Computational prediction of implantation outcome after embryo transfer

The aim of this study is to develop a computational prediction model for implantation outcome after an embryo transfer cycle. In this study, information of 500 patients and 1360 transferred embryos, including cleavage and blastocyst stages and fresh or frozen embryos, from April 2016 to February 2018, were collected. The dataset containing 82 attributes and a target label (indicating positive and negative implantation outcomes) was constructed. Six dominant machine learning approaches were examined based on their performance to predict embryo transfer outcomes. Also, feature selection procedures were used to identify effective predictive factors and recruited to determine the optimum number of features based on classifiers performance. The results revealed that random forest was the best classifier (accuracy = 90.40% and area under the curve = 93.74%) with optimum features based on a 10-fold cross-validation test. According to the Support Vector Machine-Feature Selection algorithm, the ideal numbers of features are 78. Follicle stimulating hormone/human menopausal gonadotropin dosage for ovarian stimulation was the most important predictive factor across all examined embryo transfer features. The proposed machine learning-based prediction model could predict embryo transfer outcome and implantation of embryos with high accuracy, before the start of an embryo transfer cycle.

Download Full-text

Predicting Student’s Performance Using Machine Learning Algorithm

International Journal of Advanced Research in Science, Communication and Technology ◽

10.48175/ijarsct-1209 ◽

2021 ◽

pp. 53-58

Author(s):

Sheela Rani P ◽

Dhivya S ◽

Dharshini Priya M ◽

Dharmila Chowdary A

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Prediction Model ◽

Naive Bayes ◽

Learning Algorithm ◽

Naïve Bayes ◽

Machine Learning Algorithms ◽

Support Vector ◽

Learning Approaches ◽

K Nearest Neighbors

Machine learning is a new analysis discipline that uses knowledge to boost learning, optimizing the training method and developing the atmosphere within which learning happens. There square measure 2 sorts of machine learning approaches like supervised and unsupervised approach that square measure accustomed extract the knowledge that helps the decision-makers in future to require correct intervention. This paper introduces an issue that influences students' tutorial performance prediction model that uses a supervised variety of machine learning algorithms like support vector machine , KNN(k-nearest neighbors), Naïve Bayes and supplying regression and logistic regression. The results supported by various algorithms are compared and it is shown that the support vector machine and Naïve Bayes performs well by achieving improved accuracy as compared to other algorithms. The final prediction model during this paper may have fairly high prediction accuracy .The objective is not just to predict future performance of students but also provide the best technique for finding the most impactful features that influence student’s while studying.

Download Full-text

Diagnostic Performance of 2D and 3D T2WI-Based Radiomics Features With Machine Learning Algorithms to Distinguish Solid Solitary Pulmonary Lesion

Frontiers in Oncology ◽

10.3389/fonc.2021.683587 ◽

2021 ◽

Vol 11 ◽

Author(s):

Qi Wan ◽

Jiaxuan Zhou ◽

Xiaoying Xia ◽

Jianfeng Hu ◽

Peng Wang ◽

...

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Diagnostic Performance ◽

Feature Selection Method ◽

Machine Learning Algorithms ◽

Support Vector ◽

Learning Approaches ◽

Selection Methods ◽

Linear Discriminant ◽

2D And 3D

ObjectiveTo evaluate the performance of 2D and 3D radiomics features with different machine learning approaches to classify SPLs based on magnetic resonance(MR) T2 weighted imaging (T2WI).Material and MethodsA total of 132 patients with pathologically confirmed SPLs were examined and randomly divided into training (n = 92) and test datasets (n = 40). A total of 1692 3D and 1231 2D radiomics features per patient were extracted. Both radiomics features and clinical data were evaluated. A total of 1260 classification models, comprising 3 normalization methods, 2 dimension reduction algorithms, 3 feature selection methods, and 10 classifiers with 7 different feature numbers (confined to 3–9), were compared. The ten-fold cross-validation on the training dataset was applied to choose the candidate final model. The area under the receiver operating characteristic curve (AUC), precision-recall plot, and Matthews Correlation Coefficient were used to evaluate the performance of machine learning approaches.ResultsThe 3D features were significantly superior to 2D features, showing much more machine learning combinations with AUC greater than 0.7 in both validation and test groups (129 vs. 11). The feature selection method Analysis of Variance(ANOVA), Recursive Feature Elimination(RFE) and the classifier Logistic Regression(LR), Linear Discriminant Analysis(LDA), Support Vector Machine(SVM), Gaussian Process(GP) had relatively better performance. The best performance of 3D radiomics features in the test dataset (AUC = 0.824, AUC-PR = 0.927, MCC = 0.514) was higher than that of 2D features (AUC = 0.740, AUC-PR = 0.846, MCC = 0.404). The joint 3D and 2D features (AUC=0.813, AUC-PR = 0.926, MCC = 0.563) showed similar results as 3D features. Incorporating clinical features with 3D and 2D radiomics features slightly improved the AUC to 0.836 (AUC-PR = 0.918, MCC = 0.620) and 0.780 (AUC-PR = 0.900, MCC = 0.574), respectively.ConclusionsAfter algorithm optimization, 2D feature-based radiomics models yield favorable results in differentiating malignant and benign SPLs, but 3D features are still preferred because of the availability of more machine learning algorithmic combinations with better performance. Feature selection methods ANOVA and RFE, and classifier LR, LDA, SVM and GP are more likely to demonstrate better diagnostic performance for 3D features in the current study.

