CNN-RNN Based Intelligent Recommendation for Online Medical Pre-Diagnosis Support

Effect of vitamin energy drinks on relieving exercise-induced fatigue in muscle group by ultrasonic bioimaging data analysis

OBJECTIVE

This work was aimed to analyze the effect of vitamin energy drink on muscle fatigue by surface electromyography (SEMG) and ultrasonic bioimaging (USBI).

METHODS

20 healthy men were selected to do increasing load fatigue test. Surface electromyographic signals and ultrasonic biological images were collected based on wavelet threshold function with improved thresholds. Time domain and frequency domain characteristic integrated electromyography (IEMG), root mean square amplitude (RMS), average power frequency (MPF), and surface and deep muscle morphological changes were analyzed. Hemoglobin concentration (HB), red blood cell number (RBC), mean volume of red blood cell (MCV), blood lactic acid (BLA), malondialdehyde (MDA), and phosphocreatine kinase (CK) were measured.

RESULTS

1) the Accuracy (94.10%), Sensitivity (94.43%), Specificity (93.75%), and Precision (94.07%) of the long and short-term memory (LSTM) specificity for muscle fatigue recognition were higher than those of other models. 2) Compared with the control group, the levels of BLA, MDA, and CK in the experimental group were decreased and HB levels were increased after exercise (P < 0.05). 3) IEMG and RMS of the experimental group were higher than those of the control group, and increased with time (P < 0.05). 4) The mean amplitude of the response signal decreased with time. Compared with the control group, the surface muscle thickness, deep muscle thickness, total muscle thickness, contrast, and homogeneity (HOM) decreased in the experimental group; while the angular second moment (ASM) and contrast increased, showing great differences (P < 0.05).

CONCLUSION

Surface electromyographic signal and ultrasonic biological image can be used as auxiliary monitoring techniques for muscle fatigue during exercise. Drinking vitamin energy drinks before exercise can relieve physical fatigue to a certain extent and promote the maintenance of muscle microstructure.

A new hybrid model of convolutional neural networks and hidden Markov chains for image classification

Convolutional neural networks (CNNs) have lately proven to be extremely effective in image recognition. Besides CNN, hidden Markov chains (HMCs) are probabilistic models widely used in image processing. This paper presents a new hybrid model composed of both CNNs and HMCs. The CNN model is used for feature extraction and dimensionality reduction and the HMC model for classification. In the new model, named CNN-HMC, convolutional and pooling layers of the CNN model are applied to extract features maps. Also a Peano scan is applied to obtain several HMCs. Expectation-Maximization (EM) algorithm is used to estimate HMC's parameters and to make the Bayesian Maximum Posterior Mode (MPM) classification method used unsupervised. The objective is to enhance the performances of the CNN models for the image classification task. To evaluate the performance of our proposal, it is compared to six models in two series of experiments. In the first series, we consider two CNN-HMC and compare them to two CNNs, 4Conv and Mini AlexNet, respectively. The results show that CNN-HMC model outperforms the classical CNN model, and significantly improves the accuracy of the Mini AlexNet. In the second series, it is compared to four models CNN-SVMs, CNN-LSTMs, CNN-RFs, and CNN-gcForests, which only differ from CNN-HMC by the second classification step. Based on five datasets and four metrics recall, precision, F1-score, and accuracy, results of these comparisons show again the interest of the proposed CNN-HMC. In particular, with a CNN model of 71% of accuracy, the CNN-HMC gives an accuracy ranging between 81.63% and 92.5%.

Signal Property Information-Based Target Detection with Dual-Output Neural Network in Complex Environments

The performance of traditional model-based constant false-alarm ratio (CFAR) detection algorithms can suffer in complex environments, particularly in scenarios involving multiple targets (MT) and clutter edges (CE) due to an imprecise estimation of background noise power level. Furthermore, the fixed threshold mechanism that is commonly used in the single-input single-output neural network can result in performance degradation due to changes in the scene. To overcome these challenges and limitations, this paper proposes a novel approach, a single-input dual-output network detector (SIDOND) using data-driven deep neural networks (DNN). One output is used for signal property information (SPI)-based estimation of the detection sufficient statistic, while the other is utilized to establish a dynamic-intelligent threshold mechanism based on the threshold impact factor (TIF), where the TIF is a simplified description of the target and background environment information. Experimental results demonstrate that SIDOND is more robust and performs better than model-based and single-output network detectors. Moreover, the visual explanation technique is employed to explain the working of SIDOND.

Optimizing healthcare system by amalgamation of text processing and deep learning: a systematic review

The explosion of clinical textual data has drawn the attention of researchers. Owing to the abundance of clinical data, it is becoming difficult for healthcare professionals to take real-time measures. The tools and methods are lacking when compared to the amount of clinical data generated every day. This review aims to survey the text processing pipeline with deep learning methods such as CNN, RNN, LSTM, and GRU in the healthcare domain and discuss various applications such as clinical concept detection and extraction, medically aware dialogue systems, sentiment analysis of drug reviews shared online, clinical trial matching, and pharmacovigilance. In addition, we highlighted the major challenges in deploying text processing with deep learning to clinical textual data and identified the scope of research in this domain. Furthermore, we have discussed various resources that can be used in the future to optimize the healthcare domain by amalgamating text processing and deep learning.

Natural Exponential and Three-Dimensional Chaotic System

Existing chaotic system exhibits unpredictability and nonrepeatability in a deterministic nonlinear architecture, presented as a combination of definiteness and stochasticity. However, traditional two-dimensional chaotic systems cannot provide sufficient information in the dynamic motion and usually feature low sensitivity to initial system input, which makes them computationally prohibitive in accurate time series prediction and weak periodic component detection. Here, a natural exponential and three-dimensional chaotic system with higher sensitivity to initial system input conditions showing astonishing extensibility in time series prediction and image processing is proposed. The chaotic performance evaluated theoretically and experimentally by Poincare mapping, bifurcation diagram, phase space reconstruction, Lyapunov exponent, and correlation dimension provides a new perspective of nonlinear physical modeling and validation. The complexity, robustness, and consistency are studied by recursive and entropy analysis and comparison. The method improves the efficiency of time series prediction, nonlinear dynamics-related problem solving and expands the potential scope of multi-dimensional chaotic systems.

Demystifying the Role of Natural Language Processing (NLP) in Smart City Applications: Background, Motivation, Recent Advances, and Future Research Directions

Smart cities provide an efficient infrastructure for the enhancement of the quality of life of the people by aiding in fast urbanization and resource management through sustainable and scalable innovative solutions. The penetration of Information and Communication Technology (ICT) in smart cities has been a major contributor to keeping up with the agility and pace of their development. In this paper, we have explored Natural Language Processing (NLP) which is one such technical discipline that has great potential in optimizing ICT processes and has so far been kept away from the limelight. Through this study, we have established the various roles that NLP plays in building smart cities after thoroughly analyzing its architecture, background, and scope. Subsequently, we present a detailed description of NLP's recent applications in the domain of smart healthcare, smart business, and industry, smart community, smart media, smart research, and development as well as smart education accompanied by NLP's open challenges at the very end. This work aims to throw light on the potential of NLP as one of the pillars in assisting the technical advancement and realization of smart cities.

