Reviewing ensemble classification methods in breast cancer

Hosni, Mohamed; Abnane, Ibtissam; Idri, Ali; Gea, Juan M. Carrillo de; Alemán, José Luis Fernández

doi:10.1016/j.cmpb.2019.05.019

Cited by 158 publications

(77 citation statements)

References 96 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ensemble algorithms, although more complex in their methodology, have been shown to obtain greater performance in other works. In our results, however, they also did not achieve greater performance values [40].…”

Section: Discussioncontrasting

confidence: 83%

Machine learning techniques for mortality prediction in critical traumatic patients: anatomic and physiologic variables from the RETRAUCI study

Serviá

Montserrat

Badía

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Interest in models for calculating the risk of death in traumatic patients admitted to ICUs remains high. These models use variables derived from the deviation of physiological parameters and the intensity of anatomical lesions. Our objective is to create different predictive models of the mortality of critically traumatic patients using machine learning techniques.Methods: We used 9625 records from the RETRAUCI database (National Trauma Registry of 52 Spanish ICUs in the period of 2015–2019). Hospital mortality was 12.6%. Data on demographic variables, affected anatomical areas and physiological repercussions were used. The Weka Platform was used, along with a ten-fold cross-validation for the construction of nine supervised algorithms: logistic regression binary (LR), neural network (NN), sequential minimal optimization (SMO), classification rules (JRip), classification trees (CT), Bayesian networks (BN), adaptive boosting (ADABOOST), bootstrap aggregating (BAGGING) and random forest (RFOREST). The performance of the models was evaluated by accuracy, specificity, precision, recall, F-measure, and AUC.Results: The most important factors are those associated with traumatic brain injury (TBI) and organic failures. The LR finds thorax and limb injuries as independent protective factors of mortality. The CT generates 24 decision rules and uses those related to TBI as the first variables (range 2.0–81.6%). The JRip detects the eight rules with the highest risk of mortality (65.0–94.1%). The NN model uses a hidden layer of ten nodes, which requires 180 weights for its interpretation. The BN find the relationships between the different factors that identify different patient profiles. Models with the ensemble methodology (ADABOOST, BAGGING and RandomForest) do not have greater performance. All models obtain high values in accuracy, specificity, and AUC, but obtain lower values in recall. The greatest precision is achieved by the SMO model, and the BN obtains the best recall, F-measure, and AUC.Conclusion: Machine learning techniques are useful for creating mortality classification models in critically traumatic patients. With clinical interpretation, the algorithms establish different patient profiles according to the relationship between the variables used; determine groups of patients with different evolutions, and alert clinicians to the presence of rules that indicate the greatest severity.

show abstract

Section: Discussioncontrasting

confidence: 83%

Machine learning techniques for mortality prediction in critical traumatic patients: anatomic and physiologic variables from the RETRAUCI study

Serviá

Montserrat

Badía

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The ensemble methods develop and combine the multiple machine learning models to produce better-aggregated solutions than the individual models by compensating the mistakes [58][59][60]. Generally, they use generated solutions of the individual learning methods as inputs and produce ultimate solutions through a wide range of processing techniques, including averaging, bagging, boosting, stacking, and voting [61].…”

Section: Majority Voting Ensemble Methodsmentioning

confidence: 99%

Travel-To-School Mode Choice Modelling Employing Artificial Intelligence Techniques: A Comparative Study

et al. 2019

View full text Add to dashboard Cite

Many techniques including logistic regression and artificial intelligence have been employed to explain school-goers mode choice behavior. This paper aims to compare the effectiveness, robustness, and convergence of three different machine learning tools (MLT), namely the extreme learning machine (ELM), support vector machine (SVM), and multi-layer perceptron neural network (MLP-NN) to predict school-goers mode choice behavior in Al-Khobar and Dhahran cities of the Kingdom of Saudi Arabia (KSA). It uses the students’ information, including the school grade, the distance between home and school, travel time, family income and size, number of students in the family and education level of parents as input variables to the MLT. However, their outputs were binary, that is, either to choose the passenger car or walking to the school. The study examined a promising performance of the ELM and MLP-NN suggesting their significance as alternatives for school-goers mode choice modeling. The performances of the SVM was satisfactory but not to the same level of significance in comparison with the other two. Moreover, the SVM technique is computationally more expensive over the ELM and MLP-NN. Further, this research develops a majority voting ensemble method based on the outputs of the employed MLT to enhance the overall prediction performance. The presented results confirm the efficacy and superiority of the ensemble method over the others. The study results are likely to guide the transport engineers, planners, and decision-makers by providing them with a reliable way to model and predict the traffic demand for transport infrastructures on the basis of the prevailing mode choice behavior.

show abstract

“…The ensemble technique forms a group of learners with a classification method and these learners are trained with 'x' training data. The decision of each trained learner on the 'x' test data is evaluated and the joint decision of the learners constitutes the final decision of the method [9][10][11][12].…”

Section: Ensemble Classificationmentioning

confidence: 99%

Ensemble sınıflamdırıcı tabamlı mobil tiroit tanısı

Solmaz

Alkan

Günay

2020

DÜMF Mühendislik Dergisi

View full text Add to dashboard Cite

The thyroid gland plays a major role in many metabolic activities of the human body. Thyroid disease, which is quite common in humans, affects people's quality of life significantly. Early diagnosis is very important for taking precautions. The mobile diagnostic system can be the solution for early diagnosis especially in rural areas or without going to health institution. This study has been proposed to enable people with mobile devices to obtain quick information about the disease or to seek medical assistance in any matter without going to the hospital. Functional thyroid diagnosis system is designed using mobile device, Android based software application, Database (SQL) and Server (MATLAB based decision algorithms). With the system, functional thyroid disease can be diagnosed using an android based mobile device. Different classification algorithms were searched for the most accurate diagnosis and Ensemble method which has a high success rate for thyroid disease was used in the system. Ensemble classification technique reached a success rate of 99.06% and 99.08% for the first and second data group, respectively. These success rates were calculated by using gold standard test and results were compared with the literature. Obtained test results showed that, the proposed mobile diagnosis system could be used for the diagnosis of the functional thyroid. At the same time, this system can be developed for different diseases.

show abstract

Reviewing ensemble classification methods in breast cancer

Cited by 158 publications

References 96 publications

Machine learning techniques for mortality prediction in critical traumatic patients: anatomic and physiologic variables from the RETRAUCI study

Machine learning techniques for mortality prediction in critical traumatic patients: anatomic and physiologic variables from the RETRAUCI study

Travel-To-School Mode Choice Modelling Employing Artificial Intelligence Techniques: A Comparative Study

Ensemble sınıflamdırıcı tabamlı mobil tiroit tanısı

Contact Info

Product

Resources

About