Lung cancer is one of the tumors with the highest incidence rate and mortality rate in the world. It is also the malignant tumor with the fastest growing number of patients, which seriously threatens human life. How to improve the accuracy of diagnosis and treatment of lung cancer and the survival prognosis is particularly important. Machine learning is a multi-disciplinary interdisciplinary specialty, covering the knowledge of probability theory, statistics, approximate theory and complex algorithm. It uses computer as a tool and is committed to simulating human learning methods, and divides the existing content into knowledge structures to effectively improve learning efficiency and being able to integrate computer science and statistics into medical problems. Through the introduction of algorithm to absorb the input data, and the application of computer analysis to predict the output value within the acceptable accuracy range, identify the patterns and trends in the data, and finally learn from previous experience, the development of this technology brings a new direction for the diagnosis and treatment of lung cancer. This article will review the performance and application prospects of different types of machine learning algorithms in the clinical diagnosis and survival prognosis analysis of lung cancer.
ObjectiveTo predict the total hospitalization expenses of bronchopneumonia inpatients in a tertiay hospital of Sichuan Province through BP neural network and support vector machine models, and analyze the influencing factors.MethodsThe home page information of 749 cases of bronchopneumonia discharged from a tertiay hospital of Sichuan Province in 2017 was collected and compiled. The BP neural network model and the support vector machine model were simulated by SPSS 20.0 and Clementine softwares respectively to predict the total hospitalization expenses and analyze the influencing factors.ResultsThe accuracy rate of the BP neural network model in predicting the total hospitalization expenses was 81.2%, and the top three influencing factors and their importances were length of hospital stay (0.477), age (0.154), and discharge department (0.083). The accuracy rate of the support vector machine model in predicting the total hospitalization expenses was 93.4%, and the top three influencing factors and their importances were length of hospital stay (0.215), age (0.196), and marital status (0.172), but after stratified analysis by Mantel-Haenszel method, the correlation between marital status and total hospitalization expenses was not statistically significant (χ2=0.137, P=0.711).ConclusionsThe BP neural network model and the support vector machine model can be applied to predicting the total hospitalization expenses and analyzing the influencing factors of patients with bronchopneumonia. In this study, the prediction effect of the support vector machine is better than that of the BP neural network model. Length of hospital stay is an important influencing factor of total hospitalization expenses of bronchopneumonia patients, so shortening the length of hospital stay can significantly lighten the economic burden of these patients.
Glaucoma is the leading cause of irreversible blindness, but its early symptoms are not obvious and are easily overlooked, so early screening for glaucoma is particularly important. The cup to disc ratio is an important indicator for clinical glaucoma screening, and accurate segmentation of the optic cup and disc is the key to calculating the cup to disc ratio. In this paper, a full convolutional neural network with residual multi-scale convolution module was proposed for the optic cup and disc segmentation. First, the fundus image was contrast enhanced and polar transformation was introduced. Subsequently, W-Net was used as the backbone network, which replaced the standard convolution unit with the residual multi-scale full convolution module, the input port was added to the image pyramid to construct the multi-scale input, and the side output layer was used as the early classifier to generate the local prediction output. Finally, a new multi-tag loss function was proposed to guide network segmentation. The mean intersection over union of the optic cup and disc segmentation in the REFUGE dataset was 0.904 0 and 0.955 3 respectively, and the overlapping error was 0.178 0 and 0.066 5 respectively. The results show that this method not only realizes the joint segmentation of cup and disc, but also improves the segmentation accuracy effectively, which could be helpful for the promotion of large-scale early glaucoma screening.
In order to realize the quantitative assessment of muscle strength in hand function rehabilitation and then formulate scientific and effective rehabilitation training strategies, this paper constructs a multi-scale convolutional neural network (MSCNN) - convolutional block attention module (CBAM) - bidirectional long short-term memory network (BiLSTM) muscle strength prediction model to fully explore the spatial and temporal features of the data and simultaneously suppress useless features, and finally achieve the improvement of the accuracy of the muscle strength prediction model. To verify the effectiveness of the model proposed in this paper, the model in this paper is compared with traditional models such as support vector machine (SVM), random forest (RF), convolutional neural network (CNN), CNN - squeeze excitation network (SENet), MSCNN-CBAM and MSCNN-BiLSTM, and the effect of muscle strength prediction by each model is investigated when the hand force application changes from 40% of the maximum voluntary contraction force (MVC) to 60% of the MVC. The research results show that as the hand force application increases, the effect of the muscle strength prediction model becomes worse. Then the ablation experiment is used to analyze the influence degree of each module on the muscle strength prediction result, and it is found that the CBAM module plays a key role in the model. Therefore, by using the model in this article, the accuracy of muscle strength prediction can be effectively improved, and the characteristics and laws of hand muscle activities can be deeply understood, providing assistance for further exploring the mechanism of hand functions.
Electrocardiogram (ECG) is a noninvasive, inexpensive, and convenient test for diagnosing cardiovascular diseases and assessing the risk of cardiovascular events. Although there are clear standardized operations and procedures for ECG examination, the interpretation of ECG by even trained physicians can be biased due to differences in diagnostic experience. In recent years, artificial intelligence has become a powerful tool to automatically analyze medical data by building deep neural network models, and has been widely used in the field of medical image diagnosis such as CT, MRI, ultrasound and ECG. This article mainly introduces the application progress of deep neural network models in ECG diagnosis and prediction of cardiovascular diseases, and discusses its limitations and application prospects.