Prompt Deep Light-Weight Vessel Segmentation Network (PLVS-Net)

Achieving accurate retinal vessel segmentation is critical in the progression and diagnosis of vision-threatening diseases such as diabetic retinopathy and age-related macular degeneration. Existing vessel segmentation methods are based on encoder-decoder architectures, which frequently fail to take into account the retinal vessel structure's context in their analysis. As a result, such methods have difficulty bridging the semantic gap between encoder and decoder characteristics. This paper proposes a Prompt Deep Light-weight Vessel Segmentation Network (PLVS-Net) to address these issues by using prompt blocks. Each prompt block use combination of asymmetric kernel convolutions, depth-wise separable convolutions, and ordinary convolutions to extract useful features. This novel strategy improves the performance of the segmentation network while simultaneously decreasing the number of trainable parameters. Our method outperformed competing approaches in the literature on three benchmark datasets, including DRIVE, STARE, and CHASE.

Face Recognition Method under Adaptive Image Matching and Dictionary Learning Algorithm

In this research, a robust face recognition method based on adaptive image matching and a dictionary learning algorithm was proposed. A Fisher discriminant constraint was introduced into the dictionary learning algorithm program so that the dictionary had certain category discrimination ability. The purpose was to use this technology to reduce the influence of pollution, absence, and other factors on face recognition and improve the recognition rate. The optimization method was used to solve the loop iteration to obtain the expected specific dictionary, and the selected specific dictionary was used as the representation dictionary in adaptive sparse representation. In addition, if a specific dictionary was placed in a seed space of the original training data, the mapping matrix can be used to represent the mapping relationship between the specific dictionary and the original training sample, and the test sample could be corrected according to the mapping matrix to remove the contamination in the test sample. Moreover, the feature face method and dimension reduction method were used to process the specific dictionary and the corrected test sample, and the dimensions were reduced to 25, 50, 75, 100, 125, and 150, respectively. In this research, the recognition rate of the algorithm in 50 dimensions was lower than that of the discriminatory low-rank representation method (DLRR), and the recognition rate in other dimensions was the highest. The adaptive image matching classifier was used for classification and recognition. The experimental results showed that the proposed algorithm had a good recognition rate and good robustness against noise, pollution, and occlusion. Health condition prediction based on face recognition technology has the advantages of being noninvasive and convenient operation.

An intelligent medical guidance and recommendation model driven by patient-physician communication data

Based on the online patient-physician communication data, this study used natural language processing and machine learning algorithm to construct a medical intelligent guidance and recommendation model. First, based on 16,935 patient main complaint data of nine diseases, this study used the word2vec, long-term and short-term memory neural networks, and other machine learning algorithms to construct intelligent department guidance and recommendation model. Besides, taking ophthalmology as an example, it also used the word2vec, TF-IDF, and cosine similarity algorithm to construct an intelligent physician recommendation model. Furthermore, to recommend physicians with better service quality, this study introduced the information amount of physicians' feedback to the recommendation evaluation indicator as the text and voice service quality. The results show that the department guidance model constructed by long-term and short-term memory neural networks has the best effect. The precision is 82.84%, and the F1-score is 82.61% in the test set. The prediction effect of the LSTM model is better than TextCNN, random forest, K-nearest neighbor, and support vector machine algorithms. In the intelligent physician recommendation model, under certain parameter settings, the recommendation effect of the hybrid recommendation model based on similar patients and similar physicians has certain advantages over the model of similar patients and similar physicians.

Heart Rate Estimation from Incomplete Electrocardiography Signals

As one of the most remarkable indicators of physiological health, heart rate (HR) has become an unfailing investigation for researchers. Unlike many existing methods, this article proposes an approach to implement short-time HR estimation from electrocardiography in time series missing patterns. Benefiting from the rapid development of deep learning, we adopted a bidirectional long short-term memory model (Bi-LSTM) and temporal convolution network (TCN) to recover complete heartbeat signals from those with durations are less than one cardiac cycle, and the estimated HR from recovered segment combining the input and the predicted output. We also compared the performance of Bi-LSTM and TCN in PhysioNet dataset. Validating the method over a resting heart rate range of 60−120 bpm in the database without significant arrhythmias and a corresponding range of 30−150 bpm in the database with arrhythmias, we found that networks provide an estimated approach for incomplete signals in a fixed format. These results are consistent with real heartbeats in the normal heartbeat dataset (γ > 0.7, RMSE < 10) and in the arrhythmia database (γ > 0.6, RMSE < 30), verifying that HR could be estimated by models in advance. We also discussed the short-time limits for the predictive model. It could be used for physiological purposes such as mobile sensing in time-constrained scenarios, and providing useful insights for better time series analyses in missing data patterns.

Time-aware sport goods sale prediction for healthcare with privacy-preservation

Sports industry has been playing an important role in achieving good healthcare for public. However, with the advent of COVID-19, sports industry has been influenced significantly and the industry scale is decreased considerably. In this situation, how to accurately predict the sports industry scale in terms of production and consumption is becoming a practical and valuable task, because the whole world's economy is not growing stably and users' demand to sport goods is fluctuating sharply. However, three challenges are often existing in the sports industry scale prediction. First of all, there are so many kinds of sport goods that it is hard to quickly predict their future production or consumption scales accurately. Second, for a certain sport commodity, its production or consumption scale is often related to time especially in the COVID-19 environment. Third, sports industry scale data often contain some privacy, which probably disables data stakeholders to disclose their data. In view of these three challenges, a novel sports industry scale prediction approach (named SISP) is proposed for healthcare, which is basically according to time series analysis. Through SISP approach, we can quickly and accurately predict the future production or consumption scales of sport goods, in a privacy-aware way. At last, we validate the feasibility of the proposed SISP approach in this paper.

Patient satisfaction impact indicators from a psychosocial perspective

Background

Patient satisfaction plays an important role in improving patient behavior from care, reducing healthcare costs, and improving outcomes. However, since patient satisfaction is a multidimensional concept, it remains unclear which factors are the key indicators of patient satisfaction. The purpose of this study was to verify whether and how patients' psychosocial perceptions of physicians influenced patient satisfaction.

Method

In China, 2,256 patients were surveyed on stereotypes of physicians, institutional trust, humanized perception, and communication skills, as well as patient expectations and patient satisfaction. The data were analyzed using structural equation modeling.

Results

Stereotypes, institutional trust, and humanized perception have an indirect effect on patient satisfaction through communication, and patient expectations have a direct effect on patient satisfaction.

Conclusions

"Patient-centered" communication is the key to improving patient satisfaction, while positive stereotypes at the societal level, standardization of organizational institutions, expression of the doctor's view of humanity in the doctor-patient interaction, and reasonable guidance of patient expectations are important for improving patient satisfaction.

