检索结果-内蒙古大学图书馆

An early prediction model for gestational diabetes mellitus created using machine learning algorithms

INTERNATIONAL JOURNAL OF GYNECOLOGY & OBSTETRICS 2025年第0期 2025 Mar 4页

作者： Yang, Zhifen Shi, Xiaoyue Wang, Shengpu Du, Lijia Zhang, Xiaoying Zhang, Kun Zhang, Yongqiang Ma, Jinlong Zheng, Rui Hebei Med Univ Hosp 4 Obstetr Dept 169 Tianshan St Shijiazhuang 050000 Peoples R China Hebei Univ Sci & Technol Sch Informat Sci & Engn Shijiazhuang Hebei Peoples R China

ObjectiveTo investigate high-risk factors for gestational diabetes mellitus (GDM) in early pregnancy through an analysis of demographic and clinical data, and to develops a machine-learning-based prediction model to enhance early diagnosis and intervention. MethodsA retrospective study was performed involving 942 pregnant women. A stacking ensemble (machine learning [ML]) was applied to demographic and clinical variables, creating a predictive model for GDM. Model performance was evaluated through receiver-operating characteristics (ROC) analysis, and the area under the curve (AUC) was calculated. Risk stratification was performed using quartile-based probability thresholds, and predictive accuracy was validated using an independent dataset. ResultsSignificant predictors for GDM included age, pre-pregnancy body mass index (BMI;calculated as weight in kilograms divided by the square of height in meters), history of GDM, family history of diabetes, history of fetal macrosomia, education level, history of hypertension, and gravidity. These factors, which can be collected non-invasively at the first prenatal visit, formed the basis of a robust predictive model (AUC = 0.89). The model demonstrated a strong ability to exclude GDM, at a threshold of 28.53%. ConclusionsThe machine-learning-based prediction model effectively identifies populations at high risk for GDM before invasive testing and oral glucose tolerance test, facilitating early clinical intervention and resource optimization.

关键词： early prediction model gestational diabetes mellitus hierarchical structural analysis machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Groundwater Quality Prediction Using Proximal Hyperspectral Sensing, GIS, and machine learning algorithms

引用

WATER AIR AND SOIL POLLUTION 2025年第6期236卷 1-25页

作者： Raheja, Hemant Goel, Arun Pal, Mahesh Natl Inst Technol Kurukshetra Dept Civil Engn Kurukshetra 136119 Haryana India

The primary objective of the present study is to assess the suitability of groundwater for drinking purposes using the Water Quality Index (WQI), Geographic Information System (GIS), and proximal sensing techniques. For this purpose, 272 groundwater samples collected before and after the monsoon period were analyzed for various hydrochemical parameter concentrations. To explore the relationship between water spectral reflectance and WQI, a spectroradiometer was used to measure the reflectance of each sample under laboratory conditions. Four machine learning procedures i.e., Support Vector Regression (SVR), M5P, Random Forest (RF), and Gaussian Process Regression (GPR) were used to predict WQI using resampled spectral reflectance. The WQI analysis revealed that approximately 30% of the groundwater samples fell within the poor to extremely poor-quality category in both periods, while 55.88% (Pre-monsoon) and 55.14% (Post-monsoon) of samples were classified under moderate quality, indicating marginal suitability for drinking purposes. The spectral curves of WQI indicated a lower reflectance for water samples with lower WQI values, whereas higher reflectance values were associated with higher WQI values. Performance evaluation of machine learning models demonstrated that SVR outperformed M5P, RF, and GPR, achieving the highest Correlation Coefficient (CC = 0.9964) and the lowest Root Mean Square Error (RMSE = 7.0313 mg/L) and Mean Absolute Error (MAE = 3.5056 mg/L) in the training phase, while maintaining similar performance in the testing phase (CC = 0.9964, RMSE = 7.6748 mg/L, MAE = 4.0297 mg/L). These findings highlight the potential of integrating spectral reflectance with machine learning models for accurate groundwater quality assessment and spatial mapping.

