Training Set Research Articles

Automatic classification and grading of canine tracheal collapse on thoracic radiographs by using deep learning.

Tracheal collapse is a chronic and progressively worsening disease; the severity of clinical symptoms experienced by affected individuals depends on the degree of airway collapse. Cutting-edge automated tools are necessary to modernize disease screening using radiographs across various veterinary settings, such as animal clinics and hospitals. This is primarily due to the inherent challenges associated with interpreting uncertainties among veterinarians. In this study, an artificial intelligence model was developed to screen canine tracheal collapse using archived lateral cervicothoracic radiographs. This model can differentiate between a normal and collapsed trachea, ranging from early to severe degrees. The you-only-look-once (YOLO) models, including YOLO v3, YOLO v4, and YOLO v4 tiny, were used to train and test data sets under the in-house XXX platform. The results showed that the YOLO v4 tiny-416 model had satisfactory performance in screening among the normal trachea, grade 1-2 tracheal collapse, and grade 3-4 tracheal collapse with 98.30% sensitivity, 99.20% specificity, and 98.90% accuracy. The area under the curve of the precision-recall curve was >0.8, which demonstrated high diagnostic accuracy. The intraobserver agreement between deep learning and radiologists was κ=0.975 (P<.001), with all observers having excellent agreement (κ=1.00, P<.001). The intraclass correlation coefficient between observers was >0.90, which represented excellent consistency. Therefore, the deep learning model can be a useful and reliable method for effective screening and classification of the degree of tracheal collapse based on routine lateral cervicothoracic radiographs.

A Random Forest-based Prediction for Liver Cirrhosis

Prediction of cirrhosis through timely screening and diagnosis with effective medical and lifestyle interventions can be taken to delay the disease progression and improve treatment effectiveness. Therefore, early cirrhosis prediction helps reduce associated complications and improve quality of life. This study established a random forest-based algorithm and compared its performance with other machine learning models based on an Indian Liver Patient Records. The dataset was divided 30% of the test set and 70% of the training set. The results showed that the Accuracy, Area under the curve (AUC) and Recall values of Random Forest (RF) model were 0.73, 0.76 and 0.88, respectively, which demonstrated the proposed model can predict the results better than other models. The proposed model for predicting liver cirrhosis in the future will continue to be improved and perfected to improve the accuracy of liver cirrhosis prediction and treatment effect, thereby reducing the health risks and burdens brought by the disease.

Improved random forest model for smoke detection and early warning based on sparrow search algorithm

Smoke detection technology is of great significance in the field of fire safety, aiming at the timely detection of smoke released from fires or other combustion events to safeguard people's lives and properties. In this paper, a smart smoke alarm device is developed based on AI algorithm using UCL open source dataset, which is processed by AI recognition after collecting data through IoT to achieve accurate judgement of smoke situation. The dataset is divided by 6:4 ratio, and the training set confusion matrix shows that all 1159 smoke alarm tests are correctly predicted, of which 445 times predict no smoke and 714 times predict smoke, with an accuracy rate of 100%. The test set confusion matrix shows that only 1 out of 1158 tests was incorrectly predicted, of which 184 predicted no smoke, 312 predicted smoke, and 1 was misjudged as no smoke even though it should have been smoke, with an accuracy rate of 99.7%. The successful application of this technology provides a reliable guarantee for fire warning and demonstrates the great potential of AI in the field of security.

