An evolutionary machine learning for pulmonary hypertension animal model from arterial blood gas analysis
An evolutionary machine learning for pulmonary hypertension animal model from arterial blood gas analysis
复制标题
基于动脉血气分析的肺动脉高压动物模型的进化机器学习
DOI：
10.1016/j.compbiomed.2022.105529
复制
发表时间：
2022-05-17
影响因子：
7.7
通讯作者：
Wu，Peiliang
中科院分区：
文献类型：
--
作者：
Shi，Beibei;Zhou，Tao;Wu，Peiliang
肺动脉高压（PH）是一种罕见且致命的疾病，可导致右心衰和死亡。PH的病理生理学和潜在的治疗方法尚不清楚。PH动物模型的建立和评价是PH研究的关键。本文提出了一种有效的动脉血气PH分析技术，该技术利用进化核极限学习机与多策略集成黏菌算法（MSSMA）。在MSSMA算法中，在原有的黏菌算法中加入了两个高效的蜜蜂觅食学习算子，确保了强度和多样性之间的适当权衡。在30个IEEE基准测试中对该算法进行了评估，统计结果表明，该算法的搜索性能得到了显著提高。利用MSSMA开发了一种基于动脉血气分析的PH值的核极限学习机（MSSMA- kelm）。综合而言，本文提出的MSSMA-KELM可作为动脉血气分析PH值的有效分析技术，准确度为93.31%，马修斯系数为90.13%，灵敏度为91.12%，特异性为90.73%。MSSMA-KELM可作为评价小鼠PH模型的有效方法。
Pulmonary hypertension (PH) is a rare and fatal condition that leads to right heart failure and death. The pathophysiology of PH and potential therapeutic approaches are yet unknown. PH animal models' development and proper evaluation are critical to PH research. This work presents an effective analysis technology for PH from arterial blood gas analysis utilizing an evolutionary kernel extreme learning machine with multiple strategies integrated slime mould algorithm (MSSMA). In MSSMA, two efficient bee-foraging learning operators are added to the original slime mould algorithm, ensuring a suitable trade-off between intensity and diversity. The proposed MSSMA is evaluated on thirty IEEE benchmarks and the statistical results show that the search performance of the MSSMA is significantly improved. The MSSMA is utilised to develop a kernel extreme learning machine (MSSMA-KELM) on PH from arterial blood gas analysis. Comprehensively, the proposed MSSMA-KELM can be used as an effective analysis technology for PH from arterial Blood gas analysis with an accuracy of 93.31%, Matthews coefficient of 90.13%, Sensitivity of 91.12%, and Specificity of 90.73%. MSSMA-KELM can be treated as an effective approach for evaluating mouse PH models.