Comparative analysis of supervised learning algorithms for prediction of cardiovascular diseases.

BACKGROUND: With the advent of artificial intelligence technology, machine learning algorithms have been widely used in the area of disease prediction. OBJECTIVE: Cardiovascular disease (CVD) seriously jeopardizes human health worldwide, thereby needing the establishment of an effective CVD prediction model that can be of great significance for controlling the risk of the disease and safeguarding the physical and mental health of the population. METHODS: Considering the UCI heart disease dataset as an example, initially, a single machine learning prediction model was constructed. Subsequently, six methods such as Pearson, chi-squared, RFE and LightGBM were comprehensively used for the feature screening. On the basis of the base classifiers, Soft Voting fusion and Stacking fusion was carried out to build a prediction model for cardiovascular diseases, in order to realize an early warning and disease intervention for high-risk populations. To address the data imbalance problem, the SMOTE method was adopted to process the data set, and the prediction effect of the model was analyzed using multi-dimensional and multi-indicators. RESULTS: In the single classifier model, the MLP algorithm performed optimally on the preprocessed heart disease dataset. After feature selection, five features eliminated. The ENSEM_SV algorithm that combines the base classifiers to determine the prediction results by soft voting on the results of the classifiers achieved the optimal value on five metrics such as Accuracy, Jaccard_Score, Hamm_Loss, AUC, etc., and the AUC value reached 0.951. The RF, ET, GBDT, and LGB algorithms were employed in the first stage sub-model composed of base classifiers. The AB algorithm was selected as the second stage model, and the ensemble algorithm ENSEM_ST, obtained by Stacking fusion of the two stages exhibited the best performance on 7 indicators such as Accuracy, Sensitivity, F1_Score, Mathew_Corrcoef, etc., and the AUC reached 0.952. Furthermore, a comparison of the algorithms' classification effects based on different training set occupancy was carried out. The results indicated that the prediction performance of both the fusion models was better than the single models, and the overall effect of ENSEM_ST fusion was stronger than the ENSEM_SV fusion. CONCLUSIONS: The fusion model established in this study improved the overall classification accuracy and stability of the model to a significant extent. It has a good application value in the predictive analysis of CVD diagnosis, and can provide a valuable reference in the disease diagnosis and intervention strategies.

Polymer-based cascaded waveguide Bragg grating for blood glucose sensing.

Waveguide Bragg grating (WBG) blood glucose sensing, as a biological sensing technology with broad application prospects, plays an important role in the fields of health management and medical treatment. In this work, a polymer-based cascaded WBG is applied to glucose detection. We investigated photonic devices with two different grating structures cascaded-a crossed grating and a bilateral grating-and analyzed the effects of the crossed grating period, bilateral grating period, and number of grating periods on the sensing performance of the glucose sensor. Finally, the spectral reflectance characteristics, response time, and sensing specificity of the cascaded WBG were evaluated. The experimental results showed that the glucose sensor has a sensitivity of 175 nm/RIU in a glucose concentration range of 0-2 mg/ml and has the advantages of high integration, a narrow bandwidth, and low cost.

Fabrication and characterization of polymer optical waveguide Bragg grating for pulse signal sensing.

Polymer materials have the advantages of a low Young's modulus and low-cost preparation process. In this paper, a polymer-based optical waveguide pressure sensor based on a Bragg structure is proposed. The change in the Bragg wavelength in the output spectrum of the waveguide Bragg grating (WBG) is used to linearly characterize the change in pressure acting on the device. The polymer-based WBG was developed through a polymer film preparation process, and the experimental results show that the output signal of the device has a sensitivity of 1.275 nm/kPa with a measurement range of 0-12 kPa and an accuracy of 1 kPa. The experimental results indicate that the device already perfectly responds to a pulse signal. It has significant potential application value in medical diagnostics and health testing, such as blood pressure monitoring, sleep quality monitoring, and tactile sensing.

