Scholarlink

<p>This study explores into the profound impact of foot ulcers associated with diabetes mellitus and neuropathy on the health-related quality of life (HRQoL) of diabetic individuals. An estimated 15% of patients with diabetes in the United States encounter foot ulcers at some juncture in their lives, according to the National Institutes of Health (NIH). Currently, the detection and treatment of Diabetes Foot Ulcers (DFU) predominantly take place within clinical settings, resulting in delays in early identification and intervention. Consequently, there exists a pressing imperative for the development of an at-home DFU detection system. Our proposed solution encompasses three key components: an Internet of Things (IoT) device, a machine learning model utilizing supervised learning techniques, and a mobile application interface. Firstly, the IoT device is engineered to sense foot nodes and transmit vibrations onto the foot sole. This serves as the primary means of data collection, enabling continuous monitoring in the comfort of the patient’s home. Secondly, the machine learning model is designed to predict the severity level of DFU. Leveraging supervised learning techniques, including XGBoost, K-SVM, Random Forest, and Decision tree algorithms, the model analyzes the collected data to provide accurate assessments of DFU progression. Comparative results indicate that our system achieved 96.56% accuracy when compared to current models, showcasing its superior performance in terms of accuracy, sensitivity, and specificity. Thirdly, the mobile application acts as an intuitive interface between the sensors and the patient. Through the application, users can receive real-time updates on their DFU status, along with personalized recommendations for prevention, treatment, and medication. By facilitating seamless communication and empowering patients with actionable insights, the application aims to mitigate the risk of amputations resulting from neglected DFU. In summary, our proposed at-home DFU detection system offers a comprehensive solution to address the challenges posed by diabetic foot ulcers. By enabling timely predictions and personalized interventions, we aspire to improve the HRQoL and overall well-being of diabetic individuals, thereby reducing the burden on healthcare facilities and enhancing patient outcomes.</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

Synergizing IoT and machine learning for diabetic foot ulcer detection and management

  • 期刊论文

  • 发表日期：

    2025年7月7日

查看全文
  • Rama Devi K,
  • Ramachandran P,
  • Althaf Ali A,
  • Umamaheswari S,
  • Jayabrabu Ramakrishnan

摘要

This study explores into the profound impact of foot ulcers associated with diabetes mellitus and neuropathy on the health-related quality of life (HRQoL) of diabetic individuals. An estimated 15% of patients with diabetes in the United States encounter foot ulcers at some juncture in their lives, according to the National Institutes of Health (NIH). Currently, the detection and treatment of Diabetes Foot Ulcers (DFU) predominantly take place within clinical settings, resulting in delays in early identification and intervention. Consequently, there exists a pressing imperative for the development of an at-home DFU detection system. Our proposed solution encompasses three key components: an Internet of Things (IoT) device, a machine learning model utilizing supervised learning techniques, and a mobile application interface. Firstly, the IoT device is engineered to sense foot nodes and transmit vibrations onto the foot sole. This serves as the primary means of data collection, enabling continuous monitoring in the comfort of the patient’s home. Secondly, the machine learning model is designed to predict the severity level of DFU. Leveraging supervised learning techniques, including XGBoost, K-SVM, Random Forest, and Decision tree algorithms, the model analyzes the collected data to provide accurate assessments of DFU progression. Comparative results indicate that our system achieved 96.56% accuracy when compared to current models, showcasing its superior performance in terms of accuracy, sensitivity, and specificity. Thirdly, the mobile application acts as an intuitive interface between the sensors and the patient. Through the application, users can receive real-time updates on their DFU status, along with personalized recommendations for prevention, treatment, and medication. By facilitating seamless communication and empowering patients with actionable insights, the application aims to mitigate the risk of amputations resulting from neglected DFU. In summary, our proposed at-home DFU detection system offers a comprehensive solution to address the challenges posed by diabetic foot ulcers. By enabling timely predictions and personalized interventions, we aspire to improve the HRQoL and overall well-being of diabetic individuals, thereby reducing the burden on healthcare facilities and enhancing patient outcomes.