Medical text classification based on the discriminative pre-training model and prompt-tuning

Medical text classification, as a fundamental medical natural language processing task, aims to identify the categories to which a short medical text belongs. Current research has focused on performing the medical text classification task using a pre-training language model through fine-tuning. However, this paradigm introduces additional parameters when training extra classifiers. Recent studies have shown that the "prompt-tuning" paradigm induces better performance in many natural language processing tasks because it bridges the gap between pre-training goals and downstream tasks. The main idea of prompt-tuning is to transform binary or multi-classification tasks into mask prediction tasks by fully exploiting the features learned by pre-training language models. This study explores, for the first time, how to classify medical texts using a discriminative pre-training language model called ERNIE-Health through prompt-tuning. Specifically, we attempt to perform prompt-tuning based on the multi-token selection task, which is a pre-training task of ERNIE-Health. The raw text is wrapped into a new sequence with a template in which the category label is replaced by a [UNK] token. The model is then trained to calculate the probability distribution of the candidate categories. Our method is tested on the KUAKE-Question Intention Classification and CHiP-Clinical Trial Criterion datasets and obtains the accuracy values of 0.866 and 0.861. In addition, the loss values of our model decrease faster throughout the training period compared to the fine-tuning. The experimental results provide valuable insights to the community and suggest that prompt-tuning can be a promising approach to improve the performance of pre-training models in domain-specific tasks.

Lightweight similarity checking for English literatures in mobile edge computing

With the advent of information age, mobile devices have become one of the major convenient equipment that aids people's daily office activities such as academic research, one of whose major tasks is to check the repetition rate or similarity among different English literatures. Traditional literature similarity checking solutions in cloud paradigm often call for intensive computational cost and long waiting time. To tackle this issue, in this paper, we modify the traditional literature similarity checking solution in cloud paradigm to make it suitable for the light-weight mobile edge environment. Furthermore, we put forward a lightweight similarity checking approach SC MEC for English literatures in mobile edge computing environment. To validate the advantages of SC MEC , we have designed massive experiments on a dataset. The reported experimental results show that SC MEC can deliver a satisfactory similarity checking result of literatures compared to other existing approaches.

Prediction of patient choice tendency in medical decision-making based on machine learning algorithm

Objective

Machine learning (ML) algorithms, as an early branch of artificial intelligence technology, can effectively simulate human behavior by training on data from the training set. Machine learning algorithms were used in this study to predict patient choice tendencies in medical decision-making. Its goal was to help physicians understand patient preferences and to serve as a resource for the development of decision-making schemes in clinical treatment. As a result, physicians and patients can have better conversations at lower expenses, leading to better medical decisions.

Method

Patient medical decision-making tendencies were predicted by primary survey data obtained from 248 participants at third-level grade-A hospitals in China. Specifically, 12 predictor variables were set according to the literature review, and four types of outcome variables were set based on the optimization principle of clinical diagnosis and treatment. That is, the patient's medical decision-making tendency, which is classified as treatment effect, treatment cost, treatment side effect, and treatment experience. In conjunction with the study's data characteristics, three ML classification algorithms, decision tree (DT), k-nearest neighbor (KNN), and support vector machine (SVM), were used to predict patients' medical decision-making tendency, and the performance of the three types of algorithms was compared.

Results

The accuracy of the DT algorithm for predicting patients' choice tendency in medical decision making is 80% for treatment effect, 60% for treatment cost, 56% for treatment side effects, and 60% for treatment experience, followed by the KNN algorithm at 78%, 66%, 74%, 84%, and the SVM algorithm at 82%, 76%, 80%, 94%. At the same time, the comprehensive evaluation index F1-score of the DT algorithm are 0.80, 0.61, 0.58, 0.60, the KNN algorithm are 0.75, 0.65, 0.71, 0.84, and the SVM algorithm are 0.81, 0.74, 0.73, 0.94.

Conclusion

Among the three ML classification algorithms, SVM has the highest accuracy and the best performance. Therefore, the prediction results have certain reference values and guiding significance for physicians to formulate clinical treatment plans. The research results are helpful to promote the development and application of a patient-centered medical decision assistance system, to resolve the conflict of interests between physicians and patients and assist them to realize scientific decision-making.

Ensemble of Networks for Multilabel Classification

Multilabel learning goes beyond standard supervised learning models by associating a sample with more than one class label. Among the many techniques developed in the last decade to handle multilabel learning best approaches are those harnessing the power of ensembles and deep learners. This work proposes merging both methods by combining a set of gated recurrent units, temporal convolutional neural networks, and long short-term memory networks trained with variants of the Adam optimization approach. We examine many Adam variants, each fundamentally based on the difference between present and past gradients, with step size adjusted for each parameter. We also combine Incorporating Multiple Clustering Centers and a bootstrap-aggregated decision trees ensemble, which is shown to further boost classification performance. In addition, we provide an ablation study for assessing the performance improvement that each module of our ensemble produces. Multiple experiments on a large set of datasets representing a wide variety of multilabel tasks demonstrate the robustness of our best ensemble, which is shown to outperform the state-of-the-art.

Assessment of the Use of Patient Vital Sign Data for Preventing Misidentification and Medical Errors

Patient misidentification is a preventable issue that contributes to medical errors. When patients are confused with each other, they can be given the wrong medication or unneeded surgeries. Unconscious, juvenile, and mentally impaired patients represent particular areas of concern, due to their potential inability to confirm their identity or the possibility that they may inadvertently respond to an incorrect patient name (in the case of juveniles and the mentally impaired). This paper evaluates the use of patient vital sign data, within an enabling artificial intelligence (AI) framework, for the purposes of patient identification. The AI technique utilized is both explainable (meaning that its decision-making process is human understandable) and defensible (meaning that its decision-making pathways cannot be altered, just optimized). It is used to identify patients based on standard vital sign data. Analysis is presented on the efficacy of doing this, for the purposes of catching misidentification and preventing error.

Prediction of pathological staging and grading of renal clear cell carcinoma based on deep learning algorithms

OBJECTIVE

Deep learning algorithms were used to develop a model for predicting the staging and grading of renal clear cell carcinoma to inform clinicians' treatment plans.

METHODS

Clinical and pathological information was collected from 878 patients diagnosed with renal clear cell carcinoma in the Department of Urology, Peking University First Hospital. The patients were randomly assigned to the test set (n = 702) or the verification set (n = 176). Pathological staging and grading of renal clear cell carcinoma were predicted by preoperative clinical variables using deep learning algorithms. Receiver operating characteristic curves were used to evaluate the predictive accuracy as measured by the area under the receiver operating characteristic curve (AUC).

RESULTS

For tumor pathological staging, AUC values of 0.933, 0.947, and 0.948 were obtained using the BiLSTM, CNN-BiLSTM, and CNN-BiGRU models, respectively. For tumor pathological grading, the AUC values were 0.754, 0.720, and 0.770, respectively.

CONCLUSIONS

The proposed model for predicting renal clear cell carcinoma allows for accurate projection of the staging and grading of renal clear cell carcinoma and helps clinicians optimize individual treatment plans.

CSPP-IQA: a multi-scale spatial pyramid pooling-based approach for blind image quality assessment

The traditional image quality assessment (IQA) methods are usually based on convolutional neural networks (CNNs). For these IQA methods using CNNs, limited by the feature size of the fully connected layer, the input image needs be tailored to a pre-defined size, which usually results in destroying the original structure and content of the input image and thus reduces the accuracy of the quality assessment. In this paper, a blind image quality assessment method (named CSPP-IQA), which is based on multi-scale spatial pyramid pooling, is proposed. CSPP-IQA allows inputting the original image when assessing the image quality without any image adjustment. Moreover, by facilitating the convolutional block attention module and image understanding module, CSPP-IQA achieved better accuracy, generalization and efficiency than traditional IQA methods. The result of experiments running on real-scene IQA datasets in this study verified the effectiveness and efficiency of CSPP-IQA.

