An XGBoost-based model for assessment of aortic stiffness from wrist photoplethysmogram.

BACKGROUND AND OBJECTIVE: Carotid-femoral pulse wave velocity (cf-PWV) is the gold standard for non-invasive assessment of aortic stiffness. Photoplethysmography used in wearable devices provides an indirect measurement method for cf-PWV. This study aimed to construct a cf-PWV prediction method based on the XGBoost algorithm and wrist photoplethysmogram (wPPG) for the early screening of arteriosclerosis in primary healthcare. METHODS: Data from 210 subjects were used for modeling, and 100 subjects were used as an external validation set. The wPPG pulse waves were filtered by discrete wavelet transform, and various features were extracted from each waveform, including two original indexes. The extraction rate (ER) and Pearson P were calculated to evaluate the applicability of each feature for model training. The magnitude of cf-PWV was predicted by an XGBoost-based model using the selected features and basic physiological parameters (age, sex, height, weight and BMI). The level of aortic stiffness was classified by a 3-classification strategy according to the standard cf-PWV (measured by the Complior device). Bland-Altman plot, Pearson correlation analysis, and accuracy tested performance from two aspects: predicting the magnitude of cf-PWV and classifying the level of aortic stiffness. RESULTS: In the external validation set (n = 100, age range 22-79), 97 subjects obtained features (ER = 97%). The predicted cf-PWV was significantly correlated with the standard cf-PWV (r = 0.927, P < 0.001). The accuracy (AC) of the 3-classification was 85.6%. The interrater agreement for assessing aortic stiffness was at least substantial (quadratically weighted Kappa = 0.833). CONCLUSIONS: The multi-parameter fusion cf-PWV prediction method based on the XGBoost algorithm and wPPG pulse wave analysis proves the feasibility of atherosclerosis screening in wearable devices.

Predicting the Risk of Hypertension Based on Several Easy-to-Collect Risk Factors: A Machine Learning Method.

Hypertension is a widespread chronic disease. Risk prediction of hypertension is an intervention that contributes to the early prevention and management of hypertension. The implementation of such intervention requires an effective and easy-to-implement hypertension risk prediction model. This study evaluated and compared the performance of four machine learning algorithms on predicting the risk of hypertension based on easy-to-collect risk factors. A dataset of 29,700 samples collected through a physical examination was used for model training and testing. Firstly, we identified easy-to-collect risk factors of hypertension, through univariate logistic regression analysis. Then, based on the selected features, 10-fold cross-validation was utilized to optimize four models, random forest (RF), CatBoost, MLP neural network and logistic regression (LR), to find the best hyper-parameters on the training set. Finally, the performance of models was evaluated by AUC, accuracy, sensitivity and specificity on the test set. The experimental results showed that the RF model outperformed the other three models, and achieved an AUC of 0.92, an accuracy of 0.82, a sensitivity of 0.83 and a specificity of 0.81. In addition, Body Mass Index (BMI), age, family history and waist circumference (WC) are the four primary risk factors of hypertension. These findings reveal that it is feasible to use machine learning algorithms, especially RF, to predict hypertension risk without clinical or genetic data. The technique can provide a non-invasive and economical way for the prevention and management of hypertension in a large population.

Olivary particles: unique carbon microstructure synthesized by catalytic pyrolysis of acetone.

Olivary (olive-shaped) carbon particles (OCPs) with a diameter of approximately 1.5-2 mum at the middle and a length of approximately 3-4 mum were synthesized by pyrolysis of acetone with metallic zinc as the catalyst at 600 degrees C. The content of the OCPs in the product is related to the catalyst, the pyrolysis temperature, and the time of ultrasonic dispersion before pyrolysis. The content of the OCPs was over 90% of the product under the optimum condition. Mg, Ni, Fe, Cu, Zn, and Cd powder were used as catalysts in the experiments, respectively, in which the metallic zinc powder was outstanding in the pyrolyzing process; the metallic iron and cadmium powder also improved the formation of the olivary carbon particles; however, magnesium, nickel, and copper could not operate the catalysis. Through Fourier transform infrared spectroscopy analysis, the mechanism of the formation of the olivary carbon particles was suggested to be an indirectly catalytic and self-assemble process. By high-resolution transmission electron microscope observation, an interesting arrangement of crystal planes of carbon was found that (002) planes of graphite near the surface are vertical to the surface of the OCPs and not parallel as usual.

[Imaging features of urinary dysfunction associated with ketamine abuse].

OBJECTIVE: To summarize the imaging features of urinary dysfunction associated with ketamine abuse (KAUD) for imaging diagnosis of KAUD. METHODS: We analyzed the imaging findings in 45 patients with KAUD, all having a history of ketamine abuse and presenting with severe lower urinary tract symptoms. The patients underwent imaging examinations with ultrasonography (n=45), X-ray (n=38), computed tomography (n=28), magnetic resonance imaging (n=10) or single photon emission computed tomography (n=25), and the results were classified and evaluated to identify the common imaging findings. RESULTS: The imaging changes of KAUD were found primarily in the urinary and biliary system. The most common imaging characteristics included thickening of the bladder wall, contracture and decreased functional volume of the bladder, dilation of the ureter and hydronephrosis, stricture of the upper ureter, renal impairment, dilation of the biliary system, and inflammation or swelling of the adjacent organs and lymph nodes CONCLUSION: KAUD presents with typical imaging changes. Radiologists should be aware of KAUD if the typical imaging features are detected, especially in cases with a history of ketamine abuse.