Download Full-text

Ensemble Machine Learning Approaches for Proteogenomic Cancer Studies

10.21203/rs.3.rs-101902/v1 ◽

2020 ◽

Author(s):

Yulan Liang ◽

Amin Gharipour ◽

Erik Kelemen ◽

Arpad Kelemen

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Prediction Accuracy ◽

Performance Criteria ◽

Stable Set ◽

Support Vector ◽

Kappa Statistics ◽

Learning Approaches ◽

Ensemble Machine Learning ◽

Homogeneous Ensemble

Abstract Background: The identification of important proteins is critical for medical diagnosis and prognosis in common diseases. Diverse sets of computational tools were developed for omics data reductions and protein selections. However, standard statistical models with single feature selection involve the multi-testing burden of low power with the available limited samples. Furthermore, high correlations among proteins with high redundancy and moderate effects often lead to unstable selections and cause reproducibility issues. Ensemble feature selection in machine learning may identify a stable set of disease biomarkers that could improve the prediction performance of subsequent classification models, and thereby simplify their interpretability. In this study, we developed a three-stage homogeneous ensemble feature selection approach for both identifying proteins and improving prediction accuracy. This approach was implemented and applied to ovarian cancer proteogenomics data sets: 1) binary putative homologous recombination deficiency positive or negative; and 2) multiple mRNA classes (differentiated, proliferative, immunoreactive, mesenchymal, and unknown). We conducted and compared various machine learning approaches with homogeneous ensemble feature selection including random forest, support vector machine, and neural network for predicting both binary and multiple class outcomes. Various performance criteria including sensitivity, specificity, kappa statistics were used to assess the prediction consistency and accuracy. Results: With the proposed three-stage homogeneous ensemble feature selection approaches, prediction accuracy can be improved with the limited sample through continuously reducing errors and redundancy, i.e. Treebag provided 83% prediction accuracy (85% sensitivity and 81% specificity) for binary ovarian outcomes. For mRNA multi-classes classification, our approach provided even better accuracy with increased sample size. Conclusions: Despite the different prediction accuracies from various models, homogeneous ensemble feature selection proposed identified consistent sets of top ranked important markers out of 9606 proteins linked to the binary disease and multiple mRNA class outcomes.

Download Full-text

Using Machine Learning Approaches to Predict Target Gene Expression in Rice T-DNA Insertional Mutants

Frontiers in Genetics ◽

10.3389/fgene.2021.798107 ◽

2021 ◽

Vol 12 ◽

Author(s):

Ching-Hsuan Chien ◽

Lan-Ying Huang ◽

Shuen-Fang Lo ◽

Liang-Jwu Chen ◽

Chi-Chou Liao ◽

...

Keyword(s):

Gene Expression ◽

Machine Learning ◽

Feature Selection ◽

Target Genes ◽

Promoter Sequence ◽

Activation Mechanism ◽

Support Vector ◽

Regulatory Sequence ◽

Learning Approaches ◽

Local Sequence

To change the expression of the flanking genes by inserting T-DNA into the genome is commonly used in rice functional gene research. However, whether the expression of a gene of interest is enhanced must be validated experimentally. Consequently, to improve the efficiency of screening activated genes, we established a model to predict gene expression in T-DNA mutants through machine learning methods. We gathered experimental datasets consisting of gene expression data in T-DNA mutants and captured the PROMOTER and MIDDLE sequences for encoding. In first-layer models, support vector machine (SVM) models were constructed with nine features consisting of information about biological function and local and global sequences. Feature encoding based on the PROMOTER sequence was weighted by logistic regression. The second-layer models integrated 16 first-layer models with minimum redundancy maximum relevance (mRMR) feature selection and the LADTree algorithm, which were selected from nine feature selection methods and 65 classified methods, respectively. The accuracy of the final two-layer machine learning model, referred to as TIMgo, was 99.3% based on fivefold cross-validation, and 85.6% based on independent testing. We discovered that the information within the local sequence had a greater contribution than the global sequence with respect to classification. TIMgo had a good predictive ability for target genes within 20 kb from the 35S enhancer. Based on the analysis of significant sequences, the G-box regulatory sequence may also play an important role in the activation mechanism of the 35S enhancer.

