Auxiliary Diagnosis of Breast Cancer Based on Machine Learning and Hybrid Strategy by Hua Chen, Kehui Mei, Yuan Zhou, Nan Wang, Guangxing Cai

“…Then, the features of the dataset are initially screened using the mutual information method, and further secondary feature selection is performed using the recursive feature elimination method based on the XGBoost algorithm. …”
Get full text

Prediction of Insulin Resistance in Nondiabetic Population Using LightGBM and Cohort Validation of Its Clinical Value: Cross-Sectional and Retrospective Cohort Study by Ting Peng, Rujia Miao, Hao Xiong, Yanhui Lin, Duzhen Fan, Jiayi Ren, Jiangang Wang, Yuan Li, Jianwen Chen

“…In the test group, all AUC were also greater than 0.80. The LightGBM model showed the best IR prediction performance with an accuracy of 0.7542, sensitivity of 0.6639, specificity of 0.7642, F1 ConclusionBy leveraging low-cost laboratory indicators and questionnaire data, the LightGBM model effectively predicts IR status in nondiabetic individuals, aiding in large-scale IR screening and diabetes prevention, and it may potentially become an efficient and practical tool for insulin sensitivity assessment in these settings.…”
Get full text

Hydraulic Pump Fault Diagnosis Method Based on EWT Decomposition Denoising and Deep Learning on Cloud Platform by Wanlu Jiang, Zhenbao Li, Sheng Zhang, Teng Wang, Shuqing Zhang

“…Compared with ensemble empirical mode decomposition (EEMD) and complementary ensemble empirical mode decomposition (CEEMD), the results show that the axial piston pump fault diagnosis algorithm based on EWT and 1D-CNN has higher fault identification accuracy.…”
Get full text

Tuberculosis Lesion Segmentation Improvement in X-Ray Images Using Contextual Background Label by Sahasat Khumang, Supaporn Kansomkeat, Wiwatana Tanomkiat, Sathit Intajag

“…To detect PTB at an early stage by screening chest X-Ray (CXR) images for tuberculosis (TB) lesions, we propose a semantic segmentation scheme that uses a deep learning algorithm. …”
Get full text

Naive Bayes Analysis for Nutritional Fulfillment Prediction in Children by Satrio Agung Wicaksono, Satrio Hadi Wijoyo, Fatmawati Fatmawati, Tri Afirianto, Diva Kurnianingtyas, Mochammad Chandra Saputra

“…The data used were sourced from 174 infant and toddler examinations at the Puskesmas Lawang, involving eight key attributes: gender, age, weight, height, head circumference, pre-screening, vision tests, and nutritional status. Key performance metrics were evaluated to validate the model's predictive capabilities, including accuracy, precision, recall, and F1-score. …”
Get full text

Collaborative Optimization Planning Method for Distribution Network Considering “Hydropower, Photovoltaic, Storage, and Charging” by Jinlin Liao, Jia Lin, Guilian Wu, Sudan Lai

“…The power output curve of a typical day is obtained using the K-means clustering algorithm and the hierarchical analysis method. The non-dominated sorting genetic algorithms II (NSGA-II) with elite strategy is used to solve the multi-objective model to obtain the Pareto solution set. …”
Get full text

Immunoglobulin G N-Glycosylation and Inflammatory Factors: Analysis of Biomarkers for the Diagnosis of Moyamoya Disease by Zan X, Liu C, Wang X, Sun S, Li Z, Zhang W, Sun T, Hao J, Zhang L

“…This research aimed to evaluate the diagnostic efficacy of IgG N-glycosylation for MMD.Methods: Ultra-high-performance liquid chromatography (UPLC) was employed to examine the properties of IgG N-glycans in blood samples from 116 patients with MMD and 126 controls, resulting in the quantitative determination of 24 initial glycan peaks (GP). Through the Lasso algorithm and multivariate logistic regression analysis, we constructed a diagnostic model based on initial glycans and related inflammatory factors to distinguish MMD patients from healthy individuals.Results: After adjusting for potential confounding variables, including age, fasting blood glucose (FBG), total cholesterol (TC), high-density lipoprotein (HDL), low-density lipoprotein (LDL), neutrophil count (NEUT), and lymphocyte count (LYM), our study demonstrated significant differences in the characteristics of 6 initial glycans and 16 derived glycans between the MMD cohort and the healthy control group. …”
Get full text

Tool wear prediction based on XGBoost feature selection combined with PSO-BP network by Zhangwen Lin, Yankun Fan, Jinling Tan, Zhen Li, Peng Yang, Hua Wang, Weiwei Duan

“…Experimental results show that PSO outperforms other algorithms in training the tool wear prediction model, with XGBoost feature selection reducing model construction time by 57.4% and increasing accuracy by 63.57%, demonstrating superior feature selection capabilities over Decision Tree, Random Fores, Adaboost and Extra Trees. …”
Get full text

Optimizing deep learning for accurate blood cell classification: A study on stain normalization and fine-tuning techniques by Mohammed Tareq Mutar, Jaffar Nouri Alalsaidissa, Mustafa Majid Hameed, Ali Almothaffar

“…BACKGROUND: Deep learning’s role in blood film screening is expanding, with recent advancements including algorithms for the automated detection of sickle cell anemia, malaria, and leukemia using smartphone images. …”
Get full text

Preoperative prediction of pituitary neuroendocrine tumor invasion using multiparametric MRI radiomics by Qiuyuan Yang, Tengfei Ke, Jialei Wu, Yubo Wang, Jiageng Li, Yimin He, Jianxian Yang, Nan Xu, Bin Yang