Low half-wave voltage polymeric electro-optic modulator using CLD-1/PMMA for electrocardiogram (ECG) signal acquisition.

Electro-optic (EO) modulators are typically made of inorganic materials such as lithium niobate; the replacement of these modulators with organic EO materials is a promising alternative due to their lower half-wave voltage (Vπ), ease of handling, and relatively low cost. We propose the design and fabrication of a push-pull polymer electro-optic modulator with voltage-length parameters (VπL) of 1.28 V·cm. The device uses a Mach-Zehnder structure and is made of a second-order nonlinear optical host-guest polymer composed of a CLD-1 chromophore and PMMA polymer. The experimental results show that the loss is 1.7 dB, Vπ drops to 1.6 V, and the modulation depth is 0.637 dB at 1550 nm. The results of a preliminary study show that the device is capable of efficiently detecting electrocardiogram (ECG) signals with performance on par with that of commercial ECG devices.

Comparative analysis of weka-based classification algorithms on medical diagnosis datasets.

BACKGROUND: With the advent of 5G and the era of Big Data, the rapid development of medical information technology around the world, the massive application of electronic medical records and cases, and the digitization of medical equipment and instruments, a large amount of data has accumulated in the database system of hospitals, which includes clinical diagnosis data and hospital management data. OBJECTIVE: This study aimed to examine the classification effects of different machine learning algorithms on medical datasets so as to better explore the value of machine learning methods in aiding medical diagnosis. METHODS: The classification datasets of four different medical fields in the University of California Irvine machine learning database were used as the research object. Also, six categories of classification models based on the Bayesian theorem idea, integrated learning idea, and rule-based and tree-based idea were constructed using the Weka platform. RESULTS: The between-group experiments showed that the Random Forest algorithm achieved the best results on the Indian liver disease patient dataset (ILPD), delivery cardiotocography (CADG), and lymphatic tractography (LYMP) datasets, followed by Bagging and partition and regression tree. In the within-group algorithm comparison experiments, the Bagging algorithm achieved better results than other algorithms based on the integration idea for 11 metrics on all datasets, mainly focusing on 2 binary datasets. Logit Boost had only 7 metrics with significant performance, and the best algorithm was Rotation Forest, with 28 metrics achieving optimal values. Among the algorithms based on tree ideas, the logistic model tree algorithm achieved optimal results on all metrics on the mammographic dataset (MAGR). The classification performance of BFTree, J48, and Random Tree was poor on each dataset. The best algorithm was Random Forest on the ILPD, CADG, and LYMP datasets with 27 metrics reaching the optimum. CONCLUSION: Machine learning algorithms have good application value in disease prediction and can provide a reference basis for disease diagnosis.

Silicon-photonics-based waveguide Bragg grating sensor for blood glucose monitoring.

We demonstrated the design of two different structures, a two-sided structure and a top-surface structure, of glucose waveguide Bragg grating (WBG) sensors in a single-mode silicon-on-insulator (SOI) chip. A two-sided WBG structure was fabricated, and chip preparation was realized by lithography and other processes. A photonic platform for testing the two-sided WBG using glucose was built and completed. When the blood glucose concentration changed by 1 mg/mL, the two-sided WBG had a wavelength offset of 78 pm. The experimental results show that the two structures can achieve the sensing of different blood glucose concentrations. The two-sided WBG had better sensing performance and thus has a wide range of application prospects.

Sustaining eSports Industry and Regulatory Focus: Empirical Evidence From Chinese Universities.