Download Full-text

Recurrent Stroke Prediction using Machine Learning Algorithms with Clinical Public Datasets: An Empirical Performance Evaluation

Baghdad Science Journal ◽

10.21123/bsj.2021.18.4(suppl.).1406 ◽

2021 ◽

Vol 18 (4(Suppl.)) ◽

pp. 1406

Author(s):

Fadratul Hafinaz Hassan ◽

Mohd Adib Omar

Keyword(s):

Machine Learning ◽

Prediction Model ◽

Prediction Models ◽

Recurrent Stroke ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Support Vector ◽

Learning Approaches ◽

Recurrent Strokes ◽

Public Datasets

Recurrent strokes can be devastating, often resulting in severe disability or death. However, nearly 90% of the causes of recurrent stroke are modifiable, which means recurrent strokes can be averted by controlling risk factors, which are mainly behavioral and metabolic in nature. Thus, it shows that from the previous works that recurrent stroke prediction model could help in minimizing the possibility of getting recurrent stroke. Previous works have shown promising results in predicting first-time stroke cases with machine learning approaches. However, there are limited works on recurrent stroke prediction using machine learning methods. Hence, this work is proposed to perform an empirical analysis and to investigate machine learning algorithms implementation in the recurrent stroke prediction models. This research aims to investigate and compare the performance of machine learning algorithms using recurrent stroke clinical public datasets. In this study, Artificial Neural Network (ANN), Support Vector Machine (SVM) and Bayesian Rule List (BRL) are used and compared their performance in the domain of recurrent stroke prediction model. The result of the empirical experiments shows that ANN scores the highest accuracy at 80.00%, follows by BRL with 75.91% and SVM with 60.45%.

Download Full-text

Heart Disease Prediction Model Using Naïve Bayes Algorithm and Machine Learning Techniques

International Journal of Engineering & Technology ◽

10.14419/ijet.v10i1.31310 ◽

2021 ◽

Vol 10 (1) ◽

pp. 46

Author(s):

Maria Yousef ◽

Prof. Khaled Batiha

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Heart Disease ◽

Prediction Model ◽

Naive Bayes ◽

Naïve Bayes ◽

Machine Learning Techniques ◽

Support Vector ◽

Disease Prediction ◽

Prediction Systems

These days, heart disease comes to be one of the major health problems which have affected the lives of people in the whole world. Moreover, death due to heart disease is increasing day by day. So the heart disease prediction systems play an important role in the prevention of heart problems. Where these prediction systems assist doctors in making the right decision to diagnose heart disease easily. The existing prediction systems suffering from the high dimensionality problem of selected features that increase the prediction time and decrease the performance accuracy of the prediction due to many redundant or irrelevant features. Therefore, this paper aims to provide a solution of the dimensionality problem by proposing a new mixed model for heart disease prediction based on (Naïve Bayes method, and machine learning classifiers).In this study, we proposed a new heart disease prediction model (NB-SKDR) based on the Naïve Bayes algorithm (NB) and several machine learning techniques including Support Vector Machine, K-Nearest Neighbors, Decision Tree, and Random Forest. This prediction model consists of three main phases which include: preprocessing, feature selection, and classification. The main objective of this proposed model is to improve the performance of the prediction system and finding the best subset of features. This proposed approach uses the Naïve Bayes technique based on the Bayes theorem to select the best subset of features for the next classification phase, also to handle the high dimensionality problem by avoiding unnecessary features and select only the important ones in an attempt to improve the efficiency and accuracy of classifiers. This method is able to reduce the number of features from 13 to 6 which are (age, gender, blood pressure, fasting blood sugar, cholesterol, exercise induce engine) by determining the dependency between a set of attributes. The dependent attributes are the attributes in which an attribute depends on the other attribute in deciding the value of the class attribute. The dependency between attributes is measured by the conditional probability, which can be easily computed by Bayes theorem. Moreover, in the classification phase, the proposed system uses different classification algorithms such as (DT Decision Tree, RF Random Forest, SVM Support Vector machine, KNN Nearest Neighbors) as a classifiers for predicting whether a patient has heart disease or not. The model is trained and evaluated using the Cleveland Heart Disease database, which contains 13 features and 303 samples.Different algorithms use different rules for producing different representations of knowledge. So, the selection of algorithms to build our model is based on their performance. In this work, we applied and compared several classification algorithms which are (DT, SVM, RF, and KNN) to identify the best-suited algorithm to achieve high accuracy in the prediction of heart disease. After combining the Naive Bayes method with each one of these previous classifiers the performance of these combines algorithms is evaluated by different performance metrics such as (Specificity, Sensitivity, and Accuracy). Where the experimental results show that out of these four classification models, the combination between the Naive Bayes feature selection approach and the SVM RBF classifier can predict heart disease with the highest accuracy of 98%. Finally, the proposed approach is compared with another two systems which developed based on two different approaches in the feature selection step. The first system, based on the Genetic Algorithm (GA) technique, and the second uses the Principal Component Analysis (PCA) technique. Consequently, the comparison proved that the Naive Bayes selection approach of the proposed system is better than the GA and PCA approach in terms of prediction accuracy.