Segmentation Algorithm of Magnetic Resonance Imaging Glioma under Fully Convolutional Densely Connected Convolutional Networks

This work focused on the application value of magnetic resonance imaging (MRI) image segmentation algorithm based on fully convolutional DenseNet neural network (FCDNN) in glioma diagnosis. In this work, based on the fully convolutional DenseNet algorithm, a new MRI image automatic semantic segmentation method cerebral gliomas semantic segmentation network (CGSSNet) was established and was applied to glioma MRI image segmentation by using the BraTS public dataset as research data. Under the same conditions, compare the differences of dice similarity coefficient (DSC), sensitivity, and Hausdroff distance (HD) between this algorithm and other algorithms in MRI image processing. The results showed that the CGSSNet network segmentation algorithm significantly improved the segmentation accuracy of glioma MRI images. In addition, its DSC, sensitivity, and HD values for glioma MRI images were 0.937, 0.811, and 1.201, respectively. Under different iteration times, the DSC, sensitivity, and HD values of the CGSSNet network segmentation algorithm are significantly better than other algorithms. It showed that the CGSSNet model based on the DenseNet can improve the segmentation accuracy of glioma MRI images, and has potential application value in clinical practice.

Privacy-aware and Efficient Student Clustering for Sport Training with Hash in Cloud Environment

With the wide adoption of health and sport concepts in human society, how to effectively analyze the personalized sports preferences of students based on past sports training records has become a crucial and emergent task with positive research significance. However, the past sports training records of students are often accumulated with time and stored in a central cloud platform and therefore, the data volume is too large to be processed with quick response. In addition, the past sports training records of students often contain certain sensitive information, which probably discloses partial user privacy if we cannot protect the data well. Considering these two challenges, a privacy-aware and efficient student clustering approach, named PESC is proposed, which is based on a hash technique and deployed on a central cloud platform connecting multiple local servers. Concretely, in the cloud platform, each student is firstly assigned an index based on the past sports training records stored in a local server, through a uniform hash mapping operation. Then similar students are clustered and registered in the cloud platform based on the students' respective sport indexes. At last, we infer the personalized sport preferences of each student based on their belonged clusters. To prove the feasibility of PESC, we provide a case study and a set of experiments deployed on a time-aware dataset.

Defect knowledge graph construction and application in multi-cloud IoT

As the State Grid Multi-cloud IoT platform grows and improves, an increasing number of IoT applications generate massive amounts of data every day. To meet the demands of intelligent management of State Grid equipment, we proposed a scheme for constructing the defect knowledge graph of power equipment based on multi-cloud. The scheme is based on the State Grid Multi-cloud IoT architecture and adheres to the design specifications of the State Grid SG-EA technical architecture. This scheme employs ontology design based on a fusion algorithm and proposes a knowledge graph reasoning method named GRULR based on logic rules to achieve a consistent and shareable model. The model can be deployed on multiple clouds independently, increasing the system’s flexibility, robustness, and security. The GRULR method is designed with two independent components, Reasoning Evaluator and Rule Miner, that can be deployed in different clouds to adapt to the State Grid Multi-cloud IoT architecture. By sharing high-quality rules across multiple clouds, this method can avoid vendor locking and perform iterative updates. Finally, the experiment demonstrates that the GRULR method performs well in large-scale knowledge graphs and can complete the reasoning task of the defect knowledge graph efficiently.

Multistrategy Improved Sparrow Search Algorithm Optimized Deep Neural Network for Esophageal Cancer

Deep neural network is a complex pattern recognition network system. It is widely favored by scholars for its strong nonlinear fitting ability. However, training deep neural network models on small datasets typically realizes worse performance than shallow neural network. In this study, a strategy to improve the sparrow search algorithm based on the iterative map, iterative perturbation, and Gaussian mutation is developed. This optimized strategy improved the sparrow search algorithm validated by fourteen benchmark functions, and the algorithm has the best search accuracy and the fastest convergence speed. An algorithm based on the iterative map, iterative perturbation, and Gaussian mutation improved sparrow search algorithm is designed to optimize deep neural networks. The modified sparrow algorithm is exploited to search for the optimal connection weights of deep neural network. This algorithm is implemented for the esophageal cancer dataset along with the other six algorithms. The proposed model is able to achieve 0.92 under all the eight scoring criteria, which is better than the performance of the other six algorithms. Therefore, an optimized deep neural network based on an improved sparrow search algorithm with iterative map, iterative perturbation, and Gaussian mutation is an effective approach to predict the survival rate of esophageal cancer.

Efficient and scalable patients clustering based on medical big data in cloud platform

With the outbreak and popularity of COVID-19 pandemic worldwide, the volume of patients is increasing rapidly all over the world, which brings a big risk and challenge for the maintenance of public healthcare. In this situation, quick integration and analysis of the medical records of patients in a cloud platform are of positive and valuable significance for accurate recognition and scientific diagnosis of the healthy conditions of potential patients. However, due to the big volume of medical data of patients distributed in different platforms (e.g., multiple hospitals), how to integrate these data for patient clustering and analysis in a time-efficient and scalable manner in cloud platform is still a challenging task, while guaranteeing the capability of privacy-preservation. Motivated by this fact, a time-efficient, scalable and privacy-guaranteed patient clustering method in cloud platform is proposed in this work. At last, we demonstrate the competitive advantages of our method via a set of simulated experiments. Experiment results with competitive methods in current research literatures have proved the feasibility of our proposal.

Machine learning techniques for CT imaging diagnosis of novel coronavirus pneumonia: a review

Since 2020, novel coronavirus pneumonia has been spreading rapidly around the world, bringing tremendous pressure on medical diagnosis and treatment for hospitals. Medical imaging methods, such as computed tomography (CT), play a crucial role in diagnosing and treating COVID-19. A large number of CT images (with large volume) are produced during the CT-based medical diagnosis. In such a situation, the diagnostic judgement by human eyes on the thousands of CT images is inefficient and time-consuming. Recently, in order to improve diagnostic efficiency, the machine learning technology is being widely used in computer-aided diagnosis and treatment systems (i.e., CT Imaging) to help doctors perform accurate analysis and provide them with effective diagnostic decision support. In this paper, we comprehensively review these frequently used machine learning methods applied in the CT Imaging Diagnosis for the COVID-19, discuss the machine learning-based applications from the various kinds of aspects including the image acquisition and pre-processing, image segmentation, quantitative analysis and diagnosis, and disease follow-up and prognosis. Moreover, we also discuss the limitations of the up-to-date machine learning technology in the context of CT imaging computer-aided diagnosis.

