The peak period of cardiovascular disease (CVD) is around the time of awakening in the morning, which may be related to the surge of sympathetic activity at the end of nocturnal sleep. This paper chose 140 participants as study object, 70 of which had occurred CVD events while the rest hadn’t during a two-year follow-up period. A two-layer model was proposed to investigate whether hypnopompic heart rate variability (HRV) was informative to distinguish these two types of participants. In the proposed model, the extreme gradient boosting algorithm (XGBoost) was used to construct a classifier in the first layer. By evaluating the feature importance of the classifier, those features with larger importance were fed into the second layer to construct the final classifier. Three machine learning algorithms, i.e., XGBoost, random forest and support vector machine were employed and compared in the second layer to find out which one can achieve the highest performance. The results showed that, with the analysis of hypnopompic HRV, the XGBoost+XGBoost model achieved the best performance with an accuracy of 84.3%. Compared with conventional time-domain and frequency-domain features, those features derived from nonlinear dynamic analysis were more important to the model. Especially, modified permutation entropy at scale 1 and sample entropy at scale 3 were relatively important. This study might have significance for the prevention and diagnosis of CVD, as well as for the design of CVD-risk assessment system.
Objective To quantitatively evaluate the effect of 2 types of pressures induced injury by using threedimensional (3D) reconstruction of rats loaded tibial is anterior muscle from two-dimensional (2D) image of serial histological sections. Methods Twenty female or male Sprague Dawley rats, aged 10-12 weeks and weighing 280-300 g, were randomlydivided into experimental group (n=10) and control group (n=10). The random side of tibial is anterior muscle was givenintermittent gradient (8.0-21.3 kPa) and sustained (13.3 kPa) pressure in 0.12 cm2 area in experimental group and controlgroup, respectively; the experiment was terminated and the general condition of rats was observed after 3 cycles, and a single cycle included 2 hours of compression and 30 minutes of release. The general observations of pressed skin and tibial is anterior muscle were done after 24 hours of pressure rel ief, and the tibial is anterior muscle was harvested integrally from the loaded side, then made into interval 4 μm serial sections. After HE staining, 2D images were obtained. Necrosis and injury areas were distinguished by Image Pro Plus (IPP) 6.0 software and image registration was conducted by Photoshop 8.0.1 after 2D panorama images acquired by digital microscope (× 40) and IPP mosaic software. 3D reconstruction was establ ished via data processing using Mimics 10.1 software so as to get the volume, the surface area, and 3D images of the whole piece of tibial is anterior muscle and injury areas respectively. Results All rats of 2 groups survived till experiment terminated and no skin ulcers occurred after 24 hours. Edema and indentation were observed on press side skin and tibial is anterior muscles of 2 groups, fadeless maroon area was observed in control group. A total of 994 sl ices were obtained from 20 samples of tibial is anterior muscles. 3D images suggested that injury of control group was severe, which penetrated the whole piece of tibial is anterior muscle and expandedalong the tibia bony prominence. By contrast, injury of experimental group was less, but had similar width to the contact surface of indentor. There was no significant difference in the volume and the surface area of tibial is anterior muscle between 2 groups (P gt; 0.05), while the injury volume and the injury surface area were significantly smaller in experimental group than in control group (P lt; 0.05). Conclusion 3D reconstruction is an effective method to quantitatively evaluate pathological changes inside the integrity tissue and can provide the visual basis for the mechanical property distributed in the loaded muscle. Intermittent gradient pressure can reduce deep tissue injury.
ObjectivesTo investigate simple assess method of the degree of low transvalvular gradient aortic stenosis patients with impaired left ventricular function and to investigate aortic valve replacement indications, short and mid-term outcome of this kind of patients. MethodsWe retrospectively analyzed the clinical data of 21 low-gradient patients with impaired left ventricular function in our hospital from January 2011 through May 2014. There were 15 males and 6 females aged 41-66 (54.6± 10.7) years with mean aortic transvalvular gradient less than 40 mm Hg and left ventricular ejection fraction (LVEF) less than 50%. ResultsIn response to dobutamine echocardiography stress test, 20 patients underwent aortic valve replacement. The result of intraoperative pathology showed 11 patients were with bicuspid aortic valve malformation, 4 patients with degenerative changes, 4 patients with rheumatic disease. During the same period, 3 patients underwent atrial fibrillation ablation, 1 patient with ascending aorta replacement, 2 patients with coronary artery bypass grafting, 1 patient with mitral valvuloplasty. One patient died of multiple organ failure on the fourth day after operation. The remaining patients recovered. The patients were followed up for 3 to 37 months after operation. Heart function of majority improved to gradeⅠorⅡin 3 months after surgery. The result of echocardiogram showed prosthetic valve function was good and LVEF increased (preoperative 35.7%± 8.2% vs. postoperative 49.4%± 7.2%). One patient suffered sudden death of unknown cause in the 11th months after operation. ConclusionsFor patients whose dobutamine echocardiography stress test displayed with true severe aortic stenosis and left ventricular contractile reserve capacity, after aortic valve replacement and relief of the obstruction, the left ventricular afterload decreases significantly, the left ventricular function also improves, LVEF and the quality of life improve significantly after operation.
