检索结果-内蒙古大学图书馆

Developing supervised machine learning algorithms to evaluate the therapeutic effect and laboratory-related adverse events of cyclosporine and tacrolimus in renal transplants

引用

INTERNATIONAL JOURNAL OF CLINICAL PHARMACY 2023年第3期45卷 659-668页

作者： Sridharan, Kannan Shah, Shamik Arabian Gulf Univ Coll Med & Med Sci Dept Pharmacol & Therapeut Manama Bahrain Salmaniya Med Complex Dept Nephrol Manama Bahrain Arabian Gulf Univ Coll Med & Med Sci Dept Internal Med Manama Bahrain

BackgroundSingle nucleotide polymorphisms influence the effects of tacrolimus and cyclosporine in renal *** set out to use machine learning algorithms (MLAs) to identify variables that predict the therapeutic effects and adverse events following tacrolimus and cyclosporine administration in renal transplant *** sampled 120 adult renal transplant patients (on cyclosporine or tacrolimus). Generalized linear model (GLM), support vector machine (SVM), artificial neural network (ANN), Chi-square automatic interaction detection, classification and regression tree, and K-nearest neighbors were the chosen MLAs. The mean absolute error (MAE), relative mean square error (RMSE), and regression coefficient (beta) with a 95% confidence interval (CI) were used as the model *** a stable dose of tacrolimus, the MAEs (RMSEs) of GLM, SVM, and ANN were 1.3 (1.5), 1.3 (1.8), and 1.7 (2.3) mg/day, respectively. GLM revealed that the POR*28 genotype and age significantly predicted the stable dose of tacrolimus as follows: POR*28 (beta -1.8;95% CI -3, -0.5;p = 0.006), and age (beta -0.04;95% CI -0.1, -0.006;p = 0.02). For a stable dose of cyclosporine, MAEs (RMSEs) of 93.2 (103.4), 79.1 (115.2), and 73.7 (91.7) mg/day were observed with GLM, SVM, and ANN, respectively. GLM revealed the following predictors of a stable dose of cyclosporine: CYP3A5*3 (beta -80.8;95% CI -130.3, -31.2;p = 0.001), and age (beta -3.4;95% CI -5.9, -0.9;p = 0.007).ConclusionWe observed that various MLAs could identify significant predictors that were useful to optimize tacrolimus and cyclosporine dosing regimens;yet, the findings must be externally validated.

关键词： Artificial intelligence Cyclosporine Immunosuppressants machine learning algorithms Tacrolimus

来源：评论

学校读者我要写书评

暂无评论

Value of machine learning algorithms for predicting diabetes risk: A subset analysis from a real-world retrospective cohort study

引用

JOURNAL OF DIABETES INVESTIGATION 2023年第2期14卷 309-320页

作者： Mao, Yaqian Zhu, Zheng Pan, Shuyao Lin, Wei Liang, Jixing Huang, Huibin Li, Liantao Wen, Junping Chen, Gang Fujian Med Univ Fujian Prov Hosp Dept Internal Med South BranchShengli Clin Med Coll Fuzhou Peoples R China Fujian Med Univ Fujian Prov Hosp Dept Endocrinol Shengli Clin Med Coll Fuzhou Peoples R China Fujian Acad Med Fujian Prov Key Lab Med Anal Fuzhou Peoples R China

Aims/Introduction To compare the application value of different machine learning (ML) algorithms for diabetes risk prediction. Materials and Methods This is a 3-year retrospective cohort study with a total of 3,687 participants being included in the data analysis. Modeling variable screening and predictive model building were carried out using logistic regression (LR) analysis and 10-fold cross-validation, respectively. In total, six different ML algorithms, including random forests, light gradient boosting machine, extreme gradient boosting, adaptive boosting (AdaBoost), multi-layer perceptrons and gaussian naive bayes were used for model construction. Model performance was mainly evaluated by the area under the receiver operating characteristic curve. The best performing ML model was selected for comparison with the traditional LR model and visualized using Shapley additive explanations. Results A total of eight risk factors most associated with the development of diabetes were identified by univariate and multivariate LR analysis, and they were visualized in the form of a nomogram. Among the six different ML models, the random forests model had the best predictive performance. After 10-fold cross-validation, its optimal model has an area under the receiver operating characteristic value of 0.855 (95% confidence interval [CI] 0.823-0.886) in the training set and 0.835 (95% CI 0.779-0.892) in the test set. In the traditional LR model, its area under the receiver operating characteristic value is 0.840 (95% CI 0.814-0.866) in the training set and 0.834 (95% CI 0.785-0.884) in the test set. Conclusions In the real-world epidemiological research, the combination of traditional variable screening and ML algorithm to construct a diabetes risk prediction model has satisfactory clinical application value.

