Objective To analyze the crucial factors which affect the hospitalization expenses of patients with uterine adenomyosis, in order to take corresponding measures. Methods A total of 583 patients diagnosed with uterine fibroids reported by hospitals in urban areas of Suining city through hospital quality monitoring system between December 2013 and December 2015 were included in this study. The main reasons for the expense structure was described by Pareto’s law. The importance of hospitalization expense influencing factors was analyzed by neural network model, and single factor analysis was used to analyze important influencing factors of hospitalization expenses. Results The main factors influencing hospitalization expenses included length of stay in hospital, operation techniques and illness conditions, and their importance value was respectively 0.581, 0.175 and 0.088. Conclusion Based on hospitalization expenses, length of stay in hospital and expense structure, high intensity focused ultrasound therapy is more reasonable in the treatment of uterine adenomyosis.
ObjectivesTo explore the value of neural networks (NN) in estimating propensity score, and to compare the performance of propensity score methods based on both logistic regression (LR) and NN.MethodsData sets including ten binary or continuous covariates, binary treatment variable and continuous outcome variable were simulated by SAS 9.2 software, and 5 scenarios differing by non-linear and/or non-additive associations between treatment assignment and covariates were set up. The sample sizes 500, 1000, 2000, 5000 and 10000 were considered. Propensity scores were estimated using either LR or NN model using only partial covariates associated with the outcome (methods LR1, NN1), or all covariates associated with either outcome or treatment (methods LR2, NN2). The average treatment effect (ATE) estimates, standard error (SE), bias, and mean square error (MSE) of ATE among the different models were compared.ResultsThe 95% confidence intervals of the average treatment effect were narrower in NN than that in LR models. SE, bias and MSE increased with the increasing complexity of non-linear and/or non-additive associations between the treatment and covariates, and smaller SE, bias, and MSE were observed in LR1 than LR2, and in NN1 than NN2. NN generally produced less bias than LR under most scenarios when variables associated with the outcome were introduced. SE and MSE decreased with the increasing sample size for both LR and NN models.ConclusionsNN for estimating propensity scores may be less biased and produce more precise estimates for ATE than LR in a meaningful manner when the complex association between treatment and covariates exists.
ObjectiveTo observe and analyze the accuracy of the optic disc positioning and segmentation method of fundus images based on deep learning.MethodsThe model training strategies were training and evaluating deep learning-based optic disc positioning and segmentation methods on the ORIGA dataset. A deep convolutional neural network (CNN) was built on the Caffe framework of deep learning. A sliding window was used to cut the original image of the ORIGA data set into many small pieces of pictures, and the deep CNN was used to determine whether each small piece of picture contained the complete disc structure, so as to find the area of the disc. In order to avoid the influence of blood vessels on the segmentation of the optic disc, the blood vessels in the optic disc area were removed before segmentation of the optic disc boundary. A deep network of optic disc segmentation based on image pixel classification was used to realize the segmentation of the optic disc of fundus images. The accuracy of the optic disc positioning and segmentation method was calculated based on deep learning of fundus images. Positioning accuracy=T/N, T represented the number of fundus images with correct optic disc positioning, and N represented the total number of fundus images used for positioning. The overlap error was used to compare the difference between the segmentation result of the optic disc and the actual boundary of the optic disc.ResultsOn the dataset from ORIGA, the accuracy of the optic disc localization can reach 99.6%, the average overlap error of optic disc segmentation was 7.1%. The calculation errors of the average cup-to-disk ratio for glaucoma images and normal images were 0.066 and 0.049, respectively. Disc segmentation of each image took an average of 10 ms.ConclusionThe algorithm can locate the disc area quickly and accurately, and can also segment the disc boundary more accurately.