“…Radiomics features were extracted from the manually delineated regions of interest in T1WI, T2WI and CE-T1, and the best radiomics features were screened by LASSO algorithm. Single radiomics model (T1WI, T2WI, CE-T1) and combined radiomics model (T1WI+T2WI+CE-T1) were constructed respectively. …”
Get full text

Noninvasive prediction of meningioma brain invasion via multiparametric MRI⁃based brain⁃tumor interface radiomics by CHENG Xing, WANG Zhi⁃chao, LI Hua⁃ning, WANG Xie⁃feng, YOU Yong⁃ping

“…Through five⁃fold cross⁃validation in the training set and evaluation in the testing set, comparative analysis of the predictive performance of 18 model⁃thickness combinations (6 ML algorithms × 3 BTI thicknesses) showed that the XGBoost model constructed with a 1.00 cm BTI thickness demonstrated exceptional performance. …”
Get full text

Numerical analysis method of stress wave transmission attenuation of coal and rock structural plane by Wenlong SHEN, Renren ZHU, Ziqiang CHEN, Guocang SHI

“…The simulation and machine learning of stress wave transmission in the experimental process of Split Hopkinson Pressure Bar (SHPB) were carried out by combining the Barton-Bandis nodal ontology model, UDEC discrete element simulation and Gray Wolf Algorithm optimized BP neural network technology. …”
Get full text

Efficient secure federated learning aggregation framework based on homomorphic encryption by Shengxing YU, Zhong CHEN

“…In order to solve the problems of data security and communication overhead in federated learning, an efficient and secure federated aggregation framework based on homomorphic encryption was proposed.In the process of federated learning, the privacy and security issues of user data need to be solved urgently.However, the computational cost and communication overhead caused by the encryption scheme would affect the training efficiency.Firstly, in the case of protecting data security and ensuring training efficiency, the Top-K gradient selection method was used to screen model gradients, reducing the number of gradients that need to be uploaded.A candidate quantization protocol suitable for multi-edge terminals and a secure candidate index merging algorithm were proposed to further reduce communication overhead and accelerate homomorphic encryption calculations.Secondly, since model parameters of each layer of neural networks had characteristics of the Gaussian distribution, the selected model gradients were clipped and quantized, and the gradient unsigned quantization protocol was adopted to speed up the homomorphic encryption calculation.Finally, the experimental results show that in the federated learning scenario, the proposed framework can protect data privacy, and has high accuracy and efficient performance.…”
Get full text

To accurately predict lymph node metastasis in patients with mass-forming intrahepatic cholangiocarcinoma by using CT radiomics features of tumor habitat subregions by Pengyu Chen, Zhenwei Yang, Peigang Ning, Hao Yuan, Zuochao Qi, Qingshan Li, Bo Meng, Xianzhou Zhang, Haibo Yu

“…Using information from the arterial and venous phases of multisequence CT images, tumor habitat subregions were delineated through the K-means clustering algorithm. Radiomic features were extracted and screened, and prediction models based on different subregions were constructed and compared with traditional intratumoral models. …”
Get full text

Chinese AI tool ERNIE Bot Textual Exploration of False Information by Fu Yue

“…In order to improve the accuracy of detection, this paper proposes countermeasures to improve the AI detection algorithm, enhance data training and model optimisation, and human-machine collaboration. …”
Get full text

A deep-learning approach to predict reproductive toxicity of chemicals using communicative message passing neural network by Owen He, Daoxing Chen, Yimei Li

“…In independent test sets, ReproTox-CMPNN achieved a mean AUC of 0.946, ACC of 0.857 and F1 score of 0.846, surpassing traditional algorithms to establish itself as a new state-of-the-art model in this field. …”
Get full text

Computed tomography-based radiomics predicts prognostic and treatment-related levels of immune infiltration in the immune microenvironment of clear cell renal cell carcinoma by Shiyan Song, Wenfei Ge, Xiaochen Qi, Xiangyu Che, Qifei Wang, Guangzhen Wu

“…Radiomics features were screened using LASSO analysis. Eight ML algorithms were selected for diagnostic analysis of the test set. …”
Get full text

Machine learning with the body roundness index and associated indicators: a new approach to predicting metabolic syndrome by Yaxuan He, Zekai Chen, Zhaohui Tang, Yuexiang Qin, Fang Wang

“…Traditional invasive diagnostic methods are costly, inconvenient, and unsuitable for large-scale screening. Developing a non-invasive, accurate prediction model is clinically significant for early MetS detection and prevention. …”
Get full text

Research on Feature Extraction of Performance Degradation for Flexible Material R2R Processing Roller Based on PCA by Yaohua Deng, Huiqiao Zhou, Kexing Yao, Zhiqi Huang, Chengwang Guo

“…The Jacobi iteration method was introduced to derive the algorithm for solving eigenvalue and eigenvector of the covariance matrix. …”
Get full text

Exploring timely and safe discharge from ICU: a comparative study of machine learning predictions and clinical practices by Chao Ping Wu, Rachel Benish Shirley, Alex Milinovich, Kaiyin Liu, Eduardo Mireles-Cabodevila, Hassan Khouli, Abhijit Duggal, Anirban Bhattacharyya

“…Methods This retrospective study uses data from patients in the medical ICU from 2015-to-2019 to develop ML models. The models were based on dynamic ICU-readily available features such as hourly vital signs, laboratory results, and interventions and were developed using various ML algorithms. …”
Get full text