Optimizing the setting of medical interactive rehabilitation assistant platform to improve the performance of the patients: A case study.

Tele-rehabilitation is an alternative to the conventional rehabilitation service that helps patients in remote areas to access a service that is practical in terms of logistics and cost, in a controlled environment. It includes the usage of mobile phones or other wireless devices that are applied to rehabilitation exercises. Such applications or software include exercises in the form of virtual games, treatment monitoring based on the rehabilitation progress and data analysis. However, nowadays, physiotherapists use a default profiling setting for patients carrying out rehabilitation, due to lack of information. Medical Interactive Rehabilitation Assistant (MIRA) is a computer-based (virtual reality) rehabilitation platform. The profile setting includes: a level of difficulty, percentage of tolerance and maximum range. To the best of our knowledge, there is a lack of optimization in the parameter values setting of MIRA exergames that could enhance patients' performance. Generally, non-optimal profile setting leads to reduced effectiveness. Therefore, this study aims to develop a method that optimizes the profile setting of each patient according to the estimated (desired) optimal results. The proposed method is developed using unsupervised and supervised machine learning techniques. We use Self-Organizing Map (SOM) to cluster patient records into several distinct clusters. K-fold cross validation is applied to construct the prediction models. Classification And Regression Tree (CART) is utilized to predict the patient's optimal input setting for playing the MIRA games. The combination of these techniques seems to improve the efficiency of the standard (default) way in predicting the optimal settings for exergames. To evaluate the proposed method, we conduct an experiment with data collected from a rehabilitation center. We use three metrics to quantify the quality of the results: R-squared (R2), Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The results of experimental analysis demonstrate that the proposed method is effective in predicting the adequate parameter setting in MIRA platform. The method has potential to be implemented as an intelligent system for MIRA prediction in healthcare. Moreover, the method could be extended to similar platforms for which data is available to train our method on.

Improving patient rehabilitation performance in exercise games using collaborative filtering approach.

BACKGROUND: Virtual reality is utilised in exergames to help patients with disabilities improve on the movement of their limbs. Exergame settings, such as the game difficulty, play important roles in the rehabilitation outcome. Similarly, suboptimal exergames' settings may adversely affect the accuracy of the results obtained. As such, the improvement in patients' movement performances falls below the desired expectations. In this paper, a recommender system is incorporated to suggest the most preferred movement setting for each patient, based on the movement history of the patient. METHOD: The proposed recommender system (ResComS) suggests the most suitable setting necessary to optimally improve patients' rehabilitation performances. In the course of developing the recommender system, three methods are proposed and compared: ReComS (K-nearest neighbours and collaborative filtering algorithms), ReComS+ (k-means, K-nearest neighbours, and collaborative filtering algorithms) and ReComS++ (bacterial foraging optimisation, k-means, K-nearest neighbours, and collaborative filtering algorithms). The experimental datasets are collected using the Medical Interactive Recovery Assistant (MIRA) software platform. RESULT: Experimental results, validated by the patients' exergame performances, reveal that the ReComS++ approach predicts the best exergame settings for patients with 85.76% accuracy.

Multi-task learning with a natural metric for quantitative structure activity relationship learning.

The goal of quantitative structure activity relationship (QSAR) learning is to learn a function that, given the structure of a small molecule (a potential drug), outputs the predicted activity of the compound. We employed multi-task learning (MTL) to exploit commonalities in drug targets and assays. We used datasets containing curated records about the activity of specific compounds on drug targets provided by ChEMBL. Totally, 1091 assays have been analysed. As a baseline, a single task learning approach that trains random forest to predict drug activity for each drug target individually was considered. We then carried out feature-based and instance-based MTL to predict drug activities. We introduced a natural metric of evolutionary distance between drug targets as a measure of tasks relatedness. Instance-based MTL significantly outperformed both, feature-based MTL and the base learner, on 741 drug targets out of 1091. Feature-based MTL won on 179 occasions and the base learner performed best on 171 drug targets. We conclude that MTL QSAR is improved by incorporating the evolutionary distance between targets. These results indicate that QSAR learning can be performed effectively, even if little data is available for specific drug targets, by leveraging what is known about similar drug targets.

Experienced Gray Wolf Optimization Through Reinforcement Learning and Neural Networks.

In this paper, a variant of gray wolf optimization (GWO) that uses reinforcement learning principles combined with neural networks to enhance the performance is proposed. The aim is to overcome, by reinforced learning, the common challenge of setting the right parameters for the algorithm. In GWO, a single parameter is used to control the exploration/exploitation rate, which influences the performance of the algorithm. Rather than using a global way to change this parameter for all the agents, we use reinforcement learning to set it on an individual basis. The adaptation of the exploration rate for each agent depends on the agent's own experience and the current terrain of the search space. In order to achieve this, experience repository is built based on the neural network to map a set of agents' states to a set of corresponding actions that specifically influence the exploration rate. The experience repository is updated by all the search agents to reflect experience and to enhance the future actions continuously. The resulted algorithm is called experienced GWO (EGWO) and its performance is assessed on solving feature selection problems and on finding optimal weights for neural networks algorithm. We use a set of performance indicators to evaluate the efficiency of the method. Results over various data sets demonstrate an advance of the EGWO over the original GWO and over other metaheuristics, such as genetic algorithms and particle swarm optimization.

Meta-QSAR: a large-scale application of meta-learning to drug design and discovery.