Aiming at the problems of obscure clinical auscultation features of pulmonary hypertension associated with congenital heart disease and the complexity of existing machine-aided diagnostic algorithms, an algorithm based on the statistical characteristics of the high-frequency components of the second heart sound signal is proposed. Firstly, an endpoint detection adaptive segmentation method is employed to extract the second heart sounds. Subsequently, the high-frequency component of the heart sound is decomposed using the discrete wavelet transform. Statistical features including the Hurst exponent, Lempel-Ziv information and sample entropy are extracted from this component. Finally, the extracted features are utilized to train an extreme gradient boosting algorithm (XGBoost) classifier, which achieves an accuracy of 80.45% in triple classification. Notably, this method eliminates the need for a noise reduction algorithm, allows for swift feature extraction, and achieves effective multi-classification using only three features. It is promising for early screening of pulmonary hypertension associated with congenital heart disease.
Heart sound is one of the common medical signals for diagnosing cardiovascular diseases. This paper studies the binary classification between normal or abnormal heart sounds, and proposes a heart sound classification algorithm based on the joint decision of extreme gradient boosting (XGBoost) and deep neural network, achieving a further improvement in feature extraction and model accuracy. First, the preprocessed heart sound recordings are segmented into four status, and five categories of features are extracted from the signals based on segmentation. The first four categories of features are sieved through recursive feature elimination, which is used as the input of the XGBoost classifier. The last category is the Mel-frequency cepstral coefficient (MFCC), which is used as the input of long short-term memory network (LSTM). Considering the imbalance of the data set, these two classifiers are both improved with weights. Finally, the heterogeneous integrated decision method is adopted to obtain the prediction. The algorithm was applied to the open heart sound database of the PhysioNet Computing in Cardiology(CINC) Challenge in 2016 on the PhysioNet website, to test the sensitivity, specificity, modified accuracy and F score. The results were 93%, 89.4%, 91.2% and 91.3% respectively. Compared with the results of machine learning, convolutional neural networks (CNN) and other methods used by other researchers, the accuracy and sensibility have been obviously improved, which proves that the method in this paper could effectively improve the accuracy of heart sound signal classification, and has great potential in the clinical auxiliary diagnosis application of some cardiovascular diseases.
In order to establish a bone scaffold with good biological properties, two kinds of new gradient triply periodic minimal surfaces (TPMS) scaffolds, i.e., two-way linear gradient G scaffolds (L-G) and D, G fusion scaffold (N-G) were designed based on the gyroid (G) and diamond (D)-type TPMS in this study. The structural mechanical parameters of the two kinds of scaffolds were obtained through the compressive simulation. The flow property parameters were also obtained through the computational fluid dynamics (CFD) simulation in this study, and the permeability of the two kinds of scaffolds were calculated by Darcy's law. The tissue differentiation areas of the two kinds of scaffolds were calculated based on the tissue differentiation theory. The results show that L-G scaffold has a better mechanical property than the N-G scaffold. However, N-G scaffold is better than the L-G scaffold in biological properties such as permeability and cartilage differentiation areas. The modeling processes of L-G and N-G scaffolds provide a new insight for the design of bone scaffold. The simulation in this study can also give reference for the prediction of osseointegration after the implantation of scaffold in the human body.
Objective To analyze the relationship between end-tidal carbon dioxide partial pressure (PETCO2) and arterial CO2 pressure (PaCO2) in invasive ventilated patients. Methods An observational study was conducted in adult patients admitted to Intensive Care Unit (ICU) between June 2016 and March 2017. Samples were immediately analyzed for PaCO2 using a blood gas analyzer. At the same time the arterial to end-tidal CO2 gradient was determined. Relationship in different mechanical ventilation modes, disease categories and PaO2/FiO2 were analyzed in this study. Results A total of 225 arterial blood gases were obtained from the 104 patients. In each of these modes the PETCO2 was generally lower than the PaCO2. There was a positive correlation between PaCO2 and PETCO2 regardless of different mode (r=0.70, Y=11.08+0.77X). A positive correlation was found in SIMV and SPONT modes, but not in A/C mode. The relationship between PaCO2 and PETCO2 in COPD, trauma, cerebrovascular disease and severe pneumonia patients shown a positive correlation (r value was 0.76, 0.64, 0.53, and 0.56, respectively). There was a significant correlation whether PaCO2/FiO2<200 mm Hg (r=0.69, P<0.001) or ≥200 mm Hg (r=0.71, P<0.001). Conclusions The results of this study show that PETCO2 monitoring accurately reflects PaCO2 during mechanical ventilation. A positive correlation is found in different ventilation modes, regardless of disease categories or PaCO2/FiO2.