ARDSFlag: an NLP/machine learning algorithm to visualize and detect high-probability ARDS admissions independent of provider recognition and billing codes

BackgroundDespite the significance and prevalence of acute respiratory distress syndrome (ARDS), its detection remains highly variable and inconsistent. In this work, we aim to develop an algorithm (ARDSFlag) to automate the diagnosis of ARDS based on the Berlin definition. We also aim to develop a visualization tool that helps clinicians efficiently assess ARDS criteria.MethodsARDSFlag applies machine learning (ML) and natural language processing (NLP) techniques to evaluate Berlin criteria by incorporating structured and unstructured data in an electronic health record (EHR) system. The study cohort includes 19,534 ICU admissions in the Medical Information Mart for Intensive Care III (MIMIC-III) database. The output is the ARDS diagnosis, onset time, and severity.ResultsARDSFlag includes separate text classifiers trained using large training sets to find evidence of bilateral infiltrates in radiology reports (accuracy of 91.9%±0.5%) and heart failure/fluid overload in radiology reports (accuracy 86.1%±0.5%) and echocardiogram notes (accuracy 98.4%±0.3%). A test set of 300 cases, which was blindly and independently labeled for ARDS by two groups of clinicians, shows that ARDSFlag generates an overall accuracy of 89.0% (specificity = 91.7%, recall = 80.3%, and precision = 75.0%) in detecting ARDS cases.ConclusionTo our best knowledge, this is the first study to focus on developing a method to automate the detection of ARDS. Some studies have developed and used other methods to answer other research questions. Expectedly, ARDSFlag generates a significantly higher performance in all accuracy measures compared to those methods.

Unsupervised shape-and-texture-based generative adversarial tuning of pre-trained networks for carotid segmentation from 3D ultrasound images.

Vessel-wall volume and localized three-dimensional ultrasound (3DUS) metrics are sensitive to the change of carotid atherosclerosis in response to medical/dietary interventions. Manual segmentation of the media-adventitia boundary (MAB) and lumen-intima boundary (LIB) required to obtain these metrics is time-consuming and prone to observer variability. Although supervised deep-learning segmentation models have been proposed, training of these models requires a sizeable manually segmented training set, making larger clinical studiesprohibitive. We aim to develop a method to optimize pre-trained segmentation models without requiring manual segmentation to supervise the fine-tuningprocess. We developed an adversarial framework called the unsupervised shape-and-texture generative adversarial network (USTGAN) to fine-tune a convolutional neural network (CNN) pre-trained on a source dataset for accurate segmentation of a target dataset. The network integrates a novel texture-based discriminator with a shape-based discriminator, which together provide feedback for the CNN to segment the target images in a similar way as the source images. The texture-based discriminator increases the accuracy of the CNN in locating the artery, thereby lowering the number of failed segmentations. Failed segmentation was further reduced by a self-checking mechanism to flag longitudinal discontinuity of the artery and by self-correction strategies involving surface interpolation followed by a case-specific tuning of the CNN. The U-Net was pre-trained by the source dataset involving 224 3DUS volumes with 136, 44, and 44 volumes in the training, validation and testing sets. The training of USTGAN involved the same training group of 136 volumes in the source dataset and 533 volumes in the target dataset. No segmented boundaries for the target cohort were available for training USTGAN. The validation and testing of USTGAN involved 118 and 104 volumes from the target cohort, respectively. The segmentation accuracy was quantified by Dice Similarity Coefficient (DSC), and incorrect localization rate (ILR). Tukey's Honestly Significant Difference multiple comparison test was employed to quantify the difference of DSCs between models and settings, where was considered statisticallysignificant. USTGAN attained a DSC of % in LIB and % in MAB, improving from the baseline performance of % in LIB (p ) and % in MAB (p ). Our approach outperformed six state-of-the-art domain-adaptation models (MAB: , LIB: ). The proposed USTGAN also had the lowest ILR among the methods compared (LIB: 2.5%, MAB: 1.7%). Our framework improves segmentation generalizability, thereby facilitating efficient carotid disease monitoring in multicenter trials and in clinics with less expertise in 3DUSimaging.

Differential Expression of mRNA in Peripheral Blood Mononuclear Cells May Predict Postoperative Atrial Fibrillation in Coronary Artery Bypass Surgery Patients.

