Scholarlink

This study presents a sophisticated AI-driven multi-disease prediction framework that combines G-Fuzzy logic, Ant Colony Optimization (ACO), Gated Recurrent Units (GRU), and Bidirectional Encoder Representations from Transformers (BERT). The system analyzes both structured and unstructured medical information to improve diagnostic precision for various diseases. G-Fuzzy logic tackles diagnostic ambiguities, GRU processes time-series health information, BERT interprets intricate clinical narratives, and ACO enhances feature selection to boost predictive precision. Study findings show the system's exceptional efficiency, attaining 98.5% accuracy, 98.2% precision, and 98.4% recall on actual datasets, outperforming conventional models like RNNs, SVMs, and CNN-LSTMs. ACO decreased features by 65% while maintaining predictive accuracy. By incorporating these advanced AI methods, the model provides accurate disease forecasting, medication assessment, and preventive suggestions, enhancing healthcare decision-making. The framework shows significant potential in enhancing diagnostic precision and patient results, representing an important advancement in AI-based healthcare innovations.

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

AI-Powered Multi-disease Prediction Framework Using GRU, G-Fuzzy, Ant Colony Optimization, and BERT for Drug and Precaution Analysis

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Surendar Rama Sitaraman,
  • Venkata Surya Bhavana Harish Gollavilli,
  • Harikumar Nagarajan,
  • Poovendran Alagarsundaram,
  • Kalyan Gattupalli,
  • M. M. Kamruzzaman

摘要

This study presents a sophisticated AI-driven multi-disease prediction framework that combines G-Fuzzy logic, Ant Colony Optimization (ACO), Gated Recurrent Units (GRU), and Bidirectional Encoder Representations from Transformers (BERT). The system analyzes both structured and unstructured medical information to improve diagnostic precision for various diseases. G-Fuzzy logic tackles diagnostic ambiguities, GRU processes time-series health information, BERT interprets intricate clinical narratives, and ACO enhances feature selection to boost predictive precision. Study findings show the system's exceptional efficiency, attaining 98.5% accuracy, 98.2% precision, and 98.4% recall on actual datasets, outperforming conventional models like RNNs, SVMs, and CNN-LSTMs. ACO decreased features by 65% while maintaining predictive accuracy. By incorporating these advanced AI methods, the model provides accurate disease forecasting, medication assessment, and preventive suggestions, enhancing healthcare decision-making. The framework shows significant potential in enhancing diagnostic precision and patient results, representing an important advancement in AI-based healthcare innovations.