We investigate the learning of quantitative structure activity relationships (QSARs) as a case-study of meta-learning. This application area is of the highest societal importance, as it is a key step in the development of new medicines. The standard QSAR learning problem is: given a target (usually a protein) and a set of chemical compounds (small molecules) with associated bioactivities (e.g. inhibition of the target), learn a predictive mapping from molecular representation to activity. Although almost every type of machine learning method has been applied to QSAR learning there is no agreed single best way of learning QSARs, and therefore the problem area is well-suited to meta-learning. We first carried out the most comprehensive ever comparison of machine learning methods for QSAR learning: 18 regression methods, 3 molecular representations, applied to more than 2700 QSAR problems. (These results have been made publicly available on OpenML and represent a valuable resource for testing novel meta-learning methods.) We then investigated the utility of algorithm selection for QSAR problems. We found that this meta-learning approach outperformed the best individual QSAR learning method (random forests using a molecular fingerprint representation) by up to 13%, on average. We conclude that meta-learning outperforms base-learning methods for QSAR learning, and as this investigation is one of the most extensive ever comparisons of base and meta-learning methods ever made, it provides evidence for the general effectiveness of meta-learning over base-learning.

Computational Intelligence Modeling of the Macromolecules Release from PLGA Microspheres-Focus on Feature Selection.

Poly-lactide-co-glycolide (PLGA) is a copolymer of lactic and glycolic acid. Drug release from PLGA microspheres depends not only on polymer properties but also on drug type, particle size, morphology of microspheres, release conditions, etc. Selecting a subset of relevant properties for PLGA is a challenging machine learning task as there are over three hundred features to consider. In this work, we formulate the selection of critical attributes for PLGA as a multiobjective optimization problem with the aim of minimizing the error of predicting the dissolution profile while reducing the number of attributes selected. Four bio-inspired optimization algorithms: antlion optimization, binary version of antlion optimization, grey wolf optimization, and social spider optimization are used to select the optimal feature set for predicting the dissolution profile of PLGA. Besides these, LASSO algorithm is also used for comparisons. Selection of crucial variables is performed under the assumption that both predictability and model simplicity are of equal importance to the final result. During the feature selection process, a set of input variables is employed to find minimum generalization error across different predictive models and their settings/architectures. The methodology is evaluated using predictive modeling for which various tools are chosen, such as Cubist, random forests, artificial neural networks (monotonic MLP, deep learning MLP), multivariate adaptive regression splines, classification and regression tree, and hybrid systems of fuzzy logic and evolutionary computations (fugeR). The experimental results are compared with the results reported by Szlȩk. We obtain a normalized root mean square error (NRMSE) of 15.97% versus 15.4%, and the number of selected input features is smaller, nine versus eleven.

Feature Selection via Chaotic Antlion Optimization.

BACKGROUND: Selecting a subset of relevant properties from a large set of features that describe a dataset is a challenging machine learning task. In biology, for instance, the advances in the available technologies enable the generation of a very large number of biomarkers that describe the data. Choosing the more informative markers along with performing a high-accuracy classification over the data can be a daunting task, particularly if the data are high dimensional. An often adopted approach is to formulate the feature selection problem as a biobjective optimization problem, with the aim of maximizing the performance of the data analysis model (the quality of the data training fitting) while minimizing the number of features used. RESULTS: We propose an optimization approach for the feature selection problem that considers a "chaotic" version of the antlion optimizer method, a nature-inspired algorithm that mimics the hunting mechanism of antlions in nature. The balance between exploration of the search space and exploitation of the best solutions is a challenge in multi-objective optimization. The exploration/exploitation rate is controlled by the parameter I that limits the random walk range of the ants/prey. This variable is increased iteratively in a quasi-linear manner to decrease the exploration rate as the optimization progresses. The quasi-linear decrease in the variable I may lead to immature convergence in some cases and trapping in local minima in other cases. The chaotic system proposed here attempts to improve the tradeoff between exploration and exploitation. The methodology is evaluated using different chaotic maps on a number of feature selection datasets. To ensure generality, we used ten biological datasets, but we also used other types of data from various sources. The results are compared with the particle swarm optimizer and with genetic algorithm variants for feature selection using a set of quality metrics.

Heterochromatinization induced by GAA-repeat hyperexpansion in Friedreich's ataxia can be reduced upon HDAC inhibition by vitamin B3.

Large intronic expansions of the triplet-repeat sequence (GAA.TTC) cause transcriptional repression of the Frataxin gene (FXN) leading to Friedreich's ataxia (FRDA). We previously found that GAA-triplet expansions stimulate heterochromatinization in vivo in transgenic mice. We report here using chromosome conformation capture (3C) coupled with high-throughput sequencing that the GAA-repeat expansion in FRDA cells stimulates a higher-order structure as a fragment containing the GAA-repeat expansion showed an increased interaction frequency with genomic regions along the FXN locus. This is consistent with a more compacted chromatin and coincided with an increase in both constitutive H3K9me3 and facultative H3K27me3 heterochromatic marks in FRDA. Consistent with this, DNase I accessibility in regions flanking the GAA repeats in patients was decreased compared with healthy controls. Strikingly, this effect could be antagonized with the class III histone deactylase (HDAC) inhibitor vitamin B3 (nicotinamide) which activated the silenced FXN gene in several FRDA models. Examination of the FXN locus revealed a reduction of H3K9me3 and H3K27me3, an increased accessibility to DNase I and an induction of euchromatic H3 and H4 histone acetylations upon nicotinamide treatment. In addition, transcriptomic analysis of nicotinamide treated and untreated FRDA primary lymphocytes revealed that the expression of 67% of genes known to be dysregulated in FRDA was ameliorated by the treatment. These findings show that nictotinamide can up-regulate the FXN gene and reveal a potential mechanism of action for nicotinamide in reactivating the epigenetically silenced FXN gene and therefore support the further assessment of HDAC inhibitors (HDACi's) in FRDA and diseases caused by a similar mechanism.