Journal of Bionic Engineering (2023) 20:762–781https://doi.org/10.1007/s42235-022-00292-z

Identification of Pulmonary Hypertension Animal Models Using a New Evolutionary Machine Learning Framework Based on Blood Routine Indicators

Jiao Hu1  · Shushu Lv2  · Tao Zhou3  · Huiling Chen1  · Lei Xiao1  · Xiaoying Huang4  · Liangxing Wang4  · Peiliang Wu4

1 Department of Computer Science and Artifcial Intelligence, Wenzhou University, Wenzhou 325035, People’s Republic of China 

2 Department of Dermatology, Beijing Tongren Hospital, Capital Medical University, Beijing 100730, People’s Republic of China 

3 The First Clinical College, Wenzhou Medical University, Wenzhou 325000, People’s Republic of China 

4 Department of Pulmonary and Critical Care Medicine, The First Afliated Hospital of Wenzhou Medical University, Wenzhou 325000, People’s Republic of China

AbstractPulmonary Hypertension (PH) is a global health problem that afects about 1% of the global population. Animal models of PH play a vital role in unraveling the pathophysiological mechanisms of the disease. The present study proposes a Kernel Extreme Learning Machine (KELM) model based on an improved Whale Optimization Algorithm (WOA) for predicting PH mouse models. The experimental results showed that the selected blood indicators, including Haemoglobin (HGB), Hematocrit (HCT), Mean, Platelet Volume (MPV), Platelet distribution width (PDW), and Platelet–Large Cell Ratio (P-LCR), were essential for identifying PH mouse models using the feature selection method proposed in this paper. Remarkably, the method achieved 100.0% accuracy and 100.0% specifcity in classifcation, demonstrating that our method has great potential to be used for evaluating and identifying mouse PH models. 

Keywords Feature selection · Pulmonary hypertension · Whale optimization algorithm · Extreme learning machine