This study examined the factors that affect the attitude and behavioral intentions toward electronic sports (eSports) among students of higher education institutions based on the technology acceptance model (TAM). The conditional impact of preventive regulatory focus was analyzed in various aspects developed on the regulatory focus theory. These aspects comprised of perceived usefulness, perceived ease of use, and perceived risk on the attitude toward eSports. Accordingly, data were collected from 293 students of higher education institutions in China's Henan Province, presenting a 54.56% response rate. The PLS-SEM analysis was subsequently implemented to confirm the proposed hypotheses. The empirical findings confirmed the significant positive impact of perceived usefulness and perceived ease of use on the attitude toward eSports. However, perceived risk negatively affected the attitude toward eSports. Meanwhile, the findings on the moderating hypotheses found a negligible impact on preventive regulatory focus. This impact was found explicitly on the perceived usefulness-perceived ease of use link with attitude toward eSports. However, the preventive regulatory focus negatively moderated the perceived risk attitude toward eSports. Finally, the implication and limitations were illustrated at the end of the paper.

An Optimization Algorithm for Computer-Aided Diagnosis of Breast Cancer Based on Support Vector Machine.

As one of the most vulnerable cancers of women, the incidence rate of breast cancer in China is increasing at an annual rate of 3%, and the incidence is younger. Therefore, it is necessary to conduct research on the risk of breast cancer, including the cause of disease and the prediction of breast cancer risk based on historical data. Data based statistical learning is an important branch of modern computational intelligence technology. Using machine learning method to predict and judge unknown data provides a new idea for breast cancer diagnosis. In this paper, an improved optimization algorithm (GSP_SVM) is proposed by combining genetic algorithm, particle swarm optimization and simulated annealing with support vector machine algorithm. The results show that the classification accuracy, MCC, AUC and other indicators have reached a very high level. By comparing with other optimization algorithms, it can be seen that this method can provide effective support for decision-making of breast cancer auxiliary diagnosis, thus significantly improving the diagnosis efficiency of medical institutions. Finally, this paper also preliminarily explores the effect of applying this algorithm in detecting and classifying breast cancer in different periods, and discusses the application of this algorithm to multiple classifications by comparing it with other algorithms.

Transformation of NSCLC to SCLC after 1st- and 3rd-generation EGFR-TKI resistance and response to EP regimen and erlotinib: 2 CARE-compliant case reports.

RATIONALE: Genotypic and histological evolution of non-small-cell lung cancer (NSCLC) into small-cell lung cancer (SCLC) has been described as a mechanism of acquired resistance to epidermal growth factor receptor (EGFR) tyrosine kinase inhibitor (TKI) therapy. However, the number of clinical cases is rare. PATIENT CONCERNS: Two lung adenocarcinoma patients with EGFR mutations who recurred after radical resection transformed into SCLC under treatment with the sequential first- and third-generation EGFR-TKIs. DIAGNOSIS: The 2 cases were both confirmed as SCLC by pathological rebiopsy after EGFR-TKIs resistance. INTERVENTIONS: Case 1 was treated with etoposide plus cisplatin (EP) regimen and erlotinib, while case 2 was treated with erlotinib and EP followed by oral etoposide. OUTCOMES: Case 1 treated with EP only achieved 3-month progression-free survival (PFS), which is the first case that reported T790 M/C797S cis-mutation for osimertinib resistance before the SCLC transformation. However, case 2 treated with erlotinib and EP followed by oral etoposide, PFS lasted for 8 months. LESSONS: The cases highlighted the importance of rebiopsy that identified pathologically SCLC transformation after EGFR-TKI resistance, and suggested the treatment of erlotinib plus EP followed by etoposide, which could provide a reference for such phenotype.

Xuebijing attenuates decompression-induced lung injuries.