关键词： Water Quality Index (WQI) Spatial Distribution Spectral Reflectance machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Predicting host-pathogen interactions with machine learning algorithms: A scoping review

引用

INFECTION GENETICS AND EVOLUTION 2025年 130卷 105751页

作者： Sahragard, Rasool Arabfard, Masoud Najafi, Ali Baqiyatallah Univ Med Sci Biomed Technol Inst Mol Biol Res Ctr Tehran Iran Baqiyatallah Univ Med Sci Syst Biol & Poisonings Inst Chem Injuries Res Ctr Tehran Iran

Background: Diseases caused by pathogenic microorganisms pose a persistent global health challenge. Pathogens exploit host mechanisms through intricate molecular interactions. Understanding these host-pathogen interactions (HPIs), particularly protein-protein interactions (PPIs), is crucial for developing therapeutic strategies. While experimental approaches are essential, they are often labor-intensive and costly. Researchers have been able to predict HPIs more efficiently due to recent advances in artificial intelligence and machine learning. However, existing reviews lack a systematic evaluation of different machine learning methodologies and their effectiveness. Methods: This scoping review critically examines recent studies on machine learning-based Host-Pathogen Interaction (HPI) prediction, categorizing them by host and pathogen types, machine learning algorithms, and key evaluation metrics. The methodology is based on the study beginning with a preliminary search in reputable using key phrases related to host-pathogen interactions from 2019 to 2024. This process yielded 46 relevant articles, from which 30 were selected for review after evaluating titles and abstracts. Results: Our findings indicate that tree-based algorithms, particularly Random Forest and Gradient Boosting, are the most prevalent in Host-Pathogen Interaction (HPI) prediction. The filter articles were categorized by host and pathogen type and further subdivided into four subcategories based on the prediction type and machine learning algorithms: classic, tree-based, vector-based, and neural network algorithms. Convolutional and recurrent neural networks are among the deep learning models that demonstrate promising accuracy, but they require a lot of labeled data for effective training. Additionally, the analysis uncovers significant gaps in dataset standardization and model interpretability, which pose challenges to the broader applicability of these predictive models. Conclusion: In this re

关键词： Host-pathogen interactions Protein-protein interaction Prediction algorithms machine learning algorithms Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Applying machine learning algorithms to explore the impact of combined noise and dust on hearing loss in occupationally exposed populations

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-10页

作者： Li, Yong Sun, Xin Qu, Yongtao Yang, Shuling Zhai, Yueyi Qu, Yan Hebei Med Univ Dept Otolaryngol Shijiazhuang Peoples R China Hebei Gen Hosp Dept Otolaryngol Shijiazhuang Peoples R China Hebei North Univ Zhangjiakou Peoples R China Hebei Med Univ Anim Lab Hosp 3 Shijiazhuang Peoples R China Hebei Med Univ Dept Otolaryngol Hosp 3 Shijiazhuang Peoples R China

This study aimed to explore the combined impacts of occupational noise and dust on hearing and extra-auditory functions and identify associated risk factors via machine learning techniques. Data from 14,145 workers (627 with occupational noise-induced hearing loss (ONIHL)) at Hebei Medical Examination Center (2017-2023) were analyzed. Workers with combined exposure and without specific contraindications or other hearing impairment causes were included. Demographic and clinical data were gathered. Chi-square and Mann-Whitney U tests examined variables, and multivariate logistic regression determined ONIHL risk factors. machine learning algorithms like Logistic Regression and Random Forest were developed, optimized, and evaluated. Results showed significant differences in gender, exposure, blood pressure, smoking, etc. between ONIHL and non-ONIHL groups. Male gender, combined exposure, diastolic blood pressure elevation, smoking, fasting blood glucose elevation, and age were positive predictors, while systolic blood pressure elevation was negative. The logistic model had the highest predictive ability (ROC = 0.714). Subgroup analysis revealed a significant positive correlation in specific subgroups. In summary, combined exposure increased ONIHL risk and affected health. machine learning effectively predicted ONIHL, but the study had limitations and needed further research.