Medical Data Classification Assisted by Machine Learning Strategy

With the development of science and technology, data plays an increasingly important role in our daily life. Therefore, much attention has been paid to the field of data mining. Data classification is the premise of data mining, and how well the data is classified directly affects the performance of subsequent models. In particular, in the medical field, data classification can help accurately determine the location of patients' lesions and reduce the workload of doctors in the treatment process. However, medical data has the characteristics of high noise, strong correlation, and high data dimension, which brings great challenges to the traditional classification model. Therefore, it is very important to design an advanced model to improve the effect of medical data classification. In this context, this paper first introduces the structure and characteristics of the convolutional neural network (CNN) model and then demonstrates its unique advantages in medical data processing, especially in data classification. Secondly, we design a new kind of medical data classification model based on the CNN model. Finally, the simulation results show that the proposed method achieves higher classification accuracy with faster model convergence speed and the lower training error when compared with conventional machine leaning methods, which has demonstrated the effectiveness of the new method in respect to medical data classification.

A machine learning and blockchain based secure and cost-effective framework for minor medical consultations

With the ever-increasing awareness among people regarding their health, visiting a doctor has become quite common. However, with the onset of the COVID-19 pandemic, home-based consultations are gaining popularity. Nevertheless, the worries over privacy and the lack of willingness to assist patients by the medical professionals in the online consultation process have made current models ineffective. In this paper, we present an advanced protected blockchain-based consultation model for minor medical conditions. Our model not only ensures users’ privacy but by incorporating a calculation model, it also offers an opportunity for consulting end-users to voluntarily take part in the consultation process. Our work proposes a smart contract based on machine learning to be implemented for the prediction of a score of a professional who consults based on various prioritized parameters. This is done by using word2vec and TF-IDF weighting to classify the question and cosine similarity scores for detailed orientation analysis. Based on this score, the patient is charged, and simultaneously, the responder is awarded ether. An incentivized method leads to more accessible healthcare while reducing the cost itself.

Effect of Multichannel Convolutional Neural Network-Based Model on the Repair and Aesthetic Effect of Eye Plastic Surgery Patients

Objective

This study is aimed at exploring the impact of eye model based on multichannel convolutional neural network (CNN) on eye plastic surgery and aesthetic effect, thus formulating methods to improve the effect of eye plastic surgery.

Methods

A total of 64 patients who underwent pouch plastic surgery from January 2020 to March 2021 were selected as the research objects and were divided into observation group and control group by random number table method. The subjects in the observation group were evaluated by multichannel CNN-based eye model and doctors' experience, while those in the control group were evaluated by doctors' experience only, with 32 cases in both groups. Blepharoplasty, lower eyelid skin wrinkles, skin luster, and aesthetic scores were compared between the two groups.

Results

The similarity between the multichannel CNN model detected shape and the actual eye shape (98.78%) was considerably higher than that of the CNN model detected shape (78.65%) (P < 0.05). After treatment, the indexes of pouch degree, lower eyelid skin wrinkle, eyelid lacrimal sulcus, skin gloss, and aesthetic score in the observation group were better than those in the control group (P < 0.05). The incidence of complications in the observation group (13%) was considerably lower than that in the control group (28%) (P < 0.05).

Conclusion

The eye model based on the multichannel CNN model was helpful to improve the surgical repair and aesthetic effect of patients and can improve the occurrence of postoperative complications.

Research on influencing factors of artificial intelligence multi-cloud scheduling applied talent training based on DEMATEL-TAISM

With the rapid development of Internet of Things (IoT) technology and the rising popularity of IoT devices, an increasing number of computing intensive IoT applications have been developed. However, due to the limited resources of IoT devices, cloud computing systems are required to compute intensive IoT applications. Furthermore, to be subject to a single cloud computing service provider, multi-cloud computing has become an IoT service cloud computing solution. As a result of the complexity of multi-cloud scheduling, the application of artificial intelligence is an important technology to solve IoT multi-cloud scheduling. The corresponding talent training plays an important role in the development and implementation of the IoT artificial intelligence multi-cloud scheduling. First, this paper studies the key influencing factors of IoT artificial intelligence multi-cloud scheduling applied talent training. Combined with the characteristics of the development of China’s artificial intelligence industry, this paper summarizes the influencing factors from the four-dimensional training path of government departments, universities, enterprises and scientific research institutes. The purpose of artificial intelligence multi-cloud scheduling applied talent training is to build an artificial intelligence multi-cloud scheduling applied talent training influencing factor index system. Then, the DEMATEL method is used to establish multiple correlation matrices according to the direct influence correlation between the factors and calculate the degree of influence, the degree of being influenced, the center degree and the cause degree of the factors. Using the improved AISM method, based on the idea of game confrontation, from the two opposite extraction rules of result priority and cause priority, a group of confrontation level topological maps with comprehensive influence values reflecting the interacting factors are obtained, and relevant suggestions are presented to provide a reference for the training of artificial intelligence multi-cloud scheduling applied talent.

Ultrasonic Image Features under the Intelligent Algorithm in the Diagnosis of Severe Sepsis Complicated with Renal Injury

This research was aimed at analyzing the diagnosis of severe sepsis complicated with acute kidney injury (AKI) by ultrasonic image information based on the artificial intelligence pulse-coupled neural network (PCNN) algorithm and at improving the diagnostic accuracy and efficiency of clinical severe sepsis complicated with AKI. In this research, 50 patients with sepsis complicated with AKI were collected as the observation group and 50 patients with sepsis as the control group. All patients underwent ultrasound examination. The clinical data of the two groups were collected, and the scores of acute physiology and chronic health assessment (APACHE II) and sequential organ failure assessment (SOFA) were compared. The ultrasonic image information enhancement algorithm based on artificial intelligence PCNN is constructed and simulated and is compared with the maximum between-class variance (OSTU) algorithm and the maximum entropy algorithm. The results showed that the PCNN algorithm was superior to the OSTU algorithm and maximum entropy algorithm in the segmentation results of severe sepsis combined with AKI in terms of regional consistency (UM), regional contrast (CM), and shape measure (SM). The acute physiology and chronic health evaluation (APACHE II) and sequential organ failure assessment (SOFA) scores in the observation group were substantially higher than those in the control group (P < 0.05). The interlobular artery resistance index (RI) in the observation group was substantially higher than that in the control group (P < 0.05). Moreover, the mean transit time (mTT) in the observation group was significantly higher than that in the control group (4.85 ± 1.27 vs. 3.42 ± 1.04), and the perfusion index (PI) was significantly lower than that in the control group (134.46 ± 17.29 vs. 168.37 ± 19.28), with statistical significance (P < 0.05). In summary, it can substantially increase ultrasonic image information based on the artificial intelligence PCNN algorithm. The RI, mTT, and PI of the renal interlobular artery level in ultrasound images can be used as indexes for the diagnosis of severe sepsis complicated with AKI.

Application of Laser Systems for Detection and Ranging in the Modern Road Transportation and Maritime Sector

The development of light detection and ranging (lidar) technology began in the 1960s, following the invention of the laser, which represents the central component of this system, integrating laser scanning with an inertial measurement unit (IMU) and Global Positioning System (GPS). Lidar technology is spreading to many different areas of application, from those in autonomous vehicles for road detection and object recognition, to those in the maritime sector, including object detection for autonomous navigation, monitoring ocean ecosystems, mapping coastal areas, and other diverse applications. This paper presents lidar system technology and reviews its application in the modern road transportation and maritime sector. Some of the better-known lidar systems for practical applications, on which current commercial models are based, are presented, and their advantages and disadvantages are described and analyzed. Moreover, current challenges and future trends of application are discussed. This paper also provides a systematic review of recent scientific research on the application of lidar system technology and the corresponding computational algorithms for data analysis, mainly focusing on deep learning algorithms, in the modern road transportation and maritime sector, based on an extensive analysis of the available scientific literature.