Postoperative Atrial Fibrillation (POAF) frequently follows Coronary Artery Bypass Grafting (CABG) surgery. This prospective study investigates genes linked to POAF in CABG patients, aiming to create a predictive model. Employing differential gene and methylation analyses, the study identified four genes (WARS2, CKAP2, CHI3L1, HSD17B6) associated with POAF. Preoperative plasma samples and clinical data were collected from 139 CABG patients, categorized into POAF (+) (43) and POAF (-) (96). Real-time quantitative PCR assessed gene expression, and a predictive model using the LASSO method demonstrated robust performance, with AUC values of 0.8895 in the training set and 0.7840 in the test set. This pioneering study integrates genomics and clinical data, suggesting WARS2, CKAP2, and CHI3L1 as potential indicators for POAF prediction.

Automatic Code Generation for Android Applications Based on Improved Pix2code

With the expansion of the Internet market, the traditional software development method has been difficult to meet the market demand due to the problems of long development cycle, tedious work and difficult system maintenance. Therefore, to improve software development efficiency, this study uses residual networks and bidirectional long short-term memory networks to improve the Pix2code model. The experiment results show that after improving the visual module of the Pix2code model using residual networks, the accuracy of the training set improves from 0.92 to 0.96, and the convergence time is shortened from 3 hours to 2 hours. After using a bidirectional long short-term memory network to improve the language module and decoding layer, the accuracy and convergence speed of the model have also been improved. The accuracy of the training set grew from 0.88 to 0.92, and the convergence time was shortened by 0.5 hours. However, models improved by bidirectional long short-term memory networks might exhibit over-fitting, and thus this study uses Dropout and Xavier normal distribution to improve the memory network. The results validate that the training set accuracy of the optimized bidirectional long short-term memory network remains around 0.92, but the accuracy of the test set has improved to a maximum of 85%. Dropout and Xavier normal distributions can effectively improve the over-fitting problem of bidirectional long short-term memory networks. Although they can also decrease the model’s stability, their gain is higher. The training and testing accuracy of the Pix2code improved by residual network and bidirectional long short-term memory network are 0.95 and 0.82, respectively, while the code generation accuracy of the original Pix2code is only 0.77. The above data indicates that the improved Pix2code model has improved the accuracy and stability of code automatic generation.

Cut-off value of glycated hemoglobin A1c for detecting diabetic retinopathy in the Chinese population

BACKGROUND Glycated hemoglobin A1c (HbA1c) is considered the most suitable for diabetes mellitus diagnosis due to its accuracy and convenience. However, the effect of HbA1c on diabetic retinopathy (DR) in the Han and Korean populations in Jilin, China, remains inconclusive. AIM To determine the best cut-off of HbA1c for diagnosing DR among the Chinese. METHODS This cross-sectional study included 1933 participants from the Yanbian area of Jilin Province, China. Trained investigators employed a questionnaire-based survey, physical examination, laboratory tests, and fundus photography for the investigation. The best cut-off value for HbA1c was established via the receiver operating characteristic curve. The factors associated with HbA1c-associated risk factors were determined via linear regression. RESULTS The analysis included 887 eligible Chinese Han and Korean participants, 591 of whom were assigned randomly to the training set and 296 to the validation set. The prevalence of DR was 3.27% in the total population. HbA1c of 6.2% was the best cut-off value in the training set, while it was 5.9% in the validation set. In both Chinese Han and Korean populations, an HbA1c level of 6.2% was the best cut-off value. The optimal cut-off values of fasting blood glucose (FBG) ≥ 7 mmol/L and &lt; 7 mmol/L were 8.1% and 6.2% respectively in Han populations, while those in Korean populations were 6.9% and 5.3%, respectively. Age, body mass index, and FBG were determined as the risk factors impacting HbA1c levels. CONCLUSION HbA1c may serve as a useful diagnostic indicator for DR. An HbA1c level of 6.2% may be an appropriate cut-off value for DR detection in the Chinese population.

