scholarly journals Prediction model for Prolonged fever in patients with Mycoplasma pneumoniae pneumonia : A retrospective study of 716 pediatric patients

2020 ◽  
Author(s):  
Min Sik Jang ◽  
Bit Kyeol Kim ◽  
Jihye Kim
Keyword(s):  
Neural Network ◽  
Retrospective Study ◽  
Prediction Model ◽  
Mycoplasma Pneumoniae ◽  
Prediction Models ◽  
Laboratory Data ◽  
Predictive Values ◽  
Prolonged Fever ◽  
Laboratory Values ◽  
Increased Sensitivity

Abstract Background: To identify patients with Mycoplasma pneumoniae pneumonia (MPP) with a risk of prolonged fever while on macrolides. Methods: A retrospective study was performed with 716 children admitted for MPP. Refractory MPP (RMPP) was defined as fever persisting for >72 hours after macrolide antibiotics (RMPP-3) or when fever persisted for >120 hours (RMPP-5). Radiological data, laboratory data, and fever profiles were compared between the RMPP and non-RMPP groups. Fever profiles included the highest temperature, lowest temperature, and frequency of fever. Prediction models for RMPP were created using the logistic regression method and deep neural network. Their predictive values were compared using receiver operating characteristic curves.Results: Overall, 716 patients were randomly divided into two groups: training and test cohorts for both RMPP-3 and RMPP-5. For the prediction of RMPP-3, a conventional logistic model with radiologic grouping showed increased sensitivity (63.3%) than the model using laboratory values. Adding laboratory values in the prediction model using radiologic grouping did not contribute to a meaningful increase in sensitivity (64.6%). For the prediction of RMPP-5, laboratory values or radiologic grouping showed lower sensitivities ranging from 12.9%–16.1%. However, prediction models using predefined fever profiles showed significantly increased sensitivity for predicting RMPP-5, and neural network models using 12 sequential fever data showed a greatly increased sensitivity (64.5%).Conclusions: RMPP-5 could not be effectively predicted using initial laboratory and radiologic data, which were previously reported to be predictive. Further studies using advanced mathematical models, based on large-sized easily accessible clinical data, are anticipated for predicting RMPP.

scholarly journals Prediction model for prolonged fever in patients with Mycoplasma pneumoniae pneumonia: a retrospective study of 716 pediatric patients

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Min Sik Jang ◽  
Bit Gyeol Kim ◽  
Jihye Kim
Keyword(s):  
Neural Network ◽  
Retrospective Study ◽  
Prediction Model ◽  
Mycoplasma Pneumoniae ◽  
Prediction Models ◽  
Predictive Values ◽  
Prolonged Fever ◽  
Radiologic Findings ◽  
Laboratory Values ◽  
Increased Sensitivity

Abstract Objective To identify patients with Mycoplasma pneumoniae pneumonia (MPP) with a risk of prolonged fever while on macrolides. Methods A retrospective study was performed with 716 children admitted for MPP. Refractory MPP (RMPP-3) was defined as fever persisting for > 72 h without improvement in clinical and radiologic findings after macrolide antibiotics (RMPP-3) or when fever persisted for > 120 h (RMPP-5) without improvement in clinical and radiologic findings. Radiological data, laboratory data, and fever profiles were compared between the RMPP and non-RMPP groups. Fever profiles included the highest temperature, lowest temperature, and frequency of fever. Prediction models for RMPP were created using the logistic regression method and deep neural network. Their predictive values were compared using receiver operating characteristic curves. Results Overall, 716 patients were randomly divided into two groups: training and test cohorts for both RMPP-3 and RMPP-5. For the prediction of RMPP-3, a conventional logistic model with radiologic grouping showed increased sensitivity (63.3%) than the model using laboratory values. Adding laboratory values in the prediction model using radiologic grouping did not contribute to a meaningful increase in sensitivity (64.6%). For the prediction of RMPP-5, laboratory values or radiologic grouping showed lower sensitivities ranging from 12.9 to 16.1%. However, prediction models using predefined fever profiles showed significantly increased sensitivity for predicting RMPP-5, and neural network models using 12 sequential fever data showed a greatly increased sensitivity (64.5%). Conclusion RMPP-5 could not be effectively predicted using initial laboratory and radiologic data, which were previously reported to be predictive. Further studies using advanced mathematical models, based on large-sized easily accessible clinical data, are anticipated for predicting RMPP.