关键词： Occupational exposure Noise and dust Hearing loss machine learning algorithms Risk factors

来源：评论

学校读者我要写书评

暂无评论

Exploring machine learning algorithms to predict not using modern family planning methods among reproductive age women in East Africa

引用

BMC HEALTH SERVICES RESEARCH 2024年第1期24卷 1-12页

作者： Yehuala, Tirualem Zeleke Univ Gondar Inst Publ Hlth Coll Med & Hlth Sci Dept Hlth Informat Gondar Ethiopia

BackgroundThe use of the modern family planning method provides chances for women to reach optimal child spacing, increase quality of life, increase economic status, achieve the desired family size, and prevent unsafe abortions and maternal and perinatal deaths. However, use modern family planning is low among reproductive age women in East Africa. Therefore, this study aimed at predicting not using modern family planning and identifying its associated factors among reproductive age women in east Africa using machine learning *** data set was obtained from a demographic health survey in East Africa. This study used data on weighted sample of 92,564 women who were in their reproductive age. Python software was utilized for data processing, and machine learning models such as Random Forest (RF), Decision Tree (DT), XGB (Extreme Gradient Boosting), SVM (Support Victor machine), and K-Nearest Neighbor Decision Tree (DT) were implemented. In this work, we evaluated the predictive models' performance using performance assessment criteria such as accuracy, precision, recall, and the AUC *** this study, 92,564 reproductive women's was used in the final analysis. Among the proposed machine learning models, XGB performed best overall in the proposed classifier, with an accuracy of 98.7%, precision of 99.8%, recall of 98%, 99.9% AUC score, had high specificity 98%, sensitivity 99.8%, and low error rate discovery was 0.013%. The most significant determinants of not using modern family planning in East Africa: lack of education, age 25-29, living in a rural area, being single, not knowing how to use a contraceptive, and smoking *** Gradient Boosting proved effective in predicting not using modern family planning, offering valuable insights for interventions and policy decisions in East Africa. machine learning could help achieve early prediction and intervention on reproductive women's not using modern family planning. This leads

关键词： Family planning Prediction machine learning algorithms East Africa

来源：评论

学校读者我要写书评

暂无评论

Exploration and verification a 13-gene diagnostic framework for ulcerative colitis across multiple platforms via machine learning algorithms

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-14页

作者： Wang, Jing Li, Lin Chen, Pingbo He, Chiyi Niu, Xiaoping Wan Nan Med Coll Affiliated Hosp 1 Dept Gastroenterol Wuhu 241001 Peoples R China Wan Nan Med Coll Affiliated Hosp 1 Dept Joint Orthoped Wuhu 241001 Peoples R China

Ulcerative colitis (UC) is a chronic inflammatory bowel disease with intricate pathogenesis and varied presentation. Accurate diagnostic tools are imperative to detect and manage UC. This study sought to construct a robust diagnostic model using gene expression profiles and to identify key genes that differentiate UC patients from healthy controls. Gene expression profiles from eight cohorts, encompassing a total of 335 UC patients and 129 healthy controls, were analyzed. A total of 7530 gene sets were computed using the GSEA method. Subsequent batch correction, PCA plots, and intersection analysis identified crucial pathways and genes. machine learning, incorporating 101 algorithm combinations, was employed to develop diagnostic models. Verification was done using four external cohorts, adding depth to the sample repertoire. Evaluation of immune cell infiltration was undertaken through single-sample GSEA. All statistical analyses were conducted using R (Version: 4.2.2), with significance set at a P value below 0.05. Employing the GSEA method, 7530 gene sets were computed. From this, 19 intersecting pathways were discerned to be consistently upregulated across all cohorts, which pertained to cell adhesion, development, metabolism, immune response, and protein regulation. This corresponded to 83 unique genes. machine learning insights culminated in the LASSO regression model, which outperformed others with an average AUC of 0.942. This model's efficacy was further ratified across four external cohorts, with AUC values ranging from 0.694 to 0.873 and significant Kappa statistics indicating its predictive accuracy. The LASSO logistic regression model highlighted 13 genes, with LCN2, ASS1, and IRAK3 emerging as pivotal. Notably, LCN2 showcased significantly heightened expression in active UC patients compared to both non-active patients and healthy controls (P < 0.05). Investigations into the correlation between these genes and immune cell infiltration in UC highlighted

关键词： Ulcerative colitis Diagnostic model machine learning algorithms Gene set enrichment analysis Immunocytes infiltration

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence-driven education evaluation and scoring: Comparative exploration of machine learning algorithms

引用

JOURNAL OF INTELLIGENT SYSTEMS 2024年第1期33卷

作者： Ma, Xiangfen Puyang Vocat & Tech Coll Fac Math & Informat Engn Puyang 457000 Peoples R China

