Department of Brain Disease Rehabilitation, Hailun Hospital of Traditional Chinese Medicine, Suihua, China.
Department of Acupuncture II, The Second Affiliated Hospital of Heilongjiang University of Chinese Medicine, Harbin, China.
Technol Health Care. 2024;32(6):4041-4061. doi: 10.3233/THC-231755.
Healthcare is crucial to patient care because it provides vital services for maintaining and restoring health. As healthcare technology evolves, cutting-edge tools facilitate faster diagnosis and more effective patient treatment. In the present age of pandemics, the Internet of Things (IoT) offers a potential solution to the problem of patient safety monitoring by creating a massive quantity of data about the patient through the linked devices around them and then analyzing it to estimate the patient's current status. Utilizing the IoT-based meta-heuristic algorithm allows patients to be remotely monitored, resulting in timely diagnosis and improved care. Meta-heuristic algorithms are successful, resilient, and effective in solving real-world enhancement, clustering, predicting, and grouping. Healthcare organizations need an efficient method for dealing with big data since the prevalence of such data makes it challenging to analyze for diagnosis. The current techniques used in medical diagnostics have limitations due to imbalanced data and the overfitting issue.
This study introduces the particle swarm optimization and convolutional neural network to be used as a meta-heuristic optimization method for extensive data analysis in the IoT to monitor patients' health conditions.
Particle Swarm Optimization is used to optimize the data used in the study. Information for a diabetes diagnosis model that includes cardiac risk forecasting is collected. Particle Swarm Optimization and Convolutional Neural Networks (PSO-CNN) results effectively make illness predictions. Support Vector Machine has been used to predict the possibility of a heart attack based on the classification of the collected data into projected abnormal and normal ranges for diabetes.
The results of the simulations reveal that the PSO-CNN model used to predict diabetic disease increased in accuracy by 92.6%, precision by 92.5%, recall by 93.2%, F1-score by 94.2%, and quantization error by 4.1%.
The suggested approach could be applied to identify cancer cells.
医疗保健对患者护理至关重要，因为它提供了维持和恢复健康的重要服务。随着医疗保健技术的发展，先进的工具可以促进更快的诊断和更有效的患者治疗。在当前的大流行病时代，物联网 (IoT) 通过链接设备创建大量有关患者的数据，并对其进行分析以估计患者的当前状态，为患者安全监测提供了潜在的解决方案。利用基于物联网的启发式元算法可以对患者进行远程监测，从而实现及时诊断和改善护理。启发式元算法在解决现实世界中的增强、聚类、预测和分组问题方面非常成功、有弹性且有效。由于此类数据的普及，医疗保健组织需要一种有效的方法来处理大数据，因为分析这些数据具有挑战性。由于数据不平衡和过拟合问题，目前用于医学诊断的技术存在局限性。
本研究引入粒子群优化和卷积神经网络作为元启发式优化方法，用于在物联网中对广泛的数据进行分析，以监测患者的健康状况。
使用粒子群优化来优化研究中使用的数据。收集包括心脏风险预测在内的糖尿病诊断模型的信息。粒子群优化和卷积神经网络 (PSO-CNN) 的结果可以有效地进行疾病预测。支持向量机已用于根据所收集数据的分类，将心脏病发作的可能性预测为预测异常和正常范围。
模拟结果表明，用于预测糖尿病疾病的 PSO-CNN 模型的准确性提高了 92.6%，精度提高了 92.5%，召回率提高了 93.2%，F1 得分提高了 94.2%，量化误差降低了 4.1%。
所提出的方法可用于识别癌细胞。
