Background: We should pay more attention to the long-term monitoring and early warning of type 2 diabetes and its complications. The traditional blood glucose tests are traumatic and cannot effectively monitor the development of diabetic complications. The development of mobile health is changing rapidly. Therefore, we are interested in developing a new noninvasive, economical, and instant-result method to accurately diagnose and monitor type 2 diabetes and its complications. Objective: We aimed to determine whether type 2 diabetes and its complications, including hypertension and hyperlipidemia, could be diagnosed and monitored by using pulse wave. Methods: We collected the pulse wave parameters from 50 healthy people, 139 diabetic patients without hypertension and hyperlipidemia, 133 diabetic patients with hypertension, 70 diabetic patients with hyperlipidemia, and 75 diabetic patients with hypertension and hyperlipidemia. The pulse wave parameters showing significant differences among these groups were identified. Various machine learning models such as linear discriminant analysis, support vector machines (SVMs), and random forests were applied to classify the control group, diabetic patients, and diabetic patients with complications. Results: There were significant differences in several pulse wave parameters among the 5 groups. The parameters height of tidal wave (h3), time distance between the start point of pulse wave and dominant wave (t1), and width of percussion wave in its one-third height position (W) increase and the height of dicrotic wave (h5) decreases when people develop diabetes. The parameters height of dominant wave (h1), h3, and height of dicrotic notch (h4) are found to be higher in diabetic patients with hypertension, whereas h5 is lower in diabetic patients with hyperlipidemia. For detecting diabetes, the method with the highest out-of-sample prediction accuracy is SVM with polynomial kernel. The algorithm can detect diabetes with 96.35% accuracy. However, all the algorithms have a low accuracy when predicting diabetic patients with hypertension and hyperlipidemia (below 70%). Conclusions: The results demonstrated that the noninvasive and convenient pulse-taking diagnosis described in this paper has the potential to become a low-cost and accurate method to monitor the development of diabetes. We are collecting more data to improve the accuracy for detecting hypertension and hyperlipidemia among diabetic patients. Mobile devices such as sport bands, smart watches, and other diagnostic tools are being developed based on the pulse wave method to improve the diagnosis and monitoring of diabetes, hypertension, and hyperlipidemia.

The pulse measurement instrument is based on traditional Chinese medicine (TCM) and is used to collect the pulse of patients to assist in diagnosis and treatment. In the existing pulse measurement system, desktop devices have large volumes, complex pressure adjusting operations, and unstable pressurization. Wearable devices tend to have no pressurization function or the function to pressurize three channels separately, which are not consistent with the diagnostic method in TCM. This study constructs a wearable pulse measurement system using airbags for pressurization. This system uses guide plates, guide grooves, and positioning screws to adjust the relative position of the wristband and locate Cun, Guan and Chi regions. The pulse signal measured by the sensor is collected and sent to a computer by microcontroller unit. In experiments, this system successfully obtains the best pulse-taking pressure, its pulse waveform under continuous decompression, and the pulse waveform of three regions under light, medium, and heavy pressure. Compared with the existing technology, the system has the advantages of supporting single-region and three-region pulse acquisition, independent pressure adjustment, and position adjustment. It meets the needs of home, medical, and experimental research, and it is convenient and comfortable to wear and easy to carry.

