Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support…

By João Maroco, Dina Silva, Ana Rodrigues, Manuela Guerreiro, Isabel Santana, A. de Mendonça. BMC Research Notes, 2011

402 citations recorded by the source corpus.

BackgroundDementia and cognitive impairment associated with aging are a major medical and social concern. Neuropsychological testing is a key element in the diagnostic procedures of Mild Cognitive Impairment (MCI), but has presently a limited value in the prediction of progression to dementia. We advance the hypothesis that newer statistical classification methods derived from data mining and machine learning methods like Neural Networks, Support Vector Machines and Random Forests can improve accuracy, sensitivity and specificity of predictions obtained from neuropsychological testing. Seven non parametric classifiers derived from data mining methods (Multilayer Perceptrons Neural Networks, Radial Basis Function Neural Networks, Support Vector Machines, CART, CHAID and QUEST Classification Trees and Random Forests) were compared to three traditional classifiers (Linear Discriminant Analysis, Quadratic Discriminant Analysis and Logistic Regression) in terms of overall classification accuracy, specificity, sensitivity, Area under the ROC curve and Press'Q. Model predictors were 10 neuropsychological tests currently used in the diagnosis of dementia. Statistical distributions of classification parameters obtained from a 5-fold cross-validation were compared using the Friedman's nonparametric test.ResultsPress' Q test showed that all classifiers performed better than chance alone (p < 0.05). Support Vector Machines showed the larger overall classification accuracy (Median (Me) = 0.76) an area under the ROC (Me = 0.90). However this method showed high specificity (Me = 1.0) but low sensitivity (Me = 0.3). Random Forest ranked second in overall accuracy (Me = 0.73) with high area under the ROC (Me = 0.73) specificity (Me = 0.73) and sensitivity (Me = 0.64). Linear Discriminant Analysis also showed acceptable overall accuracy (Me = 0.66), with acceptable area under the ROC (Me = 0.72) specificity (Me = 0.66) and sensitivity (Me = 0.64). The remaining classifiers showed overall classification accuracy above a median value of 0.63, but for most sensitivity was around or even lower than a median value of 0.5.ConclusionsWhen taking into account sensitivity, specificity and overall classification accuracy Random Forests and Linear Discriminant analysis rank first among all the classifiers tested in prediction of dementia using several neuropsychological tests. These methods may be used to improve accuracy, sensitivity and specificity of Dementia predictions from neuropsychological testing.

Subfields: Health Information Management, Molecular Biology, Psychiatry and Mental health

View Paper: https://www.semanticscholar.org/paper/7247fb551a812e616945f544b07916f1b4fc8497

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Health Information Management

1. Alfredo Vellido
2. Peter C. Austin

In Molecular Biology

1. Quentin J. M. Huys
2. Alfredo Vellido
3. Tiago V. Maia
4. Michael J Frank

In Psychiatry and Mental health

1. Tiago V. Maia
2. Peter C. Austin
3. Michael J Frank

Citations in the corpus

• Computational psychiatry as a bridge from neuroscience to clinical applications (2016, methodology): “This approach is inherent in support vector machines, LASSO, elastic nets, stochastic discrimination approaches such as random forests 146 and other variable-selection methods in multiple regression.”
• Machine learning in critical care: state-of-the-art and a sepsis case study (2018, background): “These fields include bioinformatics [9, 10], genetics and genomics [11, 12], clinical applications [13], medical decision support and clinical diagnosis [14, 15], oncology [16, 17], psychiatry and neurological disorders [18, 19], or cytopathology [20].”
• Multiple Random Forests Modelling for Urban Water Consumption Forecasting (2017, methodology): “Odan and Reis (2012) adopted an ANN in combination with Fourier series to address the problem of water consumption prediction for the real time operation of water distribution systems.”
• Using methods from the data mining and machine learning literature for disease classification and prediction: A case study examining classification of heart failure sub-types (2013, background): “[35] compared 10 different classifiers for predicting the evolution of mild cognitive impairment with dementia.”