Scholarlink

Malaria remains a persistent health challenge in India despite concerted control efforts. This study examines malaria data from 2012 to 2019 in Mumbai, employing Generalized Linear Models (GLMs), random forest and artificial neural network. All the models showed rainfall, mean duration of sunshine, and population density as significant variables in predicting malaria cases in Mumbai. We also observe that the GLMs outperform random forest and artificial neural network in terms of metrics such as RMSE and MAPE. This research underscores the importance of statistical modeling techniques in informing targeted interventions about the significant environmental factors influencing malaria and strengthening malaria control strategies in urban areas.

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 Malaria Cases in Mumbai: Insights from Statistical and Machine Learning Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Praveen D. Chougale,
  • Adithya B. Somaraj,
  • Usha Ananthakumar

摘要

Malaria remains a persistent health challenge in India despite concerted control efforts. This study examines malaria data from 2012 to 2019 in Mumbai, employing Generalized Linear Models (GLMs), random forest and artificial neural network. All the models showed rainfall, mean duration of sunshine, and population density as significant variables in predicting malaria cases in Mumbai. We also observe that the GLMs outperform random forest and artificial neural network in terms of metrics such as RMSE and MAPE. This research underscores the importance of statistical modeling techniques in informing targeted interventions about the significant environmental factors influencing malaria and strengthening malaria control strategies in urban areas.