scholarly journals Dynamic Modulus Prediction of a High-Modulus Asphalt Mixture

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Chaohui Wang ◽  
Songyuan Tan ◽  
Qian Chen ◽  
Jiguo Han ◽  
Liang Song ◽  
...  
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Multiple Regression ◽  
Dynamic Modulus ◽  
Prediction Error ◽  
Prediction Models ◽  
Asphalt Mixture ◽  
High Modulus ◽  
Output Stability ◽  
Svm Model

Dynamic modulus is a key evaluation index of the high-modulus asphalt mixture, but it is relatively difficult to test and collect its data. The purpose is to achieve the accurate prediction of the dynamic modulus of the high-modulus asphalt mixture and further optimize the design process of the high-modulus asphalt mixture. Five high-temperature performance indexes of high-modulus asphalt and its mixture were selected. The correlation between the above five indexes and the dynamic modulus of the high-modulus asphalt mixture was analyzed. On this basis, the dynamic modulus prediction models of the high-modulus asphalt mixture based on small sample data were established by multiple regression, general regression neural network (GRNN), and support vector machine (SVM) neural network. According to parameter adjustment and cross-validation, the output stability and accuracy of different prediction models were compared and evaluated. The most effective prediction model was recommended. The results show that the SVM model has more significant prediction accuracy and output stability than the multiple regression model and the GRNN model. Its prediction error was 0.98–9.71%. Compared with the other two models, the prediction error of the SVM model declined by 0.50–11.96% and 3.76–13.44%. The SVM neural network was recommended as the dynamic modulus prediction model of the high-modulus asphalt mixture.

A Model Based on BP Neural Network for Audible Noise Prediction

2014 ◽  
Vol 986-987 ◽  
pp. 1356-1359
Author(s):  
You Xian Peng ◽  
Bo Tang ◽  
Hong Ying Cao ◽  
Bin Chen ◽  
Yu Li
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Transmission Lines ◽  
Bp Neural Network ◽  
Prediction Models ◽  
Absolute Error ◽  
Research Area ◽  
Noise Prediction ◽  
Bp Network ◽  
Model Based

Audible noise prediction is a hot research area in power transmission engineering in recent years, especially come down to AC transmission lines. The conventional prediction models at present have got some problems such as big errors. In this paper, a prediction model is established based on BP network, in which the input variables are the four factors in the international common expression of power line audible noise and the noise value is the output. Take multiple measured power lines as an example, a train is made by the BP network and then the prediction model is set up in the hidden layer of the network. Using the trained model, the audible noise values are predicted. The final results show that the average absolute error in absolute terms of the values by the audible noise prediction model based on BP neural network is 1.6414 less than that predicted by the GE formula.

Predicting Complete Ground Reaction Forces and Moments During Gait With Insole Plantar Pressure Information Using a Wavelet Neural Network

2015 ◽  
Vol 137 (9) ◽  
Author(s):  
Taeyong Sim ◽  
Hyunbin Kwon ◽  
Seung Eel Oh ◽  
Su-Bin Joo ◽  
Ahnryul Choi ◽  
...  
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Plantar Pressure ◽  
Prediction Models ◽  
Pressure Sensors ◽  
Principal Component ◽  
Wavelet Neural Network ◽  
Human Gait ◽  
Ground Reaction Forces ◽  
Reaction Forces

In general, three-dimensional ground reaction forces (GRFs) and ground reaction moments (GRMs) that occur during human gait are measured using a force plate, which are expensive and have spatial limitations. Therefore, we proposed a prediction model for GRFs and GRMs, which only uses plantar pressure information measured from insole pressure sensors with a wavelet neural network (WNN) and principal component analysis-mutual information (PCA-MI). For this, the prediction model estimated GRFs and GRMs with three different gait speeds (slow, normal, and fast groups) and healthy/pathological gait patterns (healthy and adolescent idiopathic scoliosis (AIS) groups). Model performance was validated using correlation coefficients (r) and the normalized root mean square error (NRMSE%) and was compared to the prediction accuracy of the previous methods using the same dataset. As a result, the performance of the GRF and GRM prediction model proposed in this study (slow group: r = 0.840–0.989 and NRMSE% = 10.693–15.894%; normal group: r = 0.847–0.988 and NRMSE% = 10.920–19.216%; fast group: r = 0.823–0.953 and NRMSE% = 12.009–20.182%; healthy group: r = 0.836–0.976 and NRMSE% = 12.920–18.088%; and AIS group: r = 0.917–0.993 and NRMSE% = 7.914–15.671%) was better than that of the prediction models suggested in previous studies for every group and component (p < 0.05 or 0.01). The results indicated that the proposed model has improved performance compared to previous prediction models.