Endoplasmic reticulum stress promotes hepatocellular carcinoma by modulating immunity: a study based on artificial neural networks and single-cell sequencing

IntroductionHepatocellular carcinoma (HCC) is characterized by the complex pathogenesis, limited therapeutic methods, and poor prognosis. Endoplasmic reticulum stress (ERS) plays an important role in the development of HCC, therefore, we still need further study of molecular mechanism of HCC and ERS for early diagnosis and promising treatment targets.MethodThe GEO datasets (GSE25097, GSE62232, and GSE65372) were integrated to identify differentially expressed genes related to HCC (ERSRGs). Random Forest (RF) and Support Vector Machine (SVM) machine learning techniques were applied to screen ERSRGs associated with endoplasmic reticulum stress, and an artificial neural network (ANN) diagnostic prediction model was constructed. The ESTIMATE algorithm was utilized to analyze the correlation between ERSRGs and the immune microenvironment. The potential therapeutic agents for ERSRGs were explored using the Drug Signature Database (DSigDB). The immunological landscape of the ERSRGs central gene PPP1R16A was assessed through single-cell sequencing and cell communication, and its biological function was validated using cytological experiments.ResultsAn ANN related to the ERS model was constructed based on SRPX, THBS4, CTH, PPP1R16A, CLGN, and THBS1. The area under the curve (AUC) of the model in the training set was 0.979, and the AUC values in three validation sets were 0.958, 0.936, and 0.970, respectively, indicating high reliability and effectiveness. Spearman correlation analysis suggests that the expression levels of ERSRGs are significantly correlated with immune cell infiltration and immune-related pathways, indicating their potential as important targets for immunotherapy. Mometasone was predicted to be the most promising treatment drug based on its highest binding score. Among the six ERSRGs, PPP1R16A had the highest mutation rate, predominantly copy number mutations, which may be the core gene of the ERSRGs model. Single-cell analysis and cell communication indicated that PPP1R16A is predominantly distributed in liver malignant parenchymal cells and may reshape the tumor microenvironment by enhancing macrophage migration inhibitory factor (MIF)/CD74 + CXCR4 signaling pathways. Functional experiments revealed that after siRNA knockdown, the expression of PPP1R16A was downregulated, which inhibited the proliferation, migration, and invasion capabilities of HCCLM3 and Hep3B cells in vitro.ConclusionThe consensus of various machine learning algorithms and artificial intelligence neural networks has established a novel predictive model for the diagnosis of liver cancer associated with ERS. This study offers a new direction for the diagnosis and treatment of HCC.

Synergy between noisy quantum computers and scalable classical deep learning for quantum error mitigation

We investigate the potential of combining the computational power of noisy quantum computers and of classical scalable convolutional neural networks (CNNs). The goal is to accurately predict exact expectation values of parameterized quantum circuits representing the Trotter-decomposed dynamics of quantum Ising models. By incorporating (simulated) noisy expectation values alongside circuit structure information, our CNNs effectively capture the underlying relationships between circuit architecture and output behaviour, enabling, via transfer learning, also predictions for circuits with more qubits than those included in the training set. Notably, thanks to the quantum information, our CNNs succeed even when supervised learning based only on classical descriptors fails. Furthermore, they outperform a popular error mitigation scheme, namely, zero-noise extrapolation, demonstrating that the synergy between quantum and classical computational tools leads to higher accuracy compared with quantum-only or classical-only approaches. By tuning the noise strength, we explore the crossover from a computationally powerful classical CNN assisted by quantum noisy data, towards rather precise quantum computations, further error-mitigated via classical deep learning.

Deep Learning Assisted Classification of T1ρ-MR Based Intervertebral Disc Degeneration Phases.