INTRODUCTION: The lung is among the primary organs involved in decompression sickness (DCS). Xuebijing (XBJ), a traditional Chinese medicine, has been widely used in the treatment of various acute lung diseases. This study aimed to explore potential benefit of XBJ on lung injuries induced by DCS in a rabbit model. METHODS: Twenty-four male New Zealand white rabbits underwent a simulated air dive to 50 meters' sea water for 60 min with 2.5 min decompression, and received an intravenous injection of XBJ (5 ml·kg-1) or an equal volume of saline immediately following decompression. DCS signs were monitored for 24 h, and blood was sampled before simulated diving and at 6 h and 12 h following decompression for determination of inflammatory indices. Lung tissues were sampled after euthanasia for histology analysis and lung water content, as well as tumour necrosis factor-α level. Another six rabbits were used as control. RESULTS: XBJ significantly ameliorated lung injuries (lung wet/dry ratio and total protein content in bronchoalveolar lavage fluid), and notably inhibited systemic (serum level of interleukin-1ß) and local (tumour necrosis factor-α in bronchoalveolar lavage fluid) inflammation responses. CONCLUSIONS: The results strongly suggest the benefits of XBJ on ameliorating DCS lung injuries, which is possibly via inhibiting systemic and local inflammation. XBJ may be a potential candidate for the treatment of decompression-induced lung injuries.

Ulinastatin: A Potential Alternative to Glucocorticoid in the Treatment of Severe Decompression Sickness.

Inflammatory reaction is the crux in various clinical critical diseases including decompression sickness (DCS). Ulinastatin (UTI), a potent anti-inflammatory agent, has been used clinically, including as a substitution for steroids. This study aimed to explore the potential effects of UTI upon DCS in a rabbit model. Eighty-eight rabbits were subjected to simulated diving to 6 atmospheres absolute (ATA) for 60 min with 2.5-minute decompression. Three doses of UTI (15/7.5/3.75 × 105 U/kg) or saline were intravenously administered immediately following decompression. Circulating bubbles were monitored for 3 h following decompression and DCS signs were evaluated for 24 h. Blood was sampled 8 times during 72 h after decompression for inflammatory, endothelial, oxidative and routine blood indices. Lung tissues were also sampled for evaluating endothelial function. Another six rabbits were used as Normal controls. In the high dose UTI group the mortality, general morbidity and incidence of severe DCS was decreased from 31.25 to 9.38% (P = 0.030), 84.38 to 62.50% (P = 0.048) and 46.88 to 21.88% (P = 0.035), respectively. The high dose of UTI significantly postponed the occurrence of DCS (P = 0.030) and prolonged survival time (P = 0.009) compared with the Saline group, and significantly ameliorated inflammation responses, endothelial injuries and oxidative damage. The results strongly suggest the benefit of UTI on DCS, especially for severe cases. Large doses are needed to achieve significant effects. UTI may be a potential ideal pharmacological candidate for the treatment of severe DCS.

Corrigendum: Benefits of Escin for Decompression Sickness in Bama Pigs by Endothelial-Targeting Protection.

[This corrects the article DOI: 10.3389/fphys.2019.00605.].

Benefits of Escin for Decompression Sickness in Bama Pigs by Endothelial-Targeting Protection.

Endothelial dysfunction has been considered as pivotal in the pathogenesis of decompression sickness (DCS) and contributes substantively to subsequent inflammatory responses. Escin is well known for its endothelial protection and anti-inflammatory properties, and its protection against DCS has been proved in a rat model. This study aimed to further investigate the protection of escin against DCS in swine. Sixteen swine were subjected to a two-stage experiment with an interval of 7 days. In each stage, 7 days before a simulated air dive, the swine were treated with escin or saline. The first group received a successive administration of escin for 7 days prior to the first dive and saline for 7 days prior to the second; the second group was treated with saline and then escin. After decompression, signs of DCS and circulating bubbles were monitored, and blood was sampled for platelet count and determination of inflammatory and endothelial related indices. The death rate of DCS was markedly decreased in swine treated with escin compared with that in animals treated with saline, though not statistically significant due to the limited number of animals. Escin had no effect on bubble load but significantly ameliorated platelet reduction and endothelial dysfunction, as well as oxidative and inflammatory responses. The results further suggest the beneficial effects of escin on DCS by its endothelia-protective properties, and escin has the potential to be a candidate drug for DCS prevention and treatment.