Assistant Professor, Symbiosis Institute of Technology, Nagpur Campus, Symbiosis International (Deemed University), Pune, India.
Professor, Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram, A.P., India.
SLAS Technol. 2024 Aug;29(4):100159. doi: 10.1016/j.slast.2024.100159. Epub 2024 Jun 21.
In today's digital world, with growing population and increasing pollution, unhealthy lifestyle habits like irregular eating, junk food consumption, and lack of exercise are becoming more common, leading to various health problems, including kidney issues. These factors directly affect human kidney health. To address this, we require early detection techniques that rely on text data. Text data contains detailed information about a patient's medical history, symptoms, test results, and treatment plans, giving a complete picture of kidney health and enabling timely intervention. In this research paper, we proposed a range of sophisticated models, such as Gradient Boosting Classifier, Light GBM, CatBoost, Support Vector Classifier (SVC), Random Boost, Logistic Regression, XGBoost, Deep Neural Network (DNN), and an Improved DNN. The Improved DNN demonstrated exceptional performance, with an accuracy of 90 %, precision of 89 %, recall of 90 %, and an F1-Score of 89.5 %. By combining traditional machine learning and deep neural networks, this integrative approach enables the identification of intricate patterns in datasets. The model's data-driven processes consistently update internal parameters, guaranteeing flexibility in response to evolving healthcare settings. This research represents a notable advancement in the progress of creating a more detailed and individualised ability to diagnose kidney stones, which could potentially lead to better clinical results and patient treatment.
在当今数字化的世界中，由于人口增长和污染加剧，不规律的饮食、垃圾食品消费和缺乏运动等不健康的生活方式习惯变得越来越普遍，导致了各种健康问题，包括肾脏问题。这些因素直接影响着人类的肾脏健康。为了解决这个问题，我们需要依靠文本数据的早期检测技术。文本数据包含了有关患者病史、症状、检查结果和治疗计划的详细信息，全面反映了肾脏健康状况，从而能够及时进行干预。在本研究论文中，我们提出了一系列复杂的模型，如梯度提升分类器、轻梯度提升机、CatBoost、支持向量分类器 (SVC)、随机提升、逻辑回归、XGBoost、深度神经网络 (DNN) 和改进的 DNN。改进的 DNN 表现出色，准确率为 90%，精密度为 89%，召回率为 90%，F1 得分为 89.5%。通过将传统机器学习和深度神经网络相结合，这种集成方法能够识别数据集的复杂模式。该模型的数据驱动过程不断更新内部参数，从而能够灵活应对不断变化的医疗保健环境。这项研究代表着在创建更详细和个性化的肾结石诊断能力方面取得了显著进展，这可能会带来更好的临床结果和患者治疗效果。