ObjectiveTo apply the multi-modal deep learning model to automatically classify the ultra-widefield fluorescein angiography (UWFA) images of diabetic retinopathy (DR). MethodsA retrospective study. From 2015 to 2020, 798 images of 297 DR patients with 399 eyes who were admitted to Eye Center of Renmin Hospital of Wuhan University and were examined by UWFA were used as the training set and test set of the model. Among them, 119, 171, and 109 eyes had no retinopathy, non-proliferative DR (NPDR), and proliferative DR (PDR), respectively. Localization and assessment of fluorescein leakage and non-perfusion regions in early and late orthotopic images of UWFA in DR-affected eyes by jointly optimizing CycleGAN and a convolutional neural network (CNN) classifier, an image-level supervised deep learning model. The abnormal images with lesions were converted into normal images with lesions removed using the improved CycleGAN, and the difference images containing the lesion areas were obtained; the difference images were classified by the CNN classifier to obtain the prediction results. A five-fold cross-test was used to evaluate the classification accuracy of the model. Quantitative analysis of the marker area displayed by the differential images was performed to observe the correlation between the ischemia index and leakage index and the severity of DR. ResultsThe generated fake normal image basically removed all the lesion areas while retaining the normal vascular structure; the difference images intuitively revealed the distribution of biomarkers; the heat icon showed the leakage area, and the location was basically the same as the lesion area in the original image. The results of the five-fold cross-check showed that the average classification accuracy of the model was 0.983. Further quantitative analysis of the marker area showed that the ischemia index and leakage index were significantly positively correlated with the severity of DR (β=6.088, 10.850; P＜0.001). ConclusionThe constructed multimodal joint optimization model can accurately classify NPDR and PDR and precisely locate potential biomarkers.
ObjectiveTo propose automatic measurement of global and local tessellation density on color fundus images based on a deep convolutional neural network (DCNN) method. MethodsAn applied study. An artificial intelligence (AI) database was constructed, which contained 1 005 color fundus images captured from 1 024 eyes of 514 myopic patients in the Northern Hospital of Qingdao Eye Hospital from May to July, 2021. The images were preprocessed by using RGB color channel re-calibration method (CCR algorithm), CLAHE algorithm based on Lab color space, Retinex algorithm for multiple iterative illumination estimation, and multi-scale Retinex algorithm. The effects on the segmentation of tessellation by adopting the abovemetioned image enhancement methods and utilizing the Dice, Edge Overlap Rate and clDice loss were compared and observed. The tessellation segmentation model for extracting the tessellated region in the full fundus image as well as the tissue detection model for locating the optic disc and macular fovea were built up. Then, the fundus tessellation density (FTD), macular tessellation density (MTD) and peripapillary tessellation density (PTD) were calculated automatically. ResultsWhen applying CCR algorithm for image preprocessing and the training losses combination strategy, the Dice coefficient, accuracy, sensitivity, specificity and Jordan index for fundus tessellation segmentation were 0.723 4, 94.25%, 74.03%, 96.00% and 70.03%, respectively. Compared with the manual annotations, the mean absolute errors and root mean square errors of FTD, MTD, PTD automatically measured by the model were 0.014 3, 0.020 7, 0.026 7 and 0.017 8, 0.032 3, 0.036 5, respectively. ConclusionThe DCNN-based segmentation and detection method can automatically measure the tessellation density in the global and local regions of the fundus of myopia patients, which can more accurately assist clinical monitoring and evaluation of the impact of fundus tessellation changes on the development of myopia.
Aiming at the problems of individual differences in the asynchrony process of human lower limbs and random changes in stride during walking, this paper proposes a method for gait recognition and prediction using motion posture signals. The research adopts an optimized gated recurrent unit (GRU) network algorithm based on immune particle swarm optimization (IPSO) to establish a network model that takes human body posture change data as the input, and the posture change data and accuracy of the next stage as the output, to realize the prediction of human body posture changes. This paper first clearly outlines the process of IPSO's optimization of the GRU algorithm. It collects human body posture change data of multiple subjects performing flat-land walking, squatting, and sitting leg flexion and extension movements. Then, through comparative analysis of IPSO optimized recurrent neural network (RNN), long short-term memory (LSTM) network, GRU network classification and prediction, the effectiveness of the built model is verified. The test results show that the optimized algorithm can better predict the changes in human posture. Among them, the root mean square error (RMSE) of flat-land walking and squatting can reach the accuracy of 10−3, and the RMSE of sitting leg flexion and extension can reach the accuracy of 10−2. The R2 value of various actions can reach above 0.966. The above research results show that the optimized algorithm can be applied to realize human gait movement evaluation and gait trend prediction in rehabilitation treatment, as well as in the design of artificial limbs and lower limb rehabilitation equipment, which provide a reference for future research to improve patients' limb function, activity level, and life independence ability.
The electroencephalogram (EEG) signal is a general reflection of the neurophysiological activity of the brain, which has the advantages of being safe, efficient, real-time and dynamic. With the development and advancement of machine learning research, automatic diagnosis of Alzheimer’s diseases based on deep learning is becoming a research hotspot. Started from feedforward neural networks, this paper compared and analysed the structural properties of neural network models such as recurrent neural networks, convolutional neural networks and deep belief networks and their performance in the diagnosis of Alzheimer’s disease. It also discussed the possible challenges and research trends of this research in the future, expecting to provide a valuable reference for the clinical application of neural networks in the EEG diagnosis of Alzheimer’s disease.
