Scholarlink

Low bone mineral density (BMD), the hallmark of osteoporosis, is a growing public health concern. To date, several conventional machine learning (ML) algorithms have been put out to estimate the risk of osteoporosis. When used in clinical settings, these models have, however, demonstrated comparatively low accuracy. A fresh chance to enhance prediction performance has been presented by newly proposed deep learning (DL) techniques, such as recurrent neural networks (RNN), which can extract knowledge from intricate hidden interactions. Hence, the present research work conducted the comparison analysis of different RNN approaches such as simple RNN, long short-term memory (LSTM), and gated recurrent unit (GRU) for osteoporosis detection. The results show that low computation times can be achieved using SRNNs and good accuracy can be predicted for osteoporosis using LSTM approaches.

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

Performance Comparative Analysis of Recurrent Neural Network for Osteoporosis Disease Prediction

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • P. Lavanya,
  • G. Yashodha

摘要

Low bone mineral density (BMD), the hallmark of osteoporosis, is a growing public health concern. To date, several conventional machine learning (ML) algorithms have been put out to estimate the risk of osteoporosis. When used in clinical settings, these models have, however, demonstrated comparatively low accuracy. A fresh chance to enhance prediction performance has been presented by newly proposed deep learning (DL) techniques, such as recurrent neural networks (RNN), which can extract knowledge from intricate hidden interactions. Hence, the present research work conducted the comparison analysis of different RNN approaches such as simple RNN, long short-term memory (LSTM), and gated recurrent unit (GRU) for osteoporosis detection. The results show that low computation times can be achieved using SRNNs and good accuracy can be predicted for osteoporosis using LSTM approaches.