A CAD System for Alzheimer's Disease Classification Using Neuroimaging MRI 2D Slices

Developments in medical care have inspired wide interest in the current decade, especially to their services to individuals living prolonged and healthier lives. Alzheimer's disease (AD) is the most chronic neurodegeneration and dementia-causing disorder. Economic expense of treating AD patients is expected to grow. The requirement of developing a computer-aided technique for early AD categorization becomes even more essential. Deep learning (DL) models offer numerous benefits against machine learning tools. Several latest experiments that exploited brain magnetic resonance imaging (MRI) scans and convolutional neural networks (CNN) for AD classification showed promising conclusions. CNN's receptive field aids in the extraction of main recognizable features from these MRI scans. In order to increase classification accuracy, a new adaptive model based on CNN and support vector machines (SVM) is presented in the research, combining both the CNN's capabilities in feature extraction and SVM in classification. The objective of this research is to build a hybrid CNN-SVM model for classifying AD using the MRI ADNI dataset. Experimental results reveal that the hybrid CNN-SVM model outperforms the CNN model alone, with relative improvements of 3.4%, 1.09%, 0.85%, and 2.82% on the testing dataset for AD vs. cognitive normal (CN), CN vs. mild cognitive impairment (MCI), AD vs. MCI, and CN vs. MCI vs. AD, respectively. Finally, the proposed approach has been further experimented on OASIS dataset leading to accuracy of 86.2%.

Research and Implementation of Robot Vision Scanning Tracking Algorithm Based on Deep Learning

In order to solve the difficult problem of deep learning-based robot vision tracking algorithm research and implementation, a deep learning-based target tracking algorithm and a classical tracking algorithm were proposed. It mainly uses the combination of traditional TLD algorithm and GOTURN algorithm to benefit from a large number of offline training data and updates the learner online, so that the whole system has better performance in real-time and accuracy. The results show that the performance of the TLD algorithm is poor regardless of the accuracy curve or the accuracy curve, and the performance of GOTURN-LD is significantly improved when the illumination changes. In the face of occlusion problem, the TLD algorithm shows strong robustness. Although GOTURN-LD is not very stable, its performance is better than GOTURN on the whole.

Visual and buying sequence features-based product image recommendation using optimization based deep residual network

A recommendation system is an imaginative resolution for managing the restrictions in e-commerce services with item details and user details. Also, it is used to determine the user preferences to recommend the items they expected to buy. Several conventional collaborative filtering techniques are devised in the recommender model, but it has some complexities. Hence, an innovative optimization-driven deep residual network is devised in this paper for a product recommendation system. Here, the product of images is used for extracting features where the Convolutional neural network (CNN) features are computed, and then it is given as input to the deep residual network aimed at product recommendation. The deep residual network is trained using developed Elephant Herding Feedback Artificial Optimization (EHFAO), which is obtained by integrating Elephant Herding optimization (EHO) into the Feedback Artificial Tree (FAT). Here, the item grouping is carried out on input data based on K-means clustering. After item grouping, Cosine similarity is used to perform matching of groups, where the best group is acquired among all the available groups. Extraction of list of visitors is done from the best group. Then, the list of items is obtained from the sequence of best visitor. Next, the corresponding binary sequence is obtained for the applicable sequence of visitor. From this sequence of best visitor, the recommended product is acquired. Then, the recommended product is subjected to the sentiment analysis for which the score is determined. Here, the sentiment analysis helps to decide whether the product is recommended or not recommended. If the score is positive, then the same product is recommended; otherwise, the new product is recommended. The proposed EHFAO-based deep residual network attained better performance in comparison to the other techniques with a maximal F-measure at 84.061%, 84.061% precision, 87.845% recall along with minimal Mean Squared Error (MSE) of 0.216.

Intelligent Algorithm-Based Echocardiography to Evaluate the Effect of Lung Protective Ventilation Strategy on Cardiac Function and Hemodynamics in Patients Undergoing Laparoscopic Surgery

The aim of this study was to analyze the effect of optimal pulmonary compliance titration of PEEP regimen on cardiac function and hemodynamics in patients undergoing laparoscopic surgery. 120 patients undergoing elective laparoscopic radical resection of colorectal cancer were included as the study subjects and randomly divided into the experimental group (n = 60) and the control group (n = 60). The control group had a fixed positive end-expiratory pressure (PEEP) = 5 cmH2O. The experimental group had transesophageal ultrasound monitoring through on an improved noise reduction algorithm (ONLM) based on nonlocal mean filtering (NLM) according to optimal pulmonary compliance titration of PEEP. There was significant difference in cerebral oxygen saturation and blood glucose level at T4-T6 between the experimental group and the control group (P < 0.05); the signal-to-noise ratio (SNR), figure of merit (FOM), and structural similarity (SSIM) of ONLM algorithm were significantly higher than those of NLM algorithm and Bayes Shrink denoising algorithm, and the differences were statistically significant (P < 0.05); there was significant difference in stroke volume (SV) and cardiac output (CO) at T4-T6 between the experimental group and the control group (P < 0.05); there was significant difference in pH, partial pressure of carbon dioxide (PCO2), and PO2 at T4-T6 between the experimental group and the control group (P < 0.05); pH was higher, and PCO2 and PO2 were lower in the experimental group. The results showed that transesophageal ultrasound based on the ONLM algorithm can accurately assess cardiac function and hemodynamics in patients undergoing laparoscopic surgery. In addition, optimal pulmonary compliance titration of PEEP could better maintain arterial acid-base balance during perioperative period and increase cerebral oxygen saturation and CO, but this strategy had no significant effect on hemodynamics.

Intelligent Reconstruction Algorithm-Based Computed Tomography Images for Automatic Detection of Gastric Tumor

The aim of this study was to explore the application of computed tomography (CT) images in the diagnosis of gastric tumor under the intelligent reconstruction algorithm (IRA). 120 patients with gastric cancer were selected and all the patients underwent CT scanning, and CT images were analyzed based on the Feldkamp-Davis-Kress algorithm (FDK algorithm) to evaluate the imaging features of gastric lesions. According to biopsy or surgical pathology, the detection rate of CT images was calculated. The results showed that there were three pathological types of benign tumors (polyps, leiomyomas, and mesenchymomas) and three pathological types of malignant tumors (mesenchymomas, adenomas, and lymphomas). In addition, the detection rates of CT scans were different, reaching 94.2% on different orientations of the stomach, 90.7% of benign tumors, and 90.9% of malignant tumors, so the detection rate of different orientations was relatively high. CT images based on the FDK IRA could realize a high detection rate in diagnosis, accurately locate the lesion, and display the characteristics of the lesion and the metastasis of surrounding tissues; there were significant differences between benign and malignant gastric tumors in CT images, and the detection effect was obvious, which is worthy of clinical application and promotion.

