined rules and traditional machine learning to generative large language models (LLMs) constrained for classification. As the effort and expertise required to develop modern AI decrease, there is a risk that organizations devote too little time to understanding their limitations and sources of error. We outline key dimensions for critical appraisal of AI in rare-event recognition, including problem framing and test set design, prevalence-aware statistical evaluation, robustness assessment, and integration into human workflows. In addition, we propose an approach to structured case-level examination (SCLE), to complement statistical performance evaluation, and a set of considerations to guide procurement or development of AI models for rare-event recognition. We instantiate the framework in pharmacovigilance, drawing on three studies: rule-based retrieval of pregnancy-related reports, duplicate detection combining machine learning with probabilistic record linkage, and automated redaction of person names using an LLM. We highlight pitfalls specific to the rare-event setting including optimism from unrealistic class balance and lack of difficult positive controls in test sets—and show how cost-sensitive targets align model performance with operational value. While grounded in pharmacovigilance practice, the principles generalize to domains where positives are scarce, and error costs may be asymmetric.