ObjectiveTo investigate the perioperative hemodynamic changes of off-pump coronary artery bypass grafting (OPCABG) patients monitored by pulse recorded analysis method (MostCare/PRAM devices) and its relationship with the prognosis.MethodsA total of 89 patients who underwent OPCABG from October 2016 to January 2017 in Beiijng Anzhen Hospital were included, including 53 males and 36 females aged 60.50±8.40 years. The hemodynamic changes were recorded. The patients were divided into two groups (a major adverse cardiovascular events group and a stable group) according to whether major adverse cardiovascular events occurred or not. The difference of hemodynamic changes between the two groups was analysed.ResultsThe mean percentage increases of stroke volume (SV) in the passive leg raising (PLR) test before opening chest and after chest closure were 23.00%±3.20% and 29.40%±3.70%, respectively. Hemodynamic data were analysed seven times, namely, anaesthesia, opening chest, heparin administration, coronary artery bypass grafting, protamine administration, thoracic closure and after operation. SV was significantly decreased during above periods, while systemic vascular resistance index (SVRI) was significantlyincreased. Cardiac circle efficiency (CCE) and maximum pressure gradient (dP/dT) were decreased after anaesthesia, and decreased to the lowest value during the procedure of bypass grafting, and then they began to increase gradually after the manipulation of bypass grafting was finished. Stroke volume variation (SVV) and pulse pressure variation (PPV) were slightly decreased during anaesthesia, then increased significantly through the whole surgery. Major adverse cardiovascular events occurred in 9 patients and 4 of them died. The basic mean values of SVRI, SVV and PPV of patients in the major adverse cardiovascular events group before opening chest were significantly higher than those of patients in the stable group. There was no significant difference in the mean values of CCE, dP/dT or SV between the two groups. There was no significant correlation between the prognosis and the mean values of SVRI, SVV, PPV, CCE, dP/dT or SV.ConclusionThe hemodynamic indexes are not stable, thus, it is necessary to monitor the perioperative hemodynamic changes of OPCABG patients timely by MostCare/PRAM device and adjust treatment measures accordingly.
Objective To propose an innovative self-supervised learning method for vascular segmentation in computed tomography angiography (CTA) images by integrating feature reconstruction with masked autoencoding. Methods A 3D masked autoencoder-based framework was developed, where in 3D histogram of oriented gradients (HOG) was utilized for multi-scale vascular feature extraction. During pre-training, random masking was applied to local patches of CTA images, and the model was trained to jointly reconstruct original voxels and HOG features of masked regions. The pre-trained model was further fine-tuned on two annotated datasets for clinical-level vessel segmentation. Results Evaluated on two independent datasets (30 labeled CTA images each), our method achieved superior segmentation accuracy to the supervised neural network U-Net (nnU-Net) baseline, with Dice similarity coefficients of 91.2% vs. 89.7% (aorta) and 84.8% vs. 83.2% (coronary arteries). Conclusion The proposed self-supervised model significantly reduces manual annotation costs without compromising segmentation precision, showing substantial potential for enhancing clinical workflows in vascular disease management.
Pulsed magnetic field gradients generated by gradient coils are widely used in signal location in magnetic resonance imaging (MRI). However, gradient coils can also induce eddy currents in final magnetic field in the nearby conducting structures which lead to distortion and artifact in images, misguiding clinical diagnosis. We tried in our laboratory to measure the magnetic field of gradient-induced eddy current in 1.5 T superconducting magnetic resonance imaging device; and extracted key parameters including amplitude and time constant of exponential terms according to inductance-resistance series mathematical module. These parameters of both self-induced component and crossing component are useful to design digital filters to implement pulse pre-emphasize to reshape the waveform. A measure device that is a basement equipped with phantoms and receiving coils was designed and placed in the isocenter of the magnetic field. By applying testing sequence, contrast experiments were carried out in a superconducting magnet before and after eddy current compensation. Sets of one dimension signal were obtained as raw data to calculate gradient-induced eddy currents. Curve fitting by least squares method was also done to match inductance-resistance series module. The results also illustrated that pulse pre-emphasize measurement with digital filter was correct and effective in reducing eddy current effect. Pre-emphasize waveform was developed based on system function. The usefulness of pre-emphasize measurement in reducing eddy current was confirmed and the improvement was also presented. All these are valuable for reducing artifact in magnetic resonance imaging device.