Trying to provide ultrasonic image-aid measures for quantitative diagnosis and dynamic monitoring of liver fibrosis, we propose two scoring methods for liver fibrosis tissue in vivo, based on ultrasound radio frequency (RF) time series in this paper. Firstly, RF echo signals of human liver were recorded in this study. Then one of the recorded frame RF data was demodulated to be B model image. After that, a region of interest (ROI) in the B model image was selected. For each point in the ROI, its all frame data were acquired so that RF time series were formed. An SMR (size measure relationship) fractal dimension and six spectral features were extracted from RF time series in the ROI. With relative deviation and Fisher's discriminant ratio, seven features were weighted and summed so that the liver tissues' scores were obtained, Score-rd and Score-fisher, respectively. Area under ROC curve (AUC) and a support vector machine (SVM) were used to evaluate whether these scoring methods would be useful in distinguishing normal and cirrhosis tissues. Experimental results are shown as follows: Score-rd's AUC was 0.843, while Score-fisher was 0.816, SVM classification accuracies were both up to 87.5%. This proved that our proposed scoring methods were effective in distinguishing normal and cirrhosis tissues. Score-rd and Score-fisher have potential for clinical applications. They can also provide quantitative references for liver fibrosis diagnosis.
The study of complex networks has become a hot research area of electroencephalogram signal. Electroencephalogram time series generated by the network keeps node information of network, so studying the time series from the network can also achieve the purpose of study epileptic electroencephalogram. In this paper, we propose a method to analyze epileptic electroencephalogram based on time series which is based on improved k-nearest neighbor network. The results of the experiment showed that studying power spectrum of time series from network was easier than power spectrum of time series directly generated from the original brain data to distinguish between normal controls and epileptic patients. In addition, studying the clustering coefficient of improved k-nearest neighbor network was able to distinguish between normal persons and patients with epilepsy. This study can provide important reference for the study of epilepsy and clinical diagnosis.
The interrupted time series analysis was used to evaluate the incentive effect of the management methods of the SCI thesis fund for scientific research in West China Hospital of Sichuan University. We found an increase in number of the SCI papers and the growth rate after the adoption of scientific research incentive measures, indicating that the management methods of the SCI thesis fund had the incentive effect of scientific research. The interrupted time series analysis could be used in the incentive analysis of scientific research.
Interrupted time series (ITS) analysis is a quasi-experimental design for evaluating the effectiveness of health interventions. By controlling the time trend before the intervention, ITS is often used to estimate the level change and slope change after the intervention. However, the traditional ITS modeling strategy might indicate aggregation bias when the data was collected from different clusters. This study introduced two advanced ITS methods of handling hierarchical data to provide the methodology framework for population-level health intervention evaluation.
Photoplethysmography (PPG) is often affected by interference, which could lead to incorrect judgment of physiological information. Therefore, performing a quality assessment before extracting physiological information is crucial. This paper proposed a new PPG signal quality assessment by fusing multi-class features with multi-scale series information to address the problems of traditional machine learning methods with low accuracy and deep learning methods requiring a large number of samples for training. The multi-class features were extracted to reduce the dependence on the number of samples, and the multi-scale series information was extracted by a multi-scale convolutional neural network and bidirectional long short-term memory to improve the accuracy. The proposed method obtained the highest accuracy of 94.21%. It showed the best performance in all sensitivity, specificity, precision, and F1-score metrics, compared with 6 quality assessment methods on 14 700 samples from 7 experiments. This paper provides a new method for quality assessment in small samples of PPG signals and quality information mining, which is expected to be used for accurate extraction and monitoring of clinical and daily PPG physiological information.
Objective To explore the impact of diagnosis-related group (DRG) payment method reform under total amount control on neurology and neurosurgery departments. Methods The DRG grouping data of the Department of Neurology and the Department of Neurosurgery of Panzhihua Central Hospital from January 2018 to December 2020 were collected, and the mature DRG evaluation indexes in China were selected. Using the interrupt time series analysis method, the DRG-related indexes of the two departments before and after the introduction of the performance appraisal plan in July 2019 were compared, to evaluate the intervention effects on the two departments. Results Both neurology and neurosurgery departments showed a slow downward trend in the overall medical service capacity under the DRG payment. The efficiency of medical services showed a slow upward trend and the consumption of medical expenses showed a slow downward trend in the Department of Neurology, while the efficiency of medical services showed a slow downward trend and the consumption of medical expenses showed a slow upward trend in the Department of Neurosurgery. According to the results of interrupt time series analysis, in the Department of Neurosurgery, the total weight showed a significant downward trend before intervention (β1=−5.526, P=0.003), and the downward trend became sluggish after intervention, with a statistically significant slope difference before and after intervention (β3=4.546, P=0.047); the case-mix index showed a downward trend before intervention (β1=−0.050, P<0.001), and no obvious trend after intervention, with a statistically significant slope difference before and after intervention (β3=0.052, P=0.001); the cost consumption index showed no obvious downward trend before intervention (β1=−0.006, P=0.258), and an upward trend after intervention, with a statistically significant slope difference before and after intervention (β3=0.027, P=0.032). The impact of this assessment plan on the Department of Neurology was not statistically significant (P>0.05), needing further observation. Conclusions The reform of DRG payment method under total amount control has different effects on the evaluation indicators of clinical departments of different natures. It is recommended to implement classified management and assessment for clinical departments of different natures.