Automatic migraine classification via feature selection committee and machine learning techniques over imaging and questionnaire data.

BACKGROUND: Feature selection methods are commonly used to identify subsets of relevant features to facilitate the construction of models for classification, yet little is known about how feature selection methods perform in diffusion tensor images (DTIs). In this study, feature selection and machine learning classification methods were tested for the purpose of automating diagnosis of migraines using both DTIs and questionnaire answers related to emotion and cognition - factors that influence of pain perceptions. METHODS: We select 52 adult subjects for the study divided into three groups: control group (15), subjects with sporadic migraine (19) and subjects with chronic migraine and medication overuse (18). These subjects underwent magnetic resonance with diffusion tensor to see white matter pathway integrity of the regions of interest involved in pain and emotion. The tests also gather data about pathology. The DTI images and test results were then introduced into feature selection algorithms (Gradient Tree Boosting, L1-based, Random Forest and Univariate) to reduce features of the first dataset and classification algorithms (SVM (Support Vector Machine), Boosting (Adaboost) and Naive Bayes) to perform a classification of migraine group. Moreover we implement a committee method to improve the classification accuracy based on feature selection algorithms. RESULTS: When classifying the migraine group, the greatest improvements in accuracy were made using the proposed committee-based feature selection method. Using this approach, the accuracy of classification into three types improved from 67 to 93% when using the Naive Bayes classifier, from 90 to 95% with the support vector machine classifier, 93 to 94% in boosting. The features that were determined to be most useful for classification included are related with the pain, analgesics and left uncinate brain (connected with the pain and emotions). CONCLUSIONS: The proposed feature selection committee method improved the performance of migraine diagnosis classifiers compared to individual feature selection methods, producing a robust system that achieved over 90% accuracy in all classifiers. The results suggest that the proposed methods can be used to support specialists in the classification of migraines in patients undergoing magnetic resonance imaging.

HClass: Automatic classification tool for health pathologies using artificial intelligence techniques.

The classification of subjects' pathologies enables a rigorousness to be applied to the treatment of certain pathologies, as doctors on occasions play with so many variables that they can end up confusing some illnesses with others. Thanks to Machine Learning techniques applied to a health-record database, it is possible to make using our algorithm. hClass contains a non-linear classification of either a supervised, non-supervised or semi-supervised type. The machine is configured using other techniques such as validation of the set to be classified (cross-validation), reduction in features (PCA) and committees for assessing the various classifiers. The tool is easy to use, and the sample matrix and features that one wishes to classify, the number of iterations and the subjects who are going to be used to train the machine all need to be introduced as inputs. As a result, the success rate is shown either via a classifier or via a committee if one has been formed. A 90% success rate is obtained in the ADABoost classifier and 89.7% in the case of a committee (comprising three classifiers) when PCA is applied. This tool can be expanded to allow the user to totally characterise the classifiers by adjusting them to each classification use.

Game design to measure reflexes and attention based on biofeedback multi-sensor interaction.

This paper presents a multi-sensor system for implementing biofeedback as a human-computer interaction technique in a game involving driving cars in risky situations. The sensors used are: Eye Tracker, Kinect, pulsometer, respirometer, electromiography (EMG) and galvanic skin resistance (GSR). An algorithm has been designed which gives rise to an interaction logic with the game according to the set of physiological constants obtained from the sensors. The results reflect a 72.333 response to the System Usability Scale (SUS), a significant difference of p = 0.026 in GSR values in terms of the difference between the start and end of the game, and an r = 0.659 and p = 0.008 correlation while playing with the Kinect between the breathing level and the energy and joy factor. All the sensors used had an impact on the end results, whereby none of them should be disregarded in future lines of research, even though it would be interesting to obtain separate breathing values from that of the cardio.

Graph theory for feature extraction and classification: a migraine pathology case study.

Graph theory is also widely used as a representational form and characterization of brain connectivity network, as is machine learning for classifying groups depending on the features extracted from images. Many of these studies use different techniques, such as preprocessing, correlations, features or algorithms. This paper proposes an automatic tool to perform a standard process using images of the Magnetic Resonance Imaging (MRI) machine. The process includes pre-processing, building the graph per subject with different correlations, atlas, relevant feature extraction according to the literature, and finally providing a set of machine learning algorithms which can produce analyzable results for physicians or specialists. In order to verify the process, a set of images from prescription drug abusers and patients with migraine have been used. In this way, the proper functioning of the tool has been proved, providing results of 87% and 92% of success depending on the classifier used.

Automatic classification of dyslexic children by applying machine learning to fMRI images.

Functional Magnetic Resonance Imaging (fMRI) and Diffusion Tensor Imaging (DTI) are a source of information to study different pathologies. This tool allows to classify subjects under study, analysing in this case, the functions related to language in young patients with dyslexia. Images are obtained using a scanner and different tests are performed on subjects. After processing the images, the areas that are activated by patients when performing the paradigms or anatomy of the tracts were obtained. The main objective is to ultimately introduce a group of monocular vision subjects, whose brain activation model is unknown. This classification helps to assess whether these subjects are more akin to dyslexic or control subjects. Machine learning techniques study systems that learn how to perform non-linear classifications through supervised or unsupervised training, or a combination of both. Once the machine has been set up, it is validated with the subjects who have not been entered in the training stage. The results are obtained using a user-friendly chart. Finally, a new tool for the classification of subjects with dyslexia and monocular vision was obtained (achieving a success rate of 94.8718% on the Neuronal Network classifier), which can be extended to other further classifications.