Download Full-text

A Topical Survey: Applications of Machine Learning in Medical Issues

Journal of Computational and Theoretical Nanoscience ◽

10.1166/jctn.2020.9334 ◽

2020 ◽

Vol 17 (11) ◽

pp. 5010-5019

Author(s):

Chapala Maharana ◽

Bijan Bihari Mishra ◽

Ch. Sanjeev Kumar Dash

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Image Segmentation ◽

Learning Algorithms ◽

Disease Diagnosis ◽

Lesion Detection ◽

Machine Learning Algorithms ◽

Support Vector ◽

Learning Approaches ◽

Medical Issues

Computational Intelligence methods have replaced almost all real world applications with high accuracy within the given time period. Machine Learning approaches like classification, feature selection, feature extraction have solved many problems of different domain. They use different ML models implemented with suitable ML tool or combination of tools from NN (Neural Network), SVM (Support Vector Machine), DL (Deep Learning), ELM (Extreme Learning Machine). The model is used for training with known data along with ML algorithms (fuzzy logic, genetic algorithm) to optimize the accuracy for different medical issues for example gene expression and image segmentation for information extraction and disease diagnosis, health monitoring, disease treatment. Most of the medical problems are solved using recent advances in AI (Artificial Intelligence) technologies with the biomedical systems development (e.g., Knowledge based Decision Support Systems) and AI technologies with medical informatics science. AI based methods like machine learning algorithms implemented models are increasingly found in real life applications ex. healthcare, natural calamity detection and forecasting. There are the expert systems handled by experts for knowledge gain which is used in decision making applications. The ML models are found in different medical applications like disease diagnosis (ex. cancer prediction, diabetics disease prediction) and for treatment of diseases (ex. in diabetics disease the reduction in mean glucose concentration following intermittent gastric feeds). The feature selection ML method is used for EEG classification for detection of the severity of the disease in heart related diseases and for identification of genes in different disorder like autism disorder. The ML models are found in health record systems. There are other applications of ML approaches found in image segmentation, tissue extraction, image fragmentation for disease diagnosis (ex. lesion detection in breast cancer for malignancy) and then treatment of those diseases. ML models are found in mobile health treatment, treatment of psychology patients, treatment of dumb patients etc. Medical data handling is the vital part of health care systems for the development of AI systems which can again be solved by machine learning approaches. The ML approaches for medical issues have used ensemble methods or combinations of machine learning tools and machine learning algorithms to optimize the result with good accuracy value at a faster rate.

Download Full-text

Tree-based homogeneous ensemble model with feature selection for diabetic retinopathy prediction

Jurnal Teknologi dan Sistem Komputer ◽

10.14710/jtsiskom.2020.13669 ◽

2020 ◽

Vol 8 (4) ◽

pp. 297-303

Author(s):