Short-Term Wind Power Dynamic Prediction Based on GA-BP Neural Network

2014 ◽  
Vol 986-987 ◽  
pp. 524-528 ◽  
Author(s):  
Ting Jing Ke ◽  
Min You Chen ◽  
Huan Luo
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Wind Power ◽  
Bp Neural Network ◽  
Prediction Models ◽  
Model Parameters ◽  
Short Term ◽  
Dynamic Prediction ◽  
Power Dynamic ◽  
Prediction Approach

This paper proposes a short-term wind power dynamic prediction model based on GA-BP neural network. Different from conventional prediction models, the proposed approach incorporates a prediction error adjusting strategy into neural network based prediction model to realize the function of model parameters self-adjusting, thus increase the prediction accuracy. Genetic algorithm is used to optimize the parameters of BP neural network. The wind power prediction results from different models with and without error adjusting strategy are compared. The comparative results show that the proposed dynamic prediction approach can provide more accurate wind power forecasting.

scholarly journals The Impact Prediction Models of Neoplasia for Lung Nodules in High-Risk Patients

2020 ◽  
Vol 3 (3) ◽  
pp. 138-146
Author(s):  
Camilla Matos Pedreira ◽  
José Alves Barros Filho ◽  
Carolina Pereira ◽  
Thamine Lessa Andrade ◽  
Ricardo Mingarini Terra ◽  
...  
Keyword(s):  
High Risk ◽  
Prediction Model ◽  
Prediction Models ◽  
Lung Nodule ◽  
Smoking History ◽  
Predictive Values ◽  
Impact Prediction ◽  
High Risk Patients ◽  
Risk Patients ◽  
The Impact

Objectives: This study aims to evaluate the impact of using three predictive models of lung nodule malignancy in a population of patients at high-risk for neoplasia according to previous analysis by physicians, as well as evaluate the clinical and radiological malignancy-predictors of the images. Material and Methods: This is a retrospective cohort study, with 135 patients, undergone surgical in the period from 01/07/2013 to 10/05/2016. The study included nodules with dimensions between 5mm and 30mm, excluding multiple nodules, alveolar consolidation, pleural effusion, and lymph node enlargement. The main variables analyzed were age, sex, smoking history, extrathoracic cancer, diameter, location, and presence of spiculation. The calculation of the area under the ROC curve assessed the accuracy of each prediction model. Results: The study analyzed 135 individuals, of which 96 (71.1%) had malignant nodules. The areas under the ROC curves for each prediction model were: Swensen 0.657; Brock 0.662; and Herder 0.633. The models Swensen, Brock, and Herder presented positive predictive values in high-risk patients, corresponding to 83.3%, 81.8%, and 82.9%, respectively. Patients with the intermediate and low-risk presented a high malignant nodule rate, ranging from 69.3-72.5% and 42.8-52.6%, respectively. Conclusion: None of the three quantitative models analyzed in this study was considered satisfactory (AUC> 0.7) and should be used with caution after specialized evaluation to avoid underestimation of the risk of neoplasia. The pretest calculations might not contemplate other factors than those predicted in the regressions, that could present a role in the clinical decision of resection.

scholarly journals Driver Lane-Changing Behavior Prediction Based on Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Cheng Wei ◽  
Fei Hui ◽  
Asad J. Khattak
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Traffic Safety ◽  
Prediction Models ◽  
Time Window ◽  
Driving Safety ◽  
Physiological Data ◽  
Lane Changing ◽  
Proposed Model ◽  
Neural Network Prediction