According to the T1ρ value of nucleus pulposus, our previous study has found that intervertebral disc degeneration (IDD) can be divided into three phases based on T1ρ-MR, which is helpful for the selection of biomaterial treatment timing. However, the routine MR sequences for patients with IDD are T1- and T2-MR, T1ρ-MR is not commonly used due to long scanning time and extra expenses, which limits the application of T1ρ-MR based IDD phases. To build a deep learning model to achieve the classification of T1ρ-MR based IDD phases from routine T1-MR images. Retrospective. Sixty (M/F: 35/25) patients with low back pain or lower limb radiculopathy are randomly divided into training (N = 50) and test (N = 10) sets. 1.5 T MR scanner; T1-, T2-, and T1ρ-MR sequence (spin echo). The T1ρ values of the nucleus pulposus in intervertebral discs (IVDs) were measured. IVDs were divided into three phases based on the mean T1ρ value: pre-degeneration phase (mean T1ρ value >110 msec), rapid degeneration phase (mean T1ρ value: 80-110 msec), and late degeneration phase (mean T1ρ value <80 msec). After measurement, the T1ρ values, phases, and levels of IVDs were input into the model as labels. Intraclass correlation coefficient, area under the receiver operating characteristic curve (AUC), F1-score, accuracy, precision, and recall (P < 0.05 was considered significant). In the test dataset, the model achieved a mean average precision of 0.996 for detecting IVD levels. The diagnostic accuracy of the T1ρ-MR based IDD phases was 0.840 and the AUC was 0.871, the average AUC of 5-folds cross validation was 0.843. The proposed deep learning model achieved the classification of T1ρ-MR based IDD phases from routine T1-MR images, which may provide a method to facilitate the application of T1ρ-MR in IDD. 4 TECHNICAL EFFICACY: Stage 2.

Novel approaches in geomechanical parameter estimation using machine learning methods and conventional well logs

ABSTRACT Today, geomechanics plays a crucial role in the oil industry, particularly in enhancing production and ensuring well stability. To achieve optimal results, accurate estimation of geomechanical parameters is essential. One of the low-cost and accurate methods for estimating geomechanical parameters is the use of intelligent methods. In this research, geomechanical parameters are estimated using conventional data logs using intelligent methods. The aim of this study is to introduce a new machine learning algorithm to estimate geomechanical parameters using conventional data logs in one of the hydrocarbon field wells in southwest Iran. In this article, the shear wave velocity and uniaxial compressive strength (UCS) were estimated using machine learning algorithms. Subsequently, other geomechanical parameters were calculated based on these estimated parameters derived from machine learning algorithms. For shear wave velocity (Vs) prediction using MLP and CLM (CNN+LSTM+MLP) algorithms, First, effective features were selected using the Auto-encoder deep learning algorithm. The selected features for Vs input into the algorithms were Vp, RHOB, CALIPER, and NPHI, and then the Vs is estimated with MLP and CLM algorithm. To evaluate the results, the model was assessed using metrics such as MAE, MAPE, MSE, RMSE, NRMSE, and R2 on the train, test, and blind datasets. The CLM algorithm consistently demonstrated superior performance across all datasets, including training, testing, and blind data sets. The R2 values for blind data were R M L P 2 = 0.8727 , R C L M 2 = 0.9274 , respectively. These outputs are crucial for estimating subsequent studies. Next, Elastic Young’s moduli and Poisson’s ratio were calculated, and the dynamic brittleness index was computed using dynamic Young’s modulus and Poisson’s ratio. Subsequently, UCS values were predicted using machine learning algorithms. Since there were 12 laboratory core samples of UCS available, UCS was initially calculated using relevant empirical relations and data from some available well logs. This process aimed to extrapolate these core results to cover the entire target depth range from 3551.072 to 3799.789 m. Subsequently, a relationship between UCS derived from well logs and laboratory results was established for the depths corresponding to where the laboratory samples were recorded. Following that, an autoencoder deep network was utilized to select effective features for predicting UCS. The selected features for UCS input into the algorithms were Vp, RHOB, and CALIPER. Subsequently, UCS was estimated using MLP and CLM algorithms. To evaluate the results, the model performance was assessed using metrics such as MAE, MAPE, MSE, RMSE, NRMSE, and R2 on the train, test, and blind datasets. Furthermore, the results were checked and evaluated using a set of statistical measures calculated for the train, test, and blind datasets, that R M L P 2 = 0.9305 , R C L M 2 = 0.9953 were obtained for blind UCS data. The results demonstrate that CLM achieves high accuracy in estimating these parameters, with deep learning algorithms showing higher determination coefficients and lower errors compared to MLP. Furthermore, UCS and tensile strength were calculated, followed by the computation of static brittleness index. The relationship between dynamic and static brittleness index was also investigated. Overall, the findings indicate that machine learning algorithms are robust and accurate methods for estimating Vs, UCS, and other geomechanical parameters using conventional logs.

