Equipment management and maintenance center, Shanxi Bethune Hospital, Taiyuan, 030032, Shanxi, China.
Sci Rep. 2024 Sep 30;14(1):22677. doi: 10.1038/s41598-024-73813-x.
With the continuous updating and progress of medical equipment, the overdue medical device has problems such as management difficulties, resource waste, and potential security risks. Therefore, this paper used the Kohonen network algorithm to quantitatively evaluate and analyze the surplus value of overdue medical devices. In this paper, the Kohonen network algorithm was used to build a quantitative model of the surplus value of the overdue medical device, and the self-organization characteristics and data-driven learning ability of the Kohonen network were used to predict the surplus value of the equipment more accurately. Support vector machine was used to quantitatively evaluate and predict the surplus value of overdue medical devices, and further optimize the model performance, to provide more accurate and reliable decision support for medical equipment management. The Kohonen network algorithm used in this paper evaluated the correlation between the service life and maintenance cost of eight types of overdue medical devices and quantitatively predicted the surplus value of overdue medical devices with the random forest algorithm. According to the comparison of prediction bias, the maximum deviation between the expected surplus value and the actual surplus value is only 1, and the deviation value by the random forest algorithm is as low as 6, the Kohonen network algorithm in this paper has better prediction performance than the random forest algorithm. In the experiment of comparative analysis and verification by introducing the decision tree algorithm, the average error rate of the Kohonen network algorithm in this paper was only 20.57%, which was far lower than 46.34% of the random forest algorithm and 65.31% of decision tree algorithm. The Kohonen network algorithm used in this paper can effectively quantitatively evaluate and predict the surplus value of overdue medical devices, thus improving the efficiency of medical equipment management, reducing costs, and ensuring patient safety.
随着医疗设备的不断更新和进步，过期医疗器械存在管理困难、资源浪费和潜在安全风险等问题。因此，本文采用科荷伦网络算法对过期医疗器械的剩余价值进行定量评估和分析。本文采用科荷伦网络算法构建了过期医疗器械剩余价值的定量模型，利用科荷伦网络的自组织特性和数据驱动学习能力，更准确地预测设备的剩余价值。采用支持向量机对过期医疗器械的剩余价值进行定量评估和预测，并进一步优化模型性能，为医疗设备管理提供更准确、可靠的决策支持。本文采用的科荷伦网络算法评估了 8 种过期医疗器械的使用寿命和维修成本之间的相关性，并采用随机森林算法对过期医疗器械的剩余价值进行定量预测。根据预测偏差的比较，期望剩余价值与实际剩余价值之间的最大偏差仅为 1，随机森林算法的偏差值低至 6，本文采用的科荷伦网络算法的预测性能优于随机森林算法。在引入决策树算法进行对比分析和验证的实验中，本文采用的科荷伦网络算法的平均错误率仅为 20.57%，远低于随机森林算法的 46.34%和决策树算法的 65.31%。本文采用的科荷伦网络算法可以有效地对过期医疗器械的剩余价值进行定量评估和预测，从而提高医疗设备管理效率、降低成本，保证患者安全。
