The use of artificial neural networks in decision support in cancer: A systematic review

Lisboa, Paulo J. G.; Taktak, Azzam

doi:10.1016/j.neunet.2005.10.007

Cited by 411 publications

(200 citation statements)

References 42 publications

Supporting

Mentioning

194

Contrasting

Unclassified

Order By: Relevance

“…ANNs were applied successfully in various clinical studies. [31][32][33][34][35] Caocci et al 36 compared the performance of ANN with logistic regression for predicting acute GVHD in a group of 78 b-thalassemia major patients who underwent HSCTs. Prediction sensitivity and specificity of the ANN were 83.3% and 90.1%, respectively, versus 21.7% and 83.3% with logistic regression.…”

Section: Data Preparations (Preprocessing)mentioning

confidence: 99%

Application of machine learning algorithms for clinical predictive modeling: a data-mining approach in SCT

Shouval¹,

Bondi

Mishan

et al. 2013

Bone Marrow Transplant

107

View full text Add to dashboard Cite

Data collected from hematopoietic SCT (HSCT) centers are becoming more abundant and complex owing to the formation of organized registries and incorporation of biological data. Typically, conventional statistical methods are used for the development of outcome prediction models and risk scores. However, these analyses carry inherent properties limiting their ability to cope with large data sets with multiple variables and samples. Machine learning (ML), a field stemming from artificial intelligence, is part of a wider approach for data analysis termed data mining (DM). It enables prediction in complex data scenarios, familiar to practitioners and researchers. Technological and commercial applications are all around us, gradually entering clinical research. In the following review, we would like to expose hematologists and stem cell transplanters to the concepts, clinical applications, strengths and limitations of such methods and discuss current research in HSCT. The aim of this review is to encourage utilization of the ML and DM techniques in the field of HSCT, including prediction of transplantation outcome and donor selection.

show abstract

Section: Data Preparations (Preprocessing)mentioning

confidence: 99%

Application of machine learning algorithms for clinical predictive modeling: a data-mining approach in SCT

Shouval¹,

Bondi

Mishan

et al. 2013

Bone Marrow Transplant

107

View full text Add to dashboard Cite

show abstract

“…CAD systems have been investigated and applied for the diagnosis of various diseases, especially for cancer. Some comprehensive reviews on the topic can be found in (Kawamoto et al, 2005;Sampat et al, 2005;Lisboa and Taktak, 2006). CAD systems rely on a wide range of classifiers, such as traditional statistical and Bayesian classifiers (Duda et al, 2000), case-base reasoning classifiers (Aha et al, 1991), decision trees (Mitchell, 1997), and neural networks (Zhang, 2000).…”

Section: Introductionmentioning

confidence: 99%

“…CAD systems rely on a wide range of classifiers, such as traditional statistical and Bayesian classifiers (Duda et al, 2000), case-base reasoning classifiers (Aha et al, 1991), decision trees (Mitchell, 1997), and neural networks (Zhang, 2000). In particular, neural network classifiers are a very popular choice for medical decision making and they have shown to be very effective in the clinical domain (Lisboa, 2002;Lisboa and Taktak, 2006).…”

Section: Introductionmentioning

confidence: 99%

Training neural network classifiers for medical decision making: The effects of imbalanced datasets on classification performance

Mazurowski¹,

Habas²,

Żurada³

et al. 2008

Neural Networks

644

298

View full text Add to dashboard Cite

This study investigates the effect of class imbalance in training data when developing neural network classifiers for computer aided medical diagnosis. The investigation is performed in the presence of other characteristics that are typical among medical data, namely small training sample size, large number of features, and correlations between features. Two methods of neural network training are explored: classical backpropagation (BP) and particle swarm optimization (PSO) with clinically relevant training criteria. An experimental study is performed using simulated data and the conclusions are further validated on real clinical data for breast cancer diagnosis. The results show that classifier performance deteriorates with even modest class imbalance in the training data. Further, it is shown that BP is generally preferable over PSO for imbalanced training data especially with small data sample and large number of features. Finally, it is shown that there is no clear preference between oversampling and no compensation approach and some guidance is provided regarding a proper selection.

show abstract

“…Commonly used examples for supervised learning approaches are Support Vector Machines (SVM) 68,69 Random Forest (RF) 69 and artificial neural networks (ANN). 70,71 SVMs are commonly applied for classification analyses, 72 which are primarily applied for a two-group classification. The algorithm generates an optimal hyperplane to divide the two classes.…”

Section: Data Processing and Miningmentioning

confidence: 99%

Application of omic technologies in cancer research

et al. 2018

View full text Add to dashboard Cite

Understanding the biology of health and diseases such as cancer, generating insight into the triggers and potentiators of disease and the development of therapeutic approaches to counter and treat disease requires detailed interrogation of inherited genes, and the dynamic positioning of the transcriptome and proteome. In the last 10 years, significant technological developments and increases in sample throughput capabilities have led to a dramatic increase in the size and complexity of the datasets that can be generated. A key challenge now is to develop robust approaches for analysing and interpreting these, and converting data into biologically-and clinically-relevant information. Herein, we provide an overview of approaches for acquiring, integrating and interpreting complex datasets generated using multiple omic platforms, with a focus on the field of cancer research, and highlight key successful data handling and integration applications.

show abstract

The use of artificial neural networks in decision support in cancer: A systematic review

Cited by 411 publications

References 42 publications

Application of machine learning algorithms for clinical predictive modeling: a data-mining approach in SCT

Application of machine learning algorithms for clinical predictive modeling: a data-mining approach in SCT

Training neural network classifiers for medical decision making: The effects of imbalanced datasets on classification performance

Application of omic technologies in cancer research

Contact Info

Product

Resources

About