Research on Transformer Fault Diagnosis by WOA‐SVM Based on Feature Selection and Data Balancing

AbstractOil‐immersed transformers as one of the most important equipment in the power system, the fault prediction of it in advance can effectively reduce the subsequent harm. Aiming at the selection of input features and data sample imbalance in the transformer fault diagnosis model, this paper adopts the recursive feature elimination (RFE) method combined with SMOTETomek comprehensive sampling method to optimize the above problems. First, RFE is used to traverse all the features and filter the optimal combination of them as input features, then SMOTETomek is used to perform balancing operation on the samples of the train set, and finally, whale optimization algorithm (WOA) is used to find the best hyperparameters for support vector machine (SVM), and the results are compared with the diagnostic models operated without processing and after single processing operation, respectively. After several sets of experiments, it is proved that the optimized comprehensive fault diagnosis model performs better on the test set than both the untreated and the singly processed models, which proves the effectiveness of the methodology used in this paper. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Prediction of damage intensity to masonry residential buildings with convolutional neural network and support vector machine

During their life cycle, buildings are subjected to damage that reduces their performance and can pose a significant threat to structural safety. This paper presents the results of research into the creation of a model for predicting damage intensity of buildings located in mining terrains. The basis for the research was a database of technical and mining impact data for 185 masonry residential buildings. The intensity of damage to buildings was negligible and ranged from 0 to 6%. The Convolutional Neural Network (CNN) methodology was used to create the model. The Support Vector Machine (SVM) methodology, which is commonly used for analysis of this type of issue, was used for comparisons. The resulting models were evaluated by comparing parameters such as accuracy, precision, recall, and F1 score. The comparisons revealed only minor differences between the models. Despite the small range of damage intensity, the models created were able to achieve prediction results of around 80%. The SVM model had better results for training set accuracy, while the CNN model achieved higher values for F1 score and average precision for the test set. The results obtained justify the adoption of the CNN methodology as effective in the context of predicting the damage intensity of masonry residential buildings located in mining terrains.

CoMix: Confronting with Noisy Label Learning with Co-training Strategies on Textual Mislabeling

The existence of noisy labels is inevitable in real-world large-scale corpora. As deep neural networks are notably vulnerable to overfitting on noisy samples, this highlights the importance of the ability of language models to resist noise for efficient training. However, little attention has been paid to alleviating the influence of label noise in natural language processing. To address this problem, we present CoMix, a robust Noise-Against training strategy taking advantage of Co-training that deals with textual annotation errors in text classification tasks. In our proposed framework, the original training set is first split into labeled and unlabeled subsets according to a sample partition criteria and then applies label refurbishment on the unlabeled subsets. We implement textual interpolation in hidden space between samples on the updated subsets. Meanwhile, we employ peer diverged networks simultaneously leveraging co-training strategies to avoid the accumulation of confirm bias. Experimental results on three popular text classification benchmarks demonstrate the effectiveness of CoMix in bolstering the network’s resistance to label mislabeling under various noise types and ratios, which also outperforms the state-of-the-art methods.