Tamunopriye Ene Dagogo-George ◽

Hammed Adeleye Mojeed ◽

Abdulateef Oluwagbemiga Balogun ◽

Modinat Abolore Mabayoje ◽

Shakirat Aderonke Salihu

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Diabetic Retinopathy ◽

Ensemble Methods ◽

Predictive Performance ◽

Ensemble Classification ◽

Support Vector ◽

Learning Approaches ◽

Vector Machines ◽

Homogeneous Ensemble

Diabetic Retinopathy (DR) is a condition that emerges from prolonged diabetes, causing severe damages to the eyes. Early diagnosis of this disease is highly imperative as late diagnosis may be fatal. Existing studies employed machine learning approaches with Support Vector Machines (SVM) having the highest performance on most analyses and Decision Trees (DT) having the lowest. However, SVM has been known to suffer from parameter and kernel selection problems, which undermine its predictive capability. Hence, this study presents homogenous ensemble classification methods with DT as the base classifier to optimize predictive performance. Boosting and Bagging ensemble methods with feature selection were employed, and experiments were carried out using Python Scikit Learn libraries on DR datasets extracted from UCI Machine Learning repository. Experimental results showed that Bagged and Boosted DT were better than SVM. Specifically, Bagged DT performed best with accuracy 65.38 %, f-score 0.664, and AUC 0.731, followed by Boosted DT with accuracy 65.42 %, f-score 0.655, and AUC 0.724 when compared to SVM (accuracy 65.16 %, f-score 0.652, and AUC 0.721). These results indicate that DT's predictive performance can be optimized by employing the homogeneous ensemble methods to outperform SVM in predicting DR.

Download Full-text

Importance of GWAS risk loci and clinical data in predicting asthma using machine-learning approaches

10.21203/rs.3.rs-21271/v1 ◽

2020 ◽

Author(s):

Si-Qiao Liang ◽

Jian-Xiong Long ◽

Jingmin Deng ◽

Xuan Wei ◽

Mei-Ling Yang ◽

...

Keyword(s):

Machine Learning ◽

Risk Factors ◽

Clinical Data ◽

Genome Wide Association Study ◽

Prediction Models ◽

Area Under The Curve ◽

Gradient Boosting ◽

Support Vector ◽

Learning Approaches ◽

Extreme Gradient Boosting

Abstract Asthma is a serious immune-mediated respiratory airway disease. Its pathological processes involve genetics and the environment, but it remains unclear. To understand the risk factors of asthma, we combined genome-wide association study (GWAS) risk loci and clinical data in predicting asthma using machine-learning approaches. A case–control study with 123 asthma patients and 100 healthy controls was conducted in Zhuang population in Guangxi. GWAS risk loci were detected using polymerase chain reaction, and clinical data were collected. Machine-learning approaches (e.g., extreme gradient boosting [XGBoost], decision tree, support vector machine, and random forest algorithms) were used to identify the major factors that contributed to asthma. A total of 14 GWAS risk loci with clinical data were analyzed on the basis of 10 times of 10-fold cross-validation for all machine-learning models. Using GWAS risk loci or clinical data, the best performances were area under the curve (AUC) values of 64.3% and 71.4%, respectively. Combining GWAS risk loci and clinical data, the XGBoost established the best model with an AUC of 79.7%, indicating that the combination of genetics and clinical data can enable improved performance. We then sorted the importance of features and found that the top six risk factors for predicting asthma were rs3117098, rs7775228, family history, rs2305480, rs4833095, and body mass index. Asthma-prediction models based on GWAS risk loci and clinical data can accurately predict asthma and thus provide insights into the disease pathogenesis of asthma. Further research is required to evaluate more genetic markers and clinical data and predict asthma risk.

Download Full-text

Application of Machine Learning Approaches for the Design and Study of Anticancer Drugs

Current Drug Targets ◽

10.2174/1389450119666180809122244 ◽

2019 ◽

Vol 20 (5) ◽

pp. 488-500 ◽

Cited By ~ 6

Author(s):

Yan Hu ◽

Yi Lu ◽

Shuo Wang ◽

Mengying Zhang ◽

Xiaosheng Qu ◽

...

Keyword(s):

Machine Learning ◽

Drug Design ◽

Anticancer Drugs ◽

Nearest Neighbor ◽

Cost Effective ◽

Support Vector ◽

Learning Approaches ◽

K Nearest Neighbor ◽

Activity Prediction ◽

Linear Discriminant

Background: Globally the number of cancer patients and deaths are continuing to increase yearly, and cancer has, therefore, become one of the world's highest causes of morbidity and mortality. In recent years, the study of anticancer drugs has become one of the most popular medical topics. Objective: In this review, in order to study the application of machine learning in predicting anticancer drugs activity, some machine learning approaches such as Linear Discriminant Analysis (LDA), Principal components analysis (PCA), Support Vector Machine (SVM), Random forest (RF), k-Nearest Neighbor (kNN), and Naïve Bayes (NB) were selected, and the examples of their applications in anticancer drugs design are listed. Results: Machine learning contributes a lot to anticancer drugs design and helps researchers by saving time and is cost effective. However, it can only be an assisting tool for drug design. Conclusion: This paper introduces the application of machine learning approaches in anticancer drug design. Many examples of success in identification and prediction in the area of anticancer drugs activity prediction are discussed, and the anticancer drugs research is still in active progress. Moreover, the merits of some web servers related to anticancer drugs are mentioned.

Download Full-text