A correct lane-changing plays a crucial role in traffic safety. Predicting the lane-changing behavior of a driver can improve the driving safety significantly. In this paper, a hybrid neural network prediction model based on recurrent neural network (RNN) and fully connected neural network (FC) is proposed to predict lane-changing behavior accurately and improve the prospective time of prediction. The dynamic time window is proposed to extract the lane-changing features which include driver physiological data, vehicle kinematics data, and driver kinematics data. The effectiveness of the proposed model is validated through the experiments in real traffic scenarios. Besides, the proposed model is compared with five prediction models, and the results show that the proposed prediction model can effectively predict the lane-changing behavior more accurate and earlier than the other models. The proposed model achieves the prediction accuracy of 93.5% and improves the prospective time of prediction by about 2.1 s on average.

scholarly journals Impact of viral coinfection and macrolide-resistant mycoplasma infection in children with refractory Mycoplasma pneumoniae pneumonia

2020 ◽  
Author(s):  
Yajuan Zhou ◽  
Jing Wang ◽  
Wenjuan Chen ◽  
Nan Shen ◽  
Yue Tao ◽  
...  
Keyword(s):  
Prediction Model ◽  
Mycoplasma Pneumoniae ◽  
Medical Center ◽  
Classification Tree ◽  
Severe Disease ◽  
Drug Resistant ◽  
Mycoplasma Infection ◽  
Prolonged Fever ◽  
Lung Consolidation ◽  
Viral Coinfection

Abstract Background: Cases of refractory Mycoplasma pneumoniae pneumonia have been increasing recently; however, whether viral coinfection or macrolide-resistant M. infection contribute to the development of refractory M. pneumoniae pneumonia remains unclear. This study aimed to investigate the impacts of viral coinfection and macrolide-resistant M. pneumoniae infection on M. pneumoniae pneumonia in hospitalized children and build a model to predict a severe disease course. Methods: Nasopharyngeal swabs or sputum specimens were collected from patients with community-acquired pneumonia meeting our protocol who were admitted to Shanghai Children’s Medical Center from December 1, 2016, to May 31, 2019. The specimens were tested with the FilmArray Respiratory Panel, a multiplex polymerase chain reaction assay that detects 16 viruses, Bordetella pertussis, M. pneumoniae, and Chlamydophila pneumoniae. Univariate and multivariate logistic regression models were used to identify the risk factors for adenovirus coinfection and macrolide-resistant mycoplasma infection.Results: Among the 107 M. pneumoniae pneumonia patients, the coinfection rate was 56.07%, and 60 (60/107, 56.07%) patients were infected by drug-resistant M. pneumoniae. Adenovirus was the most prevalent coinfecting organism, accounting for 22.43% (24/107). The classification tree confirmed that viral coinfection was more common in patients younger than 3 years old. Adenovirus coinfection and drug-resistant M. pneumoniae infection occurred more commonly in patients with refractory M. pneumoniae pneumonia (P=0.019; P=0.001). A prediction model including wheezing, lung consolidation and extrapulmonary complications was used to predict adenovirus coinfection. The area under the receiver operating characteristic curve of the prediction model was 0.795 (95% CI 0.679-0.893, P<0.001). A prolonged fever duration after the application of macrolides for 48 hours was found more commonly in patients infected by drug-resistant M. pneumoniae (P=0.002). A fever duration longer than 7 days was an independent risk factor for drug-resistant Mycoplasma infection (OR=3.500, 95% CI=1.310-9.353, P=0.012).Conclusions: The occurrence of refractory M. pneumoniae pneumonia is associated with adenovirus coinfection and infection by drug-resistant M. pneumoniae. A prediction model combining wheezing, extrapulmonary complications and lung consolidation can be used to predict adenovirus coinfection in children with M. pneumoniae pneumonia. A prolonged fever duration indicates drug-resistant M. pneumoniae infection, and a reasonable change in antibiotics is necessary.

scholarly journals Development of a Radiomic-Based Model Predicting Lymph Node Involvement in Prostate Cancer Patients

Cancers ◽  
2021 ◽  
Vol 13 (22) ◽  
pp. 5672
Author(s):  
Vincent Bourbonne ◽  
Vincent Jaouen ◽  
Truong An Nguyen ◽  
Valentin Tissot ◽  
Laurent Doucet ◽  
...  
Keyword(s):  
Neural Network ◽  
Prostate Cancer ◽  
Lymph Node ◽  
Prediction Model ◽  
Risk Prediction ◽  
Prediction Models ◽  
Lymph Node Involvement ◽  
Visual Interpretation ◽  
Node Involvement ◽  
Testing Set

