Grid search in hyperparameter optimization of machine learning models for prediction of HIV/AIDS test results

Belete, Daniel Mesafint; Huchaiah, Manjaiah D.

doi:10.1080/1206212x.2021.1974663

Cited by 123 publications

(81 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With researchers devoting, grid search has been approved in various fields, as it has been found to improve the machine learning prediction model performance, such as the prediction of HIV/AIDS [57], text classification [58], and short-term PV power forecasting [37]. In this research, we proved that grid search can also improve the performance of ensemble learning in ubiquitination-site prediction tasks.…”

Section: Methodsmentioning

confidence: 76%

Ensemble Machine Learning to “Boost” Ubiquitination-sites Prediction

Jiang

2022

Preprint

View full text Add to dashboard Cite

Ubiquitination-site prediction is an important task because ubiquitination is a critical regulatory function for many biological processes such as proteasome degradation, DNA repair and transcription, signal transduction, endocytoses, and sorting. However, the highly dynamic and reversible nature of ubiquitination makes it difficult to experimentally identify specific ubiquitination sites. In this paper, we explore the possibility of improving the prediction of ubiquitination sites using ensemble machine learning methods including Random Forrest (RF), Adaptive Boosting (ADB), Gradient Boosting (GB), and eXtreme Gradient Boosting (XGB). By doing grid search with the four ensemble methods and six comparison non-ensemble learning methods including Naive Base (NB), Logistic Regression (LR), Decision Trees (DT), Support Vector Machine (SVM), LASSO, and K-Nearest Neighbor (KNN), we find that all the four ensemble methods significantly outperform one or more non-ensemble methods included in this study. XGB outperforms three out of the six non-ensemble methods that we included; ADB and RF both outperform two of the six non-ensemble methods; GB outperforms one non-ensemble method. Comparing the four ensemble methods among themselves. GB performs the worst; XGB and ADB are very comparable in terms of prediction, but ADB beats XGB by far in terms of both the unit model training time and total running time. Both XGB and ADB tend to do better than RF in terms of prediction, but RF has the shortest unit model training time out of the three. In addition, we notice that ADB tends to outperform XGB when dealing with small-scale datasets, and RF can outperform either ADB or XGB when data are less balanced. Interestingly, we find that SVM, LR, and LASSO, three of the six non-ensemble methods included, perform comparably with all the ensemble methods. Based on this study, ensemble learning is a promising approach to ignificantly improving ubiquitination-site prediction using protein segment data.

show abstract

Section: Methodsmentioning

confidence: 76%

Ensemble Machine Learning to “Boost” Ubiquitination-sites Prediction

Jiang

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The ML algorithms gave the best performance when fitted onto the dataset under optimal hypermeter settings that were obtained using grid search [ 22 ]. Also, the feature selection method SFFS [ 23 ] automatically selected k_best features from an exhaustive list of variables so that features with the best accuracy scores are chosen for model-building, thereby preventing the curse of dimensionality [ 24 ].…”

Section: Discussionmentioning

confidence: 99%

Utility of adding Radiomics to clinical features in predicting the outcomes of radiotherapy for head and neck cancer using machine learning

et al. 2022

View full text Add to dashboard Cite

Background Radiomics involves the extraction of quantitative information from annotated Computed-Tomography (CT) images, and has been used to predict outcomes in Head and Neck Squamous Cell Carcinoma (HNSCC). Subjecting combined Radiomics and Clinical features to Machine Learning (ML) could offer better predictions of clinical outcomes. This study is a comparative performance analysis of ML models with Clinical, Radiomics, and Clinico-Radiomic datasets for predicting four outcomes of HNSCC treated with Curative Radiation Therapy (RT): Distant Metastases, Locoregional Recurrence, New Primary, and Residual Disease. Methodology The study used retrospective data of 311 HNSCC patients treated with radiotherapy between 2013–2018 at our centre. Binary prediction models were developed for the four outcomes with Clinical-only, Clinico-Radiomic, and Radiomics-only datasets, using three different ML classification algorithms namely, Random Forest (RF), Kernel Support Vector Machine (KSVM), and XGBoost. The best-performing ML algorithms of the three dataset groups was then compared. Results The Clinico-Radiomic dataset using KSVM classifier provided the best prediction. Predicted mean testing accuracy for Distant Metastases, Locoregional Recurrence, New Primary, and Residual Disease was 97%, 72%, 99%, and 96%, respectively. The mean area under the receiver operating curve (AUC) was calculated and displayed for all the models using three dataset groups. Conclusion Clinico-Radiomic dataset improved the predictive ability of ML models over clinical features alone, while models built using Radiomics performed poorly. Radiomics data could therefore effectively supplement clinical data in predicting outcomes.

show abstract

“…The angle measurements were done automatically thanks to the point determinations over the input data. The model network structure was obtained through grid search hyper parameter optimization [85] including model tries with sets of parameters (as running on the same scoliosis dataset explained in the next sub-title). Table 1 shows hyper parameter sets for the CapsNet model determination.…”

Section: A Capsnet For Cobb Angle Measurementmentioning

confidence: 99%

Development of a CapsNet and Fuzzy Logic Decision Support System for Diagnosing the Scoliosis and Planning Treatments via Schroth Method

Goral

Köse

2022

IEEE Access

View full text Add to dashboard Cite

Scoliosis is a disease caused by the spine curving. It is treatable but physiotherapists may do different measurements for curvature angles. That's a problem affecting the treatment planning. This study aims to develop a Deep Learning-based decision support system, which diagnoses scoliosis and plans treatments via Schroth method. The system has an interpretable and explainable CapsNet model processing x-ray image to detect 68-point vertebrae and make Cobb angle measurements. By using angle values and patient parameters, treatment is planned through an automated Schroth definition and the Fuzzy Logic. In the evaluations, the CapsNet had dominating findings (some of them are MSE: 0.0038, PCC: 0.93, Accuracy: 0.98). The Fuzzy Logic model was accurate at exercise plans for past cases. Also, physiotherapists and patients had positive feedback for the system usage, trustworthiness, diagnosis, treatment planning and tracking. As a conclusion, the system ensures advancements for automated diagnosis and treatment of scoliosis.

show abstract

Grid search in hyperparameter optimization of machine learning models for prediction of HIV/AIDS test results

Cited by 123 publications

References 12 publications

Ensemble Machine Learning to “Boost” Ubiquitination-sites Prediction

Ensemble Machine Learning to “Boost” Ubiquitination-sites Prediction

Utility of adding Radiomics to clinical features in predicting the outcomes of radiotherapy for head and neck cancer using machine learning

Development of a CapsNet and Fuzzy Logic Decision Support System for Diagnosing the Scoliosis and Planning Treatments via Schroth Method

Contact Info

Product

Resources

About