A predictive model for ischemic colitis: Integrating clinical and laboratory parameters

AbstractObjectiveWe aimed to develop a predictive model for the clinical diagnosis of ischemic colitis (IC).MethodsClinical data were collected from patients with acute IC lesions who were diagnosed and admitted to Beijing Tsinghua Changgung Hospital from January 2016 to December 2022. These patients were included in the IC case group in this retrospective observational study. The control group comprised patients aged ≥40 years who were diagnosed with abdominal pain during the same period, excluding those with IC. All patients were divided into a training and test sets based on the time window. Least absolute shrinkage and selection operator regression was used to screen risk factors for the occurrence of IC. Logistic stepwise regression (maximum likelihood ratio method) was performed in multifactorial analysis, and a diagnostic prediction model for IC was established using R language. The area under the receiver operating characteristic (ROC) curve (AUC) was examined to assess differentiation using working ROC curves. We used bootstrap resampling (1000 times) for internal validation. Model calibration curves and decision curve analysis (DCA) were also applied.ResultsOur study indicates that constipation, hematochezia, neutrophil counts, and specific abdominal computed tomography (CT) (plain scan) findings, including intestinal wall edema and thickening, intestinal lumen stenosis, and dilation, are independent predictors of IC. The predictive model exhibited high discriminative ability with an AUC of 0.9788 in the training set, and the calibration and DCA curves demonstrated excellent model performance. After validation, the AUC remained robust at 0.9868, underscoring the model's reliability in predicting IC.ConclusionAccording to our model, constipation accompanied by hematochezia necessitates careful consideration of IC. Abdominal CT (plain scan) is an effective diagnostic tool for IC, and it is common for patients to exhibit elevated neutrophil counts. The predictive model, demonstrating high discriminative ability and accuracy, shows promise for practical application in clinical settings, aiding in the early diagnosis and management of IC.

Enhancing User Experience through Recommendation Systems: A Case Study in the E-commerce Sector

The significance of recommendation system techniques in improving user experience on e-commerce platforms should be considered as data-driven technologies progress. Conventional recommendation systems frequently need help dealing with issues such as data sparsity, cold start problems, and scalability, which significantly affect the ability of e-commerce platforms to offer accurate and relevant recommendations to consumers. This study evaluates the effectiveness of different recommendation system methodologies, including Averaging, Content-Based Filtering, Collaborative Filtering, Matrix Factorization, and Hybrid Approaches. Utilizing an extensive dataset from an e-commerce company, which encompasses consumer and product information such as ProductID, ProductName, Category, Price, CustomerID, and RatingReview, the dataset is divided into training and testing sets to assess the accuracy of the recommendation system models. Metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), R-squared, Precision, and Recall are used for this evaluation. Preliminary results indicate that applying advanced recommendation system techniques, especially after optimizing hyperparameters, dramatically improves the accuracy of recommendations and increases user satisfaction compared to more straightforward methods. These findings can revolutionize recommendation tactics on e-commerce platforms, leading to more tailored and gratifying user experiences. The outcomes of this research are expected to enhance the optimization of recommendation systems and broaden the current knowledge on this topic within e-commerce.

Robust unsupervised 5D seismic data reconstruction on both regular and irregular grid

Seismic data reconstruction in five dimensions (5D) has become a central focus in seismic data processing, addressing challenges posed by irregular sampling due to physical and budgetary constraints. Most traditional high-dimensional reconstruction methods commonly utilize the fast Fourier transform (FFT), requiring regular grids and preliminary 4D binning before 5D interpolation. Discrete Fourier transform and non-equidistant FFT can honour original irregular coordinates. However, when using exact locations, these methods become computationally expensive. This study introduces an unsupervised deep-learning methodology to learn a continuous function across sampling points in seismic data, facilitating reconstruction on both regular and irregular grids. The network comprises a multilayer perceptron (MLP) with linear layers and element-wise periodic activation functions. It excels at mapping input coordinates to corresponding seismic data amplitudes without relying on external training sets. The network’s intrinsic low-frequency bias is crucial in prioritizing acquiring self-similar features over high-frequency, incoherent ones during training. This characteristic mitigates incoherent noise in seismic data, including random and erratic components. To assess the robustness of the unsupervised reconstruction technique, we conduct comprehensive evaluations using synthetic data examples sampled both regularly and irregularly, as well as field-data examples with and without binning. The findings demonstrate the efficacy of the proposed deep-learning framework in achieving resilient and accurate seismic data reconstruction across diverse sampling scenarios.