An Evaluation System Based on User Big Data Management and Artificial Intelligence for Automatic Vehicles

As artificial intelligence technique is widely used in the automatic driving system, the safety evaluation of automatic vehicles is considered to be the most important demand. Under this context, in this paper, an evaluation system, which is composed of several important evaluation projects is proposed based on big data. These indicators reflect the performance of the automatic driving system. Besides, the principle of the evaluation index and the data management scheme are explained. In terms of the evaluation projects, the online test and the offline test are included, when the former focuses on the function design that is as expected, while the latter aims to ensure the actual driving experience of the automatic driving system. The evaluated results provide optimization direction of the algorithm index. Furthermore, based on AI technology and user big data management, the system saves lots of test cost and guarantees algorithm performance and system stability.

Three-Dimensional Ultrasound Imaging under Optimized Nuclear Regression Reconstruction Algorithm in the Diagnosis Vaginal Delivery and Cesarean Section on the Anal Sphincter Complex of Primiparas

This study was aimed at analyzing the injury of anal sphincter (AS) for primipara caused by the vaginal delivery and cesarean section under the guidance of three-dimensional (3D) ultrasound images. A total of 160 patients who underwent postpartum reexamination were enrolled as the research subjects, including 80 cases of natural delivery (group A) and 80 cases of cesarean section pregnant women (group B), all of whom underwent three-dimensional ultrasound imaging scans. At the same time, an optimized kernel regression reconstruction (KRR) algorithm was proposed for the enhancement of ultrasound images. It was found that the running time after acceleration by the graphics processing unit (GPU) was obviously superior to that of a single-threaded CPU and a multithreaded CPU, showing statistical differences (P < 0.05). The thickness of the proximal and distal external AS in group A was much thinner in contrast to that in group B, showing statistical difference (P < 0.05). Therefore, the 3D ultrasound image based on the optimized KRR algorithm can accurately assess the morphology of AS injury in primipara, and the adverse effect of natural delivery on the AS complex in primipara was greater than that of cesarean section.

Random Walk Algorithm-Based Computer Tomography (CT) Image Segmentation Analysis Effect of Spiriva Combined with Symbicort on Immunologic Function of Non-Small-Cell Lung Cancer

The objective of this research was to explore the effect of the treatment regimen of Spiriva combined with Symbicort on the immune function of non-small-cell lung cancer (NSCLC) based on computed tomography (CT) imaging features. An automatic CT image segmentation algorithm (RW-CT) was constructed based on random walk (RW) and image segmentation technology. The image segmentation algorithm based on the Toboggan method (C-CT) was introduced to compare with the traditional RW algorithm. 60 subjects were divided into four groups: a Chinese combined with Western medicine group (treated with Spiriva combined with Symbicort, group C+W), a Chinese medicine group (treated with Spiriva, group C), a Western medicine group (treated with Symbicort, group W), and a model group for control (group M). The results show that the Dice coefficient of the RW-CT algorithm was obviously larger than that of the C-CT algorithm and the RW algorithm, while the Hausdorff distance (HD) of the RW-CT algorithm was much smaller than that of the other two algorithms ( $P<0.05$ ). The proportion of positive cells of hypoxia-inducible factor-1α (HIF-1α) in group C+W was the least (15%-23%), followed by the group W (21%-29%) and the group C (28%-37%), and that in the group M was the highest (39%-49%). There was a remarkable difference in the immunohistochemical scores (HIS) of vascular endothelial growth factor (VEGF) in the tumor tissues between group C+W and the group M ( $H=14.200$ , $P=0.001$ ), but there was no great difference from the group C and the group W ( $P>0.05$ ). There was a notable difference in the IHS of vascular endothelial factor recepto-2 (VEGFR-2) between the group C+W medication group and the group M ( $H=12.800$ , $P=0.002$ ), and there was no statistical difference between the group C and W ( $P>0.05$ ). In short, the RW-CT constructed based on RW was better than the traditional algorithms for CT image segmentation. The Spiriva combined with Symbicort could effectively inhibit the expression of VEGF, VEGFR-2, and HIF-1α in NSCLC and promote the immunologic function of the body.

Effects of Early Nursing Monitoring on Pregnancy Outcomes of Pregnant Women with Gestational Diabetes Mellitus under Internet of Things

To analyze the effect of early nursing intervention based on fetal heart signal extraction algorithm and Internet of Things (IoT) wireless communication technology on the adverse pregnancy outcomes of pregnant women with gestational diabetes mellitus (GDM) and newborns, 88 pregnant women diagnosed with GDM who underwent the 75 g glucose tolerance test at 24-28 gestational weeks in the hospital were selected as the research objects. According to the different intervention methods, the patients were divided into 44 cases of the experimental group (nursing intervention based on maternal and infant monitoring system) and 44 cases of the control group (outpatient follow-up intervention). The results showed that the compliance score and diet compliance rate of patients in the experimental group were signally higher than those in the control group at 1 and 3 months after intervention (P < 0.05). The levels of fasting blood glucose (FBG), blood glucose 2 hours after the meal, and hemoglobin A1c (HbA1c) in the experimental group were lower than those in the control group at 1 and 3 months after intervention (P < 0.05). The number of giant babies, hypoglycemia, hyperbilirubinemia, fetal distress, premature delivery, and birth weight in the experimental group was all lower than those in the control group, while the Apgar scores were higher than that in the control group (P < 0.05). To sum up, the intervention based on the intelligent maternal and infant monitoring system could timely help pregnant women adjust their diet structure and optimize the management of blood glucose and blood lipids, thus effectively improving the adverse pregnancy outcome and maintaining the health of pregnant women and newborns.

V. Fusion Based AER System Using Deep Learning Approach for Amplitude and Frequency Analysis

Automatic emotion recognition from Speech (AERS) systems based on acoustical analysis reveal that some emotional classes persist with ambiguity. This study employed an alternative method aimed at providing deep understanding into the amplitude–frequency, impacts of various emotions in order to aid in the advancement of near term, more effectively in classifying AER approaches. The study was undertaken by converting narrow 20 ms frames of speech into RGB or grey-scale spectrogram images. The features have been used to fine-tune a feature selection system that had previously been trained to recognise emotions. Two different Linear and Mel spectral scales are used to demonstrate a spectrogram. An inductive approach for in sighting the amplitude and frequency features of various emotional classes. We propose a two-channel profound combination of deep fusion network model for the efficient categorization of images. Linear and Mel- spectrogram is acquired from Speech-signal, which is prepared in the recurrence area to input Deep Neural Network. The proposed model Alex-Net with five convolutional layers and two fully connected layers acquire most vital features form spectrogram images plotted on the amplitude-frequency scale. The state-of-the-art is compared with benchmark dataset (EMO-DB). RGB and saliency images are fed to pre-trained Alex-Net tested both EMO-DB and Telugu dataset with an accuracy of 72.18% and fused image features less computations reaching to an accuracy 75.12%. The proposed model show that Transfer learning predict efficiently than Fine-tune network. When tested on Emo-DB dataset, the propȯsed system adequately learns discriminant features from speech spectrȯgrams and outperforms many stȧte-of-the-art techniques.