Objective To analyze the risk factors of type 2 diabetes mellitus and establish BP neural network model for screening of type 2 diabetes mellitus based on particle swarm optimization (PSO) algorithm. Methods Inpatients with type 2 diabetes mellitus in the Department of Endocrinology of the Affiliated Hospital of Guangdong Medical University and the Second Affiliated Hospital of Guangdong Medical University between July 2021 and August 2022 were selected as the case group and healthy people in the Health Management Center of the Affiliated Hospital of Guangdong Medical University as the control group. Basic information and physical and laboratory examination indicators were collected for comparative analysis. PSO-BP neural network model, BP neural network model and logistic regression models were established using MATLAB R2021b software and the optimal screening model of type 2 diabetes mellitus was selected. Based on the optimal model, the mean impact value algorithm was used to screen the risk factors of type 2 diabetes mellitus. Results A total of 1 053 patients were included in the case group and 914 healthy peoples in the control group. Except for type of salt, family history of comorbidities, body mass index, total cholesterol, low density lipoprotein cholesterol and staple food intake (P>0.05), the other indexes showed significant differences between the two groups. The performance of the PSO-BP neural network model outperformed the BP neural network model and the logistic regression model. Based on PSO-BP neural network model, the mean impact value algorithm showed that the risk factors for type 2 diabetes mellitus were fasting blood glucose , heart rate, age , waist-arm ratio and marital status , and the protective factors for type 2 diabetes mellitus were high density lipoprotein cholestero, vegetable intake, residence, education level, fruit intake and meat intake. Conclusions There are many influencing factors of type 2 diabetes mellitus. Focus should be placed on high-risk groups and regular disease screening should be carried out to reduce the risk of type 2 diabetes. The screening model of PSO-BP neural network performs the best, and it can be extended to the early screening and diagnosis of other diseases in the future.
The continuous left ventricle blood pressure prediction based on selected heart sound features was realized in this study. The experiments were carried out on three beagle dogs and the variations of cardiac hemodynamics were induced by various dose of epinephrine. The phonocardiogram, electrocardiogram and blood pressures in left ventricle were synchronously acquired. We obtained 28 valid recordings in this study. An artificial neural network was trained with the selected feature to predict left ventricular blood pressure and this trained network made a good performance. The results showed that the absolute average error was 7.3 mm Hg even though the blood pressures had a large range of fluctuation. The average correlation coefficient between the predicted and the measured blood pressure was 0.92. These results showed that the method in this paper was helpful to monitor left ventricular hemodynamics non-invasively and continuously.
The pace of modern life is accelerating, the pressure of life is gradually increasing, and the long-term accumulation of mental fatigue poses a threat to health. By analyzing physiological signals and parameters, this paper proposes a method that can identify the state of mental fatigue, which helps to maintain a healthy life. The method proposed in this paper is a new recognition method of psychological fatigue state of electrocardiogram signals based on convolutional neural network and long short-term memory. Firstly, the convolution layer of one-dimensional convolutional neural network model is used to extract local features, the key information is extracted through pooling layer, and some redundant data is removed. Then, the extracted features are used as input to the long short-term memory model to further fuse the ECG features. Finally, by integrating the key information through the full connection layer, the accurate recognition of mental fatigue state is successfully realized. The results show that compared with traditional machine learning algorithms, the proposed method significantly improves the accuracy of mental fatigue recognition to 96.3%, which provides a reliable basis for the early warning and evaluation of mental fatigue.
The processing mechanism of the human brain for speech information is a significant source of inspiration for the study of speech enhancement technology. Attention and lateral inhibition are key mechanisms in auditory information processing that can selectively enhance specific information. Building on this, the study introduces a dual-branch U-Net that integrates lateral inhibition and feedback-driven attention mechanisms. Noisy speech signals input into the first branch of the U-Net led to the selective feedback of time-frequency units with high confidence. The generated activation layer gradients, in conjunction with the lateral inhibition mechanism, were utilized to calculate attention maps. These maps were then concatenated to the second branch of the U-Net, directing the network’s focus and achieving selective enhancement of auditory speech signals. The evaluation of the speech enhancement effect was conducted by utilising five metrics, including perceptual evaluation of speech quality. This method was compared horizontally with five other methods: Wiener, SEGAN, PHASEN, Demucs and GRN. The experimental results demonstrated that the proposed method improved speech signal enhancement capabilities in various noise scenarios by 18% to 21% compared to the baseline network across multiple performance metrics. This improvement was particularly notable in low signal-to-noise ratio conditions, where the proposed method exhibited a significant performance advantage over other methods. The speech enhancement technique based on lateral inhibition and feedback-driven attention mechanisms holds significant potential in auditory speech enhancement, making it suitable for clinical practices related to artificial cochleae and hearing aids.
The medical literature contains a wealth of valuable medical knowledge. At present, the research on extraction of entity relationship in medical literature has made great progress, but with the exponential increase in the number of medical literature, the annotation of medical text has become a big problem. In order to solve the problem of manual annotation time such as consuming and heavy workload, a remote monitoring annotation method is proposed, but this method will introduce a lot of noise. In this paper, a novel neural network structure based on convolutional neural network is proposed, which can solve a large number of noise problems. The model can use the multi-window convolutional neural network to automatically extract sentence features. After the sentence vectors are obtained, the sentences that are effective to the real relationship are selected through the attention mechanism. In particular, an entity type (ET) embedding method is proposed for relationship classification by adding entity type characteristics. The attention mechanism at sentence level is proposed for relation extraction in allusion to the unavoidable labeling errors in training texts. We conducted an experiment using 968 medical references on diabetes, and the results showed that compared with the baseline model, the present model achieved good results in the medical literature, and F1-score reached 93.15%. Finally, the extracted 11 types of relationships were stored as triples, and these triples were used to create a medical map of complex relationships with 33 347 nodes and 43 686 relationship edges. Experimental results show that the algorithm used in this paper is superior to the optimal reference system for relationship extraction.