关键词： Diabetes machine learning algorithms Predictive model

来源：评论

学校读者我要写书评

暂无评论

Evaluation of supervised machine learning algorithms in predicting the poor anticoagulation control and stable weekly doses of warfarin

引用

INTERNATIONAL JOURNAL OF CLINICAL PHARMACY 2023年第1期45卷 79-87页

作者： Sridharan, Kannan Ramanathan, Murali Al Banna, Rashed Arabian Gulf Univ Coll Med & Med Sci Dept Pharmacol & Therapeut Manama Bahrain Univ Buffalo State Univ New York Sch Pharm & Pharmaceut Sci Dept Pharmaceut Sci Buffalo NY USA Salmaniya Med Complex Dept Cardiol Manama Bahrain

Background machine learning algorithms (MLAs) carry a huge potential in identifying predicting factors and are being explored for their utility in the field of personalized medicine. Aim We aimed to investigate MLAs for identifying predictors (clinical and genetic) of poor anticoagulation status (ACS) and stable weekly warfarin dose (SWWD). Method Clinical factors, in addition to the CYP2C9, VKORC1, and CYP4F2 genotypes, were obtained for patients receiving warfarin for at least the previous six months. The C5.0 decision tree classification algorithm was used to predict poor ACS while classification and regression tree analysis (CART), in addition to the Chi-square automatic interaction detector (CHAID), was used to predict SWWD. The percentage of patients within 20% of the actual dose, root mean squared error (RMSE), and area under the receiver-operating characteristics curve (AUROC) were identified as performance indicators of the models. Results In the C5.0 classification decision tree, the CYP4F2 genotype was the strongest predictor of ACS (AUROC = 0.53). In the CART analysis of SWWD, VKORC1 polymorphisms were the most significant predictor, followed by the CYP2C9 genotype (percentage of patients within 20% of the actual dose = 38.2%, RMSE = 13.6). For the CHAID algorithm, the percentage of patients within 20% of the actual dose was 49%, while the RMSE was found to be 13.4. Conclusion Genetic and non-genetic predictive factors were identified by the MLAs for ACS and SWWD. Further, the need to externally validate the MLAs in a prospective study was highlighted.

关键词： Anticoagulants Artificial intelligence Decision trees machine learning algorithms Pharmacogenetics

来源：评论

学校读者我要写书评

暂无评论

Sex classification accuracy through machine learning algorithms - morphometric variables of human ear and nose

引用

BMC RESEARCH NOTES 2025年第1期18卷 1-10页

作者： Kaur, Tej Krishan, Kewal Sharma, Akanksha Guleria, Ankita Sharma, Vishal Panjab Univ Inst Forens Sci & Criminol Chandigarh India Panjab Univ UGC Ctr Adv Study Dept Anthropol Sect 14 Chandigarh India

ObjectiveSex determination is an important parameter for personal identification in forensic and medico-legal examinations. The study aims at predicting sex accuracy from different parameters of ear and nose by using a novel approach of machine learning Library, 'PyCaret'.ResultsThe present research was carried out on 508 participants (264 males and 244 females) aged 18-35 years from north India. Various ear and nose measurements were recorded on each participant. PyCaret employs a train-eval-testing validation approach, yielding a comprehensive output of the model in the form of a table that consolidates the average scores of all models over ten folds, including the respective time values. These models were compared based on performance metrics, and time taken. The logistic regression classifier emerged as the top-performing model, achieving the highest scores of 86.75% for sex prediction accuracy. Nasal breadth has been concluded as the most significant variable in accurate sex prediction. The findings indicate that the majority of the ear and nose characteristics significantly contribute to sexual dimorphism. This novel approach for sex classification can be efficiently used in a variety of forensic examinations and crime scene investigation especially where there is a need for estimation of sex for personal identification.

关键词： Human anatomy and morphology Ear and nose morphology Forensic identification machine learning algorithms PyCaret Sex classification

来源：评论

学校读者我要写书评

暂无评论

Methods and tools for automatic or semi-automatic recognition of selected emotions using machine learning algorithms

Methods and tools for automatic or semi-automatic recognitio...

