Scholarlink

<p>Concomitant administration of Japanese encephalitis (JE) and other travel-related vaccines is common, yet safety data on these combinations remain limited. This study applies machine learning (ML) techniques to predict adverse events following immunisation (AEFI) using active surveillance data from Australian travellers. Five ML models were evaluated, with random forest demonstrating the highest predictive performance. Important predictors included age, number of vaccines received, and specific vaccine types. The final model was implemented in an interactive web-based tool to support clinical decision-making and improve communication of AEFI risk. This approach demonstrates the potential of ML to enhance vaccine safety monitoring in travel medicine.</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

Predicting vaccine reactogenicity using machine learning: evidence from japanese encephalitis vaccine combinations

  • 期刊论文

  • 发表日期：

    2025年12月8日

查看全文
  • Hongen Lu,
  • Colleen L. Lau,
  • Alan Leeb,
  • Deborah J. Mills,
  • Nicolas Smoll,
  • Nazmul Islam,
  • Helen J. Mayfield,
  • Yoni Nazarathy,
  • Luis Furuya-Kanamori

摘要

Concomitant administration of Japanese encephalitis (JE) and other travel-related vaccines is common, yet safety data on these combinations remain limited. This study applies machine learning (ML) techniques to predict adverse events following immunisation (AEFI) using active surveillance data from Australian travellers. Five ML models were evaluated, with random forest demonstrating the highest predictive performance. Important predictors included age, number of vaccines received, and specific vaccine types. The final model was implemented in an interactive web-based tool to support clinical decision-making and improve communication of AEFI risk. This approach demonstrates the potential of ML to enhance vaccine safety monitoring in travel medicine.