With the widespread popularity of intelligent education, artificial intelligence plays an important role in the field of education. Currently, there are issues such as low accuracy and low adaptability. By comparing algorithms such as logistic regression, decision tree, random forest (RF), support vector machine, and long short-term memory (LSTM) recurrent neural network (RNN), this article adopted a multi-classification fusion strategy and fully considered the adaptability of the algorithm to evaluate and grade students in two scenarios with different grades and teaching quality. By encoding and normalizing student grades, six evaluation parameters were selected for the evaluation criteria of teaching quality through principal component analysis feature selection. Multi-classifier models were used to fuse the five models in pairs, improving the accuracy of the experimental evaluation. Finally, the experimental data of the six fused multi-classification models in the scenarios of student performance estimation and teaching quality estimation were compared, and the experimental effects of education evaluation and grading under different models were analyzed. The experimental results showed that the LSTM RNN-RF model had the strongest adaptability in the scenario of student performance estimation, with an estimation accuracy of 98.5%, which was 12.9% higher than a single RF model. This experiment was closely related to educational scenarios and fully considered the adaptability of different machine learning algorithms to different scenarios, improving the prediction and classification accuracy of the model.

关键词： artificial intelligence machine learning algorithms educational assessment and scoring multi-classifier models adaptability and accuracy

来源：评论

学校读者我要写书评

暂无评论

Predicting whole-life carbon emissions for buildings using different machine learning algorithms: A case study on typical residential properties in Cornwall, UK

引用

APPLIED ENERGY 2024年 357卷

作者： Zheng, Lin Mueller, Markus Luo, Chunbo Yan, Xiaoyu Univ Exeter Fac Environm Engn Dept Renewable Energy Grp Penryn TR10 9FE England Univ Exeter Environm & Sustainabil Inst Fac Environm Sci & Econ Penryn Campus Penryn TR10 9FE England Univ Exeter Fac Environm Sci & Econ Dept Earth & Environm Sci Penryn Campus Penryn TR10 9FE England Univ Exeter Inst Data Sci & Artificial Intelligence Exeter EX4 4RN England Univ Exeter Fac Environm Sci & Econ Dept Comp Sci Exeter EX4 4RN England Univ Exeter Penryn Campus Penryn TR10 9FE England

Whole-life carbon emissions (WLCE) studies are critical in assessing the environmental impact of buildings and promoting sustainable design practices. However, existing methods for estimating WLCE are time-consuming and data-intensive, limiting their usefulness in the early building design stages. In response to this, this research introduces a novel approach by harnessing various machine learning algorithms to predict WLCE and WLCE intensity (normalised by floor area) for buildings. To evaluate the suitability of machine learning algorithms, we conducted an experiment involving ten algorithms to build the prediction models. These models were trained using data from 150 typical residential properties in Cornwall, UK, along with 28 features obtained from a comprehensive survey, including floor area, heating type, and occupant characteristics. The ten algorithms include Multiple Linear Regression, and non-linear algorithms such as Decision Tree, Random Forest. Performance evaluation metrics, such as coefficient of determination (R2), mean absolute error (MAE), means squared error (MSE), root-mean-square error (RMSE), and elapsed time, were employed. Our research contributes to the field by showcasing the effectiveness of machine learning models in predicting building WLCE. We reveal that all the tested machine learning algorithms have the capability to predict WLCE and WLCE intensity, non-linear models outperform linear ones, and the Random Forest (RF) model demonstrates superior performance in terms of accuracy, stability, and efficiency. This research encourages the integration of life cycle studies into the early design stage, even within tight building design schedules, offering practical guidance to architects and designers. Furthermore, these results also benefit a wide range of stakeholders, not only the architects but also the engineers, policymakers, and life cycle assessment (LCA) researchers, contributing to the advancement of data-driven sustainability app

关键词： Whole life carbon emissions Life cycle thinking machine learning algorithms Sustainable building Carbon reduction Data -driven approaches

来源：评论

学校读者我要写书评

暂无评论

Screening and Analysis of Core Genes for Osteoporosis Based on Bioinformatics Analysis and machine learning algorithms

引用

INDIAN JOURNAL OF ORTHOPAEDICS 2024年第7期58卷 944-954页

作者： Lu, Yongxia Wang, Wei Yang, Baiyuan Cao, Gui Du, Yue Liu, Jingyu Chengdu Seventh Peoples Hosp Dept Endocrinol & Metab Chengdu Peoples R China Chengdu Seventh Peoples Hosp Dept Neurol Chengdu Peoples R China