Clinical Trial Classification of SNS24 Calls with Neural Networks

SNS24, the Portuguese National Health Contact Center, is a telephone and digital public service that provides clinical services. SNS24 plays an important role in the identification of users’ clinical situations according to their symptoms. Currently, there are a number of possible clinical algorithms defined, and selecting the appropriate clinical algorithm is very important in each telephone triage episode. Decreasing the duration of the phone calls and allowing a faster interaction between citizens and SNS24 service can further improve the performance of the telephone triage service. In this paper, we present a study using deep learning approaches to build classification models, aiming to support the nurses with the clinical algorithm’s choice. Three different deep learning architectures, namely convolutional neural network (CNN), recurrent neural network (RNN), and transformers-based approaches are applied across a total number of 269,654 call records belonging to 51 classes. The CNN, RNN, and transformers-based model each achieve an accuracy of 76.56%, 75.88%, and 78.15% over the test set in the preliminary experiments. Models using the transformers-based architecture are further fine-tuned, achieving an accuracy of 79.67% with Adam and 79.72% with SGD after learning rate fine-tuning; an accuracy of 79.96% with Adam and 79.76% with SGD after epochs fine-tuning; an accuracy of 80.57% with Adam after the batch size fine-tuning. Analysis of similar clinical symptoms is carried out using the fine-tuned neural network model. Comparisons are done over the labels predicted by the neural network model, the support vector machines model, and the original labels from SNS24. These results suggest that using deep learning is an effective and promising approach to aid the clinical triage of the SNS24 phone call services.

Risk Factor Analysis for Predicting the Onset of Rotator Cuff Calcific Tendinitis Based on Artificial Intelligence

Background

Symptomatic rotator cuff calcific tendinitis (RCCT) is a common shoulder disorder, and approaches combined with artificial intelligence greatly facilitate the development of clinical practice. Current scarce knowledge of the onset suggests that clinicians may need to explore this disease thoroughly.

Methods

Clinical data were retrospectively collected from subjects diagnosed with RCCT at our institution within the period 2008 to 2020. A standardized questionnaire related to shoulder symptoms was completed in all cases, and standardized radiographs of both shoulders were extracted using a human-computer interactive electronic medical system (EMS) to clarify the clinical diagnosis of symptomatic RCCT. Based on the exclusion of asymptomatic subjects, risk factors in the baseline characteristics significantly associated with the onset of symptomatic RCCT were assessed via stepwise logistic regression analysis.

Results

Of the 1,967 consecutive subjects referred to our academic institution for shoulder discomfort, 237 were diagnosed with symptomatic RCCT (12.05%). The proportion of women and the prevalence of clinical comorbidities were significantly higher in the RCCT cohort than those in the non-RCCT cohort. Stepwise logistic regression analysis confirmed that female gender, hyperlipidemia, diabetes mellitus, and hypothyroidism were independent risk factors for the entire cohort. Stratified by gender, the study found a partial overlap of risk factors contributing to morbidity in men and women. Diagnosis of hyperlipidemia, diabetes mellitus, and hypothyroidism in male cases and diabetes mellitus in female cases were significantly associated with symptomatic RCCT.

Conclusion

Independent predictors of symptomatic RCCT are female, hyperlipidemia, diabetes mellitus, and hypothyroidism. Men diagnosed with hyperlipidemia, diabetes mellitus, and hypothyroidism are at high risk for symptomatic RCCT, while more medical attention is required for women with diabetes mellitus. Artificial intelligence offers pioneering innovations in the diagnosis and treatment of musculoskeletal disorders, and careful assessment through individualized risk stratification can help predict onset and targeted early stage treatment.

POIs Category Recommendation for Cultural Country Travel Enterprises based on Check-in Information

With the ever-increasing popularity of traveling market, more and more people are willing to spend their time and enjoy life by visiting some Point Of Interests (POI) especially for the citizens living in city. Therefore, it is of practical and significant value for travel enterprises to recommend appropriate country POIs to target travelers. However, the massive POIs as well as their diversity place a heavy burden on the POIs recommendation decision-makings especially when the available historical traveler-POIs check-in data are very sparse. In view of this challenge, we put forward a novel cultural country POIs category recommendation method based on historical knowledge and experienced information, e.g., check-in time and POIs category, i.e., CPCR. At last, CPCR method is evaluated via experiments on WS-DREAM dataset.

Differentiation of lumbar disc herniation and lumbar spinal stenosis using natural language processing–based machine learning based on positive symptoms

OBJECTIVE

The purpose of this study was to develop natural language processing (NLP)–based machine learning algorithms to automatically differentiate lumbar disc herniation (LDH) and lumbar spinal stenosis (LSS) based on positive symptoms in free-text admission notes. The secondary purpose was to compare the performance of the deep learning algorithm with the ensemble model on the current task.

METHODS

In total, 1921 patients whose principal diagnosis was LDH or LSS between June 2013 and June 2020 at Zhongda Hospital, affiliated with Southeast University, were retrospectively analyzed. The data set was randomly divided into a training set and testing set at a 7:3 ratio. Long Short-Term Memory (LSTM) and extreme gradient boosting (XGBoost) models were developed in this study. NLP algorithms were assessed on the testing set by the following metrics: receiver operating characteristic (ROC) curve, area under the curve (AUC), accuracy score, recall score, F1 score, and precision score.

RESULTS

In the testing set, the LSTM model achieved an AUC of 0.8487, accuracy score of 0.7818, recall score of 0.9045, F1 score of 0.8108, and precision score of 0.7347. In comparison, the XGBoost model achieved an AUC of 0.7565, accuracy score of 0.6961, recall score of 0.7387, F1 score of 0.7153, and precision score of 0.6934.

CONCLUSIONS

NLP-based machine learning algorithms were a promising auxiliary to the electronic health record in spine disease diagnosis. LSTM, the deep learning model, showed better capacity compared with the widely used ensemble model, XGBoost, in differentiation of LDH and LSS using positive symptoms. This study presents a proof of concept for the application of NLP in prediagnosis of spine disease.

Financial Market Sentiment Prediction Technology and Application Based on Deep Learning Model

In the real world, there are a variety of situations that require strategy control, that is reinforcement learning, as a method for studying the decision-making and behavioral strategies of intelligence. It has received a lot of research and empirical evidence on its functions and roles and is also a method recognized by scholars. Among them, combining reinforcement learning with sentiment analysis is an important theoretical research direction, but so far there is still relatively little research work about it, and it still has the problems of poor application effect and low accuracy rate. Therefore, in this study, we use the features related to sentiment analysis and deep reinforcement learning and use various algorithms for optimization to deal with the above problems. In this study, a sentiment analysis method incorporating knowledge graphs is designed using the characteristics of the stock trading market. A deep reinforcement learning investment trading strategy algorithm for sentiment analysis combined with knowledge graphs from this study is used in the subsequent experiments. The deep reinforcement learning system combining sentiment analysis and knowledge graph implemented in this study not only analyzes the algorithm from the theoretical aspect but also simulates data from the stock exchange market for experimental comparison and analysis. The experimental results illustrate that the deep reinforcement learning algorithm combining sentiment analysis and knowledge graphs used in this study can achieve better gains than the existing traditional reinforcement learning algorithms and has better practical application value.