Cardiovascular disease is the leading cause of death worldwide, accounting for 48.0% of all deaths in Europe and 34.3% in the United States. Studies have shown that arterial stiffness takes precedence over vascular structural changes and is therefore considered to be an independent predictor of many cardiovascular diseases. At the same time, the characteristics of Korotkoff signal is related to vascular compliance. The purpose of this study is to explore the feasibility of detecting vascular stiffness based on the characteristics of Korotkoff signal. First, the Korotkoff signals of normal and stiff vessels were collected and preprocessed. Then the scattering features of Korotkoff signal were extracted by wavelet scattering network. Next, the long short-term memory (LSTM) network was established as a classification model to classify the normal and stiff vessels according to the scattering features. Finally, the performance of the classification model was evaluated by some parameters, such as accuracy, sensitivity, and specificity. In this study, 97 cases of Korotkoff signal were collected, including 47 cases from normal vessels and 50 cases from stiff vessels, which were divided into training set and test set according to the ratio of 8 : 2. The accuracy, sensitivity and specificity of the final classification model was 86.4%, 92.3% and 77.8%, respectively. At present, non-invasive screening method for vascular stiffness is very limited. The results of this study show that the characteristics of Korotkoff signal are affected by vascular compliance, and it is feasible to use the characteristics of Korotkoff signal to detect vascular stiffness. This study might be providing a new idea for non-invasive detection of vascular stiffness.
Electromagnetic stimulation is an important neuromodulation technique that modulates the electrical activity of neurons and affects cortical excitability for the purpose of modulating the nervous system. The phenomenon of inverse stochastic resonance is a response mechanism of the biological nervous system to external signals and plays an important role in the signal processing of the nervous system. In this paper, a small-world neural network with electrical synaptic connections was constructed, and the inverse stochastic resonance of the small-world neural network under electromagnetic stimulation was investigated by analyzing the dynamics of the neural network. The results showed that: the Levy channel noise under electromagnetic stimulation could cause the occurrence of inverse stochastic resonance in small-world neural networks; the characteristic index and location parameter of the noise had significant effects on the intensity and duration of the inverse stochastic resonance in neural networks; the larger the probability of randomly adding edges and the number of nearest neighbor nodes in small-world networks, the more favorable the anti-stochastic resonance was; by adjusting the electromagnetic stimulation parameters, a dual regulation of the inverse stochastic resonance of the neural network can be achieved. The results of this study provide some theoretical support for exploring the regulation mechanism of electromagnetic nerve stimulation technology and the signal processing mechanism of nervous system.
ObjectiveTo construct a prediction model of diabetics distal symmetric polyneuropathy (DSPN) based on neural network algorithm and the characteristic data of traditional Chinese medicine and Western medicine. MethodsFrom the inpatients with diabetes in the First Affiliated Hospital of Anhui University of Chinese Medicine from 2017 to 2022, 4 071 cases with complete data were selected. The early warning model of DSPN was established by using neural network, and 49 indicators including general epidemiological data, laboratory examination, signs and symptoms of traditional Chinese medicine were included to analyze the potential risk factors of DSPN, and the weight values of variable features were sorted. Validation was performed using ten-fold crossover, and the model was measured by accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and AUC value. ResultsThe mean duration of diabetes in the DSPN group was about 4 years longer than that in the non-DSPN group (P<0.001). Compared with non-DSPN patients, DSPN patients had a significantly higher proportion of Chinese medicine symptoms and signs such as numbness of limb, limb pain, dizziness and palpitations, fatigue, thirst with desire to drink, dry mouth and throat, blurred vision, frequent urination, slow reaction, dull complexion, purple tongue, thready pulse and hesitant pulse (P<0.001). In this study, the DSPN neural network prediction model was established by integrating traditional Chinese and Western medicine feature data. The AUC of the model was 0.945 3, the accuracy was 87.68%, the sensitivity was 73.9%, the specificity was 92.7%, the positive predictive value was 78.7%, and the negative predictive value was 90.72%. ConclusionThe fusion of Chinese and Western medicine characteristic data has great clinical value for early diagnosis, and the established model has high accuracy and diagnostic efficacy, which can provide practical tools for DSPN screening and diagnosis in diabetic population.