Model based on the automated AI-driven CT quantification is effective for the diagnosis of refractory Mycoplasma pneumoniae pneumonia

The prediction of refractory Mycoplasma pneumoniae pneumonia (RMPP) remains a clinically significant challenge. This study aimed to develop an early predictive model utilizing artificial intelligence (AI)-derived quantitative assessment of lung lesion extent on initial computed tomography (CT) scans and clinical indicators for RMPP in pediatric inpatients. A retrospective cohort study was conducted on patients with M. pneumoniae pneumonia (MP) admitted to the Children’s Hospital of Nanjing Medical University, China from January 2019 to December 2020. An early prediction model was developed by stratifying the patients with Mycoplasma pneumoniae pneumonia (MPP) into two cohorts according to the presence or absence of refractory pneumonia. A retrospective cohort of 126 children diagnosed with Mycoplasma pneumoniae pneumonia (MPP) was utilized as a training set, with 85 cases classified as RMPP. Subsequently, a prospective cohort comprising 54 MPP cases, including 37 instances of RMPP, was assembled as a validation set to assess the performance of the predictive model for RMPP from January to December 2021. We defined a constant Φ which can combine the volume and CT value of pulmonary lesions and be further used to calculate the logarithm of Φ to the base of 2 (Log2Φ). A clinical-imaging prediction model was then constructed utilizing Log2Φ and clinical characteristics. Performance was evaluated by the area under the receiver operating characteristic curve (AUC). The clinical model demonstrated AUC values of 0.810 and 0.782, while the imaging model showed AUC values of 0.764 and 0.769 in the training and test sets, respectively. The clinical-imaging model, incorporating Log2Φ, temperature(T), aspartate aminotransferase (AST), preadmission fever duration (PFD), and preadmission macrolides therapy duration (PMTD), achieved the highest AUC values of 0.897 and 0.895 in the training and test sets, respectively. A prognostic model developed through automated quantification of lung disease on CT scans, in conjunction with clinical data in MPP may be utilized for the early identification of RMPP.

Development and validation of nomogram for predicting the risk of transferring to the ICU for children with influenza.

Development of a nomogram model for predicting the magnitude of risk of transferring hospitalized children with influenza to the ICU. In a single-center retrospective study, 318 children with influenza who were hospitalized in our hospital from January 2018 to August 2023 were collected as study subjects. Children with influenza were randomly assigned to the training set and validation set in a ratio of 4:1. In the training set, risk factors were identified using univariate and multivariate logistic regression analyses, and a nomogram model was created on this basis. The validation set was used to evaluate the predictive power of the model. Multifactorial logistic regression analysis revealed six independent risk factors for transfer to the ICU in hospitalized children with influenza, including elevated peripheral white blood cell counts, elevated large platelet ratios, reduced mean platelet width, reduced complement C3, elevated serum globulin levels, and reduced total immunoglobulin M levels. Using these six metrics as predictors to construct a nomogram graphical model, the C-index was 0.970 (95% Cl: 0.953-0.988). The areas under the curve for the training and validation sets were 0.966 (95%Cl 0.947-0.985) and 0.919 (95%Cl 0.851-0.986), respectively. A nomogram for predicting the risk of transferring to the ICU for children with influenza was developed and validated, which demonstrates good calibration and clinical benefits.