引用

Progress in Applied Electrical Engineering (PAEE)

作者： Schneider, Piotr Mikolajewski, Dariusz Bryniarska, Anna Igras-Cybulska, Magdalena Cybulski, Artur Marcinowicz, Walery Janiszewski, Maciej Kawala-Sterniuk, Aleksandra Marie Curie Sklodowska Univ Inst Comp Sci Dept Neuroinformat & Biomed Engn Lublin Poland Hishoo Sp Zoo Gdynia Poland Kazimierz Wielki Univ Fac Comp Sci Bydgoszcz Poland Opole Univ Technol Fac Elect Engn Automat Control & Informat Opole Poland

ISBN: (纸本)9798331527570;9798331527563

Automatic or semi-automatic recognition of selected emotions using machine learning (ML) algorithms requires practical, fast and accurate implementation of the steps involved in acquiring the actual signals (e.g. speech, facial expression, posture and body movements), recording them in the form of an optimal feature vector/matrix, correctly interpreting the above data and reproducing and generalising this process within the ML system. Depending on the accuracy and speed required and the degree of its 'invasiveness' (e.g. by attaching sensors to the user's body), single or multi-modal interpretations of biometric signals associated with different groups of emotions are possible. This group of studies, despite their relative non-invasiveness, requires the caution prescribed by the Artificial Intelligence (AI) Act and RODO Act and the possibility of being replaced (if necessary) by alternatives. This article aims to analyse the opportunities and risks associated with this group of technologies, with a particular focus on directions for further development.

关键词： machine learning algorithms emotion recognition artificial intelligence automatic recognition

来源：评论

学校读者我要写书评

暂无评论

Predicting Water Safety: Harnessing the Power of Simple machine learning algorithms 3

Predicting Water Safety: Harnessing the Power of Simple Mach...

引用

International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)

作者： Dumbre, Dipali Devi, Seeta Chavan, Ranjana Symbiosis Int Deemed Univ SIU Symbiosis Coll Nursing SCON Pune Maharashtra India

ISBN: (纸本)9798350389432;9798350389449;9798350389456

One of the most valuable resources that is necessary for all life is water. Water pollution lowers the quality of the water, which affects the health of marine life and, consequently, that of humans who utilize it. Because of this, it's imperative to monitor water quality and guarantee the survival of marine life. This research will use artificial intelligence and machine learning techniques to evaluate the efficacy of several models in forecasting water safety. Orange tools are used to apply several prediction models, including Decision Tree, Gradient Boosting, Naive Bayes, Neural Network, SGD, kNN, and CN2 rule inducer. The review employs publicly available secondary data from Keggle, ensuring transparency and accessibility in the research methodology. The results demonstrate that the GB, Neural Network, and Tree achieved superior accuracy ratings of 0.992, 0.998, 0.997, and 0.997, respectively, with remarkable AUC values of 1.000, 1.000, and 0.969. In addition, their recall and accuracy scores are 0.998, 0.998, 0.998, and 0.997, confirming their outstanding performance in predicting water safety.

关键词： Water safety Prediction Artificial Intelligence machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Applying Formal Methods to Elicit Specifications for Grid Data Analysis Applications Using machine learning algorithms

Applying Formal Methods to Elicit Specifications for Grid Da...

引用

Computing Conference

作者： Subburaj, Vinitha Hannah Subburaj, Anitha Sarah West Texas A&M Univ Canyon TX 79015 USA

ISBN: (纸本)9783031622717;9783031622694;9783031622687

This research focuses on the application of formal methods to elicit formal specifications for machine learning algorithms (MLAs) in the context of grid data analysis. The incorporation of machine learning into grid data applications holds significant importance for enhancing decision-making processes. However, the absence of precise specifications often poses challenges in the development and validation of these algorithms. This study focuses on the early integration of formal methods throughout the development lifecycle to specify requirements for MLAs in grid data analysis applications. The paper will first list the MLA requirements in natural languages, existing solutions, and the utilization of Descartes Agent, a formal specification language, for early-stage specifications. Descartes Agent is employed to model the functional requirements of MLAs. Through a case study example, this study demonstrates the efficacy of Descartes - Agent in precisely specifying functional needs for MLAs in grid data analysis applications that leverage machine learning.

关键词： machine learning algorithms Grid data analysis Descartes - Agent

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Power Transformer Winding Fault Diagnosis Using machine learning algorithms 32

A Comparative Study of Power Transformer Winding Fault Diagn...