Background. Cardiovascular diseases have been always the most common cause of morbidity and mortality worldwide. Health monitoring of high‐risk and suspected patients is essential. Currently, invasive coronary angiography is still the most direct and accurate method of determining the severity of coronary artery lesions, but it may not be the optimal clinical choice for suspected patients who had clinical symptoms of coronary heart disease (CHD) such as chest pain but no coronary artery lesion. Modern medical research indicates that radial pulse waves contain substantial pathophysiologic information about the cardiovascular and circulation systems; therefore, analysis of these waves could be a noninvasive technique for assessing cardiovascular disease. Objective. The objective of this study was to analyze the radial pulse wave to construct models for assessing the extent of coronary artery lesions based on pulse features and investigate the latent value of noninvasive detection technology based on pulse wave in the evaluation of cardiovascular disease, so as to promote the development of wearable devices and mobile medicine. Method. This study included 529 patients suspected of CHD who had undergone coronary angiography. Patients were sorted into a control group with no lesions, a 1 or 2 lesion group, and a multiple (3 or more) lesion group as determined by coronary angiography. The linear time‐domain features and the nonlinear multiscale entropy features of their radial pulse wave signals were compared, and these features were used to construct models for identifying the range of coronary artery lesions using the k‐nearest neighbor (KNN), decision tree (DT), and random forest (RF) machine learning algorithms. The average precision of these algorithms was then compared. Results. (1) Compared with the control group, the group with 1 or 2 lesions had increases in their radial pulse wave time‐domain features H2/H1, H3/H1, and W2 (P < 0.05), whereas the group with multiple lesions had decreases in MSE1, MSE2, MSE3, MSE4, and MSE5 (P < 0.05). (2) Compared with the 1 or 2 lesion group, the multiple lesion group had increases in T1/T (P < 0.05) and decreases in T and W1 (P < 0.05). (3) The RF model for identifying numbers of coronary artery lesions had a higher average precision than the models built with KNN or DT. Furthermore, average precision of the model was highest (80.98%) if both time‐domain features and multiscale entropy features of radial pulse signals were used to construct the model. Conclusion. Pulse wave signal can identify the range of coronary artery lesions with acceptable accuracy; this result is promising valuable for assessing the severity of coronary artery lesions. The technique could be used to development of mobile medical treatments or remote home monitoring systems for patients suspected or those at high risk of coronary atherosclerotic heart disease.

The performance of gas sensors based on micro-heater is highly dependent on the environment temperature, heater temperature, and gas flow rate. The performance fluctuation of gas sensors induced by environment temperature drift can be reduced in different ways. In this article, different sizes and shapes of obstacles are placed around the sensitive component of the thermal conductivity gas sensor to study the effect of gas flow rate on the gas sensor performance. Both the simulation and experiment results indicate that the obstacle design can reduce the interference of gas flow rate on gas sensor performance. As the obstacle size increases, the influence of gas flow rate decreases and the dynamic detection accuracy of the gas sensor increases at the same gas flow rate, and the voltage variation of the sensor with quadrangular prism obstacle shape is minimal, and the gas velocity reduction effect is 1.77% better than cylinder obstacle shape. The effect of gas flow rate on the gas response is also investigated by detecting the voltage response of the MG811 gas sensor with and without thermostatical control. The result shows that the gas flow rate not only reduces the temperature of the sensor (direct influence), but also promotes the chemical reaction of the sensor, which releases a large amount of heat (indirect influence). The corresponding relationship between voltage response and gas flow rate is obtained through controlling the temperature of sensitive components thermostatically. This article provides a new angle for improving the accuracy of the gas sensor in different gas flow rate environments, which can improve the detection rate of the wireless monitoring system.

Traditional diagnostic methods for asthma, a widespread chronic respiratory illness, are often limited by factors such as patient cooperation with spirometry. Non-invasive acoustic analysis using machine learning offers a promising alternative for objective diagnosis by analyzing vocal characteristics. This study aimed to develop and validate a robust classification model for adult asthma using acoustic features from the vocalized /ɑː/ sound. In a case-control study, voice recordings of the /ɑː/ sound were collected from a primary cohort of 214 adults and an independent external validation cohort of 200 adults. This study extracted features using a modified extended Geneva Minimalistic Acoustic Parameter Set and compared seven machine learning models. The top-performing model, Extreme Gradient Boosting, was further assessed through ten-fold cross-validation, external validation, and feature analysis using SHapley Additive exPlanations and Local Interpretable Model-Agnostic Explanations. The Extreme Gradient Boosting classifier achieved the highest performance on the test set, with an accuracy of 0.8514, an Area Under the Curve of 0.9130, a recall of 0.8804, a precision of 0.8387, an F1-score of 0.8567, a Kappa coefficient of 0.7018, and a Matthews Correlation Coefficient of 0.7071. On the external validation set, the model maintained strong performance with an accuracy of 0.8100, AUC of 0.8755, recall of 0.8300, precision of 0.7981, F1-score of 0.8137, Kappa of 0.6200, and Matthews Correlation Coefficient of 0.6205. Interpretability analysis identified formant frequencies as the most significant acoustic predictors. An Extreme Gradient Boosting model utilizing features from the extended Geneva Minimalistic Acoustic Parameter Set is an accurate and viable non-invasive method for classifying adult asthma, holding significant potential for developing accessible tools for early diagnosis, remote monitoring, and improved asthma management.

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.