ObjectiveThis study aimed to identify osteoporosis-related core genes using bioinformatics analysis and machine learning *** expression profiles of osteoporosis patients were obtained from the Gene Expression Profiles (GEO) database, with GEO35958 and GEO84500 used as training sets, and GEO35957 and GSE56116 as validation sets. Differential gene expression analysis was performed using the R software "limma" package. A weighted gene co-expression network analysis (WGCNA) was conducted to identify key modules and modular genes of osteoporosis. Kyoto Gene and Genome Encyclopedia (KEGG), Gene Ontology (GO), and gene set enrichment analysis (GSEA) were performed on the differentially expressed genes. LASSO, SVM-RFE, and RF machine learning algorithms were used to screen for core genes, which were subsequently validated in the validation set. Predicted microRNAs (miRNAs) from the core genes were also analyzed, and differential miRNAs were validated using quantitative real-time PCR (qPCR) *** total of 1280 differentially expressed genes were identified. A disease key module and 215 module key genes were identified by WGCNA. Three core genes (ADAMTS5, COL10A1, KIAA0040) were screened by machine learning algorithms, and COL10A1 had high diagnostic value for osteoporosis. Four core miRNAs (has-miR-148a-3p, has-miR-195-3p, has-miR-148b-3p, has-miR-4531) were found by intersecting predicted miRNAs with differential miRNAs from the dataset (GSE64433, GSE74209). The qPCR experiments validated that the expression of has-miR-195-3p, has-miR-148b-3p, and has-miR-4531 was significantly increased in osteoporosis *** study demonstrated the utility of bioinformatics analysis and machine learning algorithms in identifying core genes associated with osteoporosis.

关键词： Bioinformatics machine learning algorithms Osteoporosis Core genes

来源：评论

学校读者我要写书评

暂无评论

Automatically Finding the Biggest Fold Value for More Accurate Classification and Diagnosis in machine learning algorithms

引用

IRANIAN JOURNAL OF SCIENCE AND TECHNOLOGY-TRANSACTIONS OF ELECTRICAL ENGINEERING 2024年第2期48卷 661-686页

作者： Avuclu, Emre Aksaray Univ Fac Engn Dept Software Engn Aksaray Turkiye

Correct diagnosis in medicine is of great importance as it is one of the most important issues in medicine. Today, researchers have embarked on many new searches to make an accurate medical diagnosis. In order for any disease to be cured, it is necessary to define it precisely early and accurately. In this study, a new method was proposed to make a more accurate medical diagnosis. This method is based on automatically selecting the fold with the best accuracy rate after k-fold crossvalidation is performed in any database. In this way, scientific studies that lead to more accurate results will be carried out by using the fold with the highest accuracy in both classification and medical diagnosis procedures. This method has been applied on two different databases, Ecoli and Wisconsin Breast Cancer Diagnostic (WBCD) databases, which are used in scientific studies by many researchers in the literature. The statistical measurements of each fold values of both databases used have been examined in detail. Diagnostics for these databases were carried out using 7 different machine learning algorithms (MLA), (k nearest neighbor (k-NN), Decision Tree (DT), Random Forest (RF), Multinominal Logistic Regression (MLR), Naive Bayes (NB), Support Vector machine (SVM), Minumum (Mean) Distance Classifier (MMDC)). In the test procedures for Ecoli dataset, the following accuracy values were obtained for k-NN, DT, RF, MLR, NB, SVM, MMDC, respectively;0.8485, 0.8358, 0.9848, 0.8182, 0.6667, 0.8636, 0.7424. For the WBCD database, the following accuracy values were obtained for k-NN, DT, RF, MLR, NB, SVM, MMDC, respectively;0.9856, 0.9568, 0.9784, 0.9856, 0.9856, 0.9856, 0.9784. Other results were given in detail in the experimental studies section. It is of great importance to choose the most accurate MLAs to be used in medical diagnosis for human life. Thus, in the studies to be done with MLAs in medicine or any field in the literature, how the best score that can be obtained from MLAs wi

关键词： Biomedical diagnosis Biggest k-fold Cancer diagnosis Crossvalidation machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：