引用

32nd Southern African Universities Power Engineering Conference (SAUPEC)

作者： Dlamini, G. A. Z. Thango, B. A. Bokoro, P. N. Univ Johannesburg Dept Elect & Elect Engn Technol Johannesburg South Africa

ISBN: (纸本)9798350371345

In today's distribution and transmission infrastructure, power transformers have proven to be one of the maximum crucial components. Assessing the integrity of power transformer winding is imperative as winding failure is the most dominant failure location. Based on the reported literature a common trend with the research work is that they only consider one machine learning method and do not use other existing methods as benchmarks to corroborate proposed approaches. In this work, a comparative analysis of two trained well known, and broadly applied machine learning algorithms (MLAs): Artificial Neural Network (ANN) and Support Vector machine (SVM) to assess the power transformer winding fault is carried out. This work also introduces a machine learning algorithm that has the highest performance in terms of accuracy (validation and testing) with measured data from 300 power transformers that are independently inspected by industry connoisseurs. The obtained results show that the ANN method yields the best results when compared to the other algorithm.

关键词： power transformers frequency response analysis machine learning algorithms Neural Networks Support Vector machine

来源：评论

学校读者我要写书评

暂无评论

Predicting building damage grade by earthquake: a Bayesian Optimization-based comparative study of machine learning algorithms

引用

Asian Journal of Civil Engineering 2024年第1期25卷 253-264页

作者： Al-Rawashdeh, Mohammad Al Nawaiseh, Moh’d Yousef, Isam Bisharah, Majdi Alkhadrawi, Sajeda Al-Bdour, Hamza Department of Civil Engineering Faculty of Engineering Al-Balqa Applied University As-Salt Jordan Department of Civil Engineering Faculty of Engineering Amman Arab University Amman Jordan Department of Civil Engineering Munib and Angela Masri Faculty Engineering Aqaba University of Technology Aqaba Jordan Department of Civil Engineering University Putra Malaysia Selangor Serdang Malaysia Water and Environmental Engineering Department Al-Balqa Applied University Huson College Huson Jordan Master of Engineering Project Management Faculty of Engineering Jadara University Irbid Jordan

This study compares Bayesian Optimization-based machine learning systems that anticipate earthquake-damaged buildings and to evaluates building damage classification models. Using metrics, this study evaluates Random Forest, ElasticNet, and Decision Tree algorithms. This study showed damage level asymmetry. Fifth grade is the most prevalent and first grade the least. The class imbalance makes estimating building damage grades difficult, emphasizing the necessity for careful modeling. Bayesian Optimization optimizes machine learning algorithm hyperparameters to solve this problem. The optimization technique maximizes the receiver operating characteristic curve (AUROC), which measures the models’ ability to discern between damage levels. Convergence shows that Bayesian Optimization improves model discrimination. The optimized models classified building damage grades with an AUROC of 0.9952. Comparing machine learning algorithms yields insights. The ElasticNet model predicts building damage grade with 92.56% test accuracy and 92.67% train accuracy. With 89.39% test accuracy and 99.82% train accuracy, the Random Forest model performs well. The Decision Tree model has 89.19% test and 99.94% train accuracy. Mean Squared Error (MSE) shows that the Random Forest model makes more accurate predictions than the others. In this study, machine learning techniques forecast building deterioration. Research should address class imbalance, because it affects model performance. Bayesian Optimization helps models acquire data patterns, improving classification accuracy. This study shows that machine learning and optimization can forecast building seismic damage grades. The proposed model can successfully use for earthquake risk assessment and mitigation. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： Bayesian optimization Building damage grade prediction Class imbalance Comparative analysis machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial Advanced machine learning algorithms for Biomedical Data and Imaging - Part II

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2023年第1期27卷 188-189页

作者： Tanveer, M. Lin, Chin-Teng Singh, Amit Kumar Indian Inst Technol Indore Indore India Univ Technol Sydney Sydney NSW Australia Natl Inst Technol Patna Patna Bihar India

The papers in this special section (Part II) focus on advanced machine learning algorithms for biomedical data and imaging. The papers in Part II aim at bringing together contributions from both academia and industry ... 详细信息

关键词： Special issues and sections machine learning algorithms Biomedical imaging Bioinformatics Functional magnetic resonance imaging Ultrasonic imgaging Telemedicine Feature extraction Brain modeling

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：