Significant advances in lymph node involvement (LNI) risk modeling in prostate cancer (PCa) have been achieved with the addition of visual interpretation of magnetic resonance imaging (MRI) data, but it is likely that quantitative analysis could further improve prediction models. In this study, we aimed to develop and internally validate a novel LNI risk prediction model based on radiomic features extracted from preoperative multimodal MRI. All patients who underwent a preoperative MRI and radical prostatectomy with extensive lymph node dissection were retrospectively included in a single institution. Patients were randomly divided into the training (60%) and testing (40%) sets. Radiomic features were extracted from the index tumor volumes, delineated on the apparent diffusion coefficient corrected map and the T2 sequences. A ComBat harmonization method was applied to account for inter-site heterogeneity. A prediction model was trained using a neural network approach (Multilayer Perceptron Network, SPSS v24.0©) combining clinical, radiomic and all features. It was then evaluated on the testing set and compared to the current available models using the Receiver Operative Characteristics and the C-Index. Two hundred and eighty patients were included, with a median age of 65.2 y (45.3–79.6), a mean PSA level of 9.5 ng/mL (1.04–63.0) and 79.6% of ISUP ≥ 2 tumors. LNI occurred in 51 patients (18.2%), with a median number of extracted nodes of 15 (10–19). In the testing set, with their respective cutoffs applied, the Partin, Roach, Yale, MSKCC, Briganti 2012 and 2017 models resulted in a C-Index of 0.71, 0.66, 0.55, 0.67, 0.65 and 0.73, respectively, while our proposed combined model resulted in a C-Index of 0.89 in the testing set. Radiomic features extracted from the preoperative MRI scans and combined with clinical features through a neural network seem to provide added predictive performance compared to state of the art models regarding LNI risk prediction in PCa.

scholarly journals Prediction of late-onset fetal growth restriction using a combined first- and second-trimester screening model in South Chinese infants: a retrospective study

2020 ◽  
Author(s):  
Haiqing Zheng ◽  
Yan Feng ◽  
Jiexin Zhang ◽  
Kuanrong Li ◽  
Huiying Liang ◽  
...  
Keyword(s):  
Retrospective Study ◽  
Birth Weight ◽  
Prediction Model ◽  
Fetal Growth ◽  
Fetal Growth Restriction ◽  
Detection Rate ◽  
Prediction Models ◽  
Late Onset ◽  
Validation Dataset ◽  
Second Trimester

Abstract Background: Prediction models for early and late fetal growth restriction (FGR) have been established in many high-income countries. However, prediction models for late FGR in China are limited. This study aimed to develop a simple combined first- and second-trimester prediction model for screening late-onset FGR in South Chinese infants. Methods: This retrospective study included 2258 women who had singleton pregnancies and received routine ultrasound scans as training dataset. A validation dataset including 565 pregnant women was used to evaluate the model in order to enable an unbiased estimation. Late-onset FGR was defined as a birth weight < the 10th percentile plus abnormal Doppler indices and/or a birth weight below the 3rd percentile after 32 weeks, regardless of the Doppler status. Multivariate logistic regression was used to develop a prediction model. The model included the a priori risk (maternal characteristics), the second-trimester head circumference (HC/AC) / abdomen circumference (HC) ratio and estimated fetal weight (EFW). Results: Ninety-three fetuses were identified as late-onset FGR. The significant predictors for late-onset FGR were maternal age, height, weight, and medical history; the second-trimester HC/ AC ratio; and the EFW. This model achieved a detection rate (DR) of 52.6% for late-onset FGR at a 10% false positive rate (FPR) (area under the curve (AUC): 0.80, 95%CI 0.76-0.85). The AUC of the validation dataset was 0.65 (95%CI 0.54-0.78). Conclusions: A multivariate model combining first- and second-trimester default tests can detect 52.6% of cases of late-onset FGR at a 10% FPR. Further studies with more screening markers are needed to improve the detection rate.

Sign in / Sign up

Export Citation Format

Share Document