Uncertainty quantification of microcirculatory characteristic parameters for recognition of cardiovascular diseases.

BACKGROUND: Cardiovascular disease is one of the leading causes of death worldwide. However, according to studies, 90% of cardiovascular diseases can be prevented. Cardiovascular function parameters are an important basis for the diagnosis of cardiovascular diseases. The pulse wave also contains a wealth of physiological and pathological information, which can reflect the trend of cardiac function parameters at an early stage, so the measurement and analysis of the pulse wave signal becomes more and more important. The wearable pulse signal acquisition device has gradually become a new trend. In the mobile health scenario, convenient use is the prerequisite for long-term and rapid health monitoring. The data containing diverse pulse wave signals is the basis for obtaining more comprehensive and accurate human physiopathological information. Accurate data analysis and processing is the key to realizing the important goal of cardiovascular health monitoring. OBJECTIVE: Based on the concept of mobile health care, wearable devices are developed to obtain physiological signals. The zero-dimensional model and the optimization algorithm are combined to complete the uncertainty quantification of the microcirculation parameters. Then, a feature set containing the cardiovasvular parameters can be constructed. The machine learning algorithm can be used to build a model that can accurately realize cardiovascular disease identification. METHODS: This paper adopts laboratory-developed equipment to acquire the wrist pulse wave and fingertip volume pulse wave. A total of 323 samples were collected from healthy populations, hypertensive patients and patients with coronary heart disease (CHD). The pulse blood flow model in fingertip microcirculation is established, and the uncertainty quantification of model parameters is completed based on slime mold algorithm (SMA). After comparing and analyzing the performance of four algorithms on pulse wave classification, the identification model of cardiovascular diseases is established based on the microcirculatory characteristic parameter set and random forest algorithm (RF). RESULTS: RF showed good classification performance among the four classification algorithms. The identification accuracy of the model built on the microcirculatory characteristic parameter set and RF algorithm all reached more than 88%. The highest recognition accuracy was 95.51% for coronary heart disease samples, 92.11% for healthy samples, and 88.55% for hypertensive samples. It can be seen that the model based on RF algorithm has a good ability to distinguish the characteristic parameters in different cardiovascular health states. CONCLUSIONS: The wearable device designed in this paper can facilitate the daily health monitoring of cardiovascular disease. By using the combination of the physical model and machine learning model, the uncertainty quantification of microcirculation parameters and the identification of cardiovascular disease was finally completed. The recognition model based on machine learning provides a new idea and method for the research of cardiovascular health monitoring through pulse waves.

Ensemble Learning-Based Pulse Signal Recognition: Classification Model Development Study.

BACKGROUND: In pulse signal analysis and identification, time domain and time frequency domain analysis methods can obtain interpretable structured data and build classification models using traditional machine learning methods. Unstructured data, such as pulse signals, contain rich information about the state of the cardiovascular system, and local features of unstructured data can be extracted and classified using deep learning. OBJECTIVE: The objective of this paper was to comprehensively use machine learning and deep learning classification methods to fully exploit the information about pulse signals. METHODS: Structured data were obtained by using time domain and time frequency domain analysis methods. A classification model was built using a support vector machine (SVM), a deep convolutional neural network (DCNN) kernel was used to extract local features of the unstructured data, and the stacking method was used to fuse the above classification results for decision making. RESULTS: The highest average accuracy of 0.7914 was obtained using only a single classifier, while the average accuracy obtained using the ensemble learning approach was 0.8330. CONCLUSIONS: Ensemble learning can effectively use information from structured and unstructured data to improve classification accuracy through decision-level fusion. This study provides a new idea and method for pulse signal classification, which is of practical value for pulse diagnosis objectification.