Condensed matter physics (CMP) seeks to understand the microscopic interactions of matter at the quantum and atomistic levels, and describes how these interactions result in both mesoscopic and macroscopic properties. CMP overlaps with many other important branches of science, such as chemistry, materials science, statistical physics, and high-performance computing. With the advancements in modern machine learning (ML) technology, a keen interest in applying these algorithms to further CMP research has created a compelling new area of research at the intersection of both fields. In this review, we aim to explore the main areas within CMP, which have successfully applied ML techniques to further research, such as the description and use of ML schemes for potential energy surfaces, the characterization of topological phases of matter in lattice systems, the prediction of phase transitions in off-lattice and atomistic simulations, the interpretation of ML theories with physics-inspired frameworks and the enhancement of simulation methods with ML algorithms. We also discuss in detail the main challenges and drawbacks of using ML methods on CMP problems, as well as some perspectives for future developments.
Hypomyelination with atrophy of the basal ganglia and cerebellum (H‐ABC) is a neurodegenerative disease due to mutations in TUBB4A. Patients suffer from extrapyramidal movements, spasticity, ataxia, and cognitive deficits. Magnetic resonance imaging features are hypomyelination and atrophy of the striatum and cerebellum. A correlation between the mutations and their cellular, tissue and organic effects is largely missing. The effects of these mutations on sensory functions have not been described so far. We have previously reported a rat carrying a TUBB4A (A302T) mutation and sharing most of the clinical and radiological signs with H‐ABC patients. Here, for the first time, we did a comparative study of the hearing function in an H‐ABC patient and in this mutant model. By analyzing hearing function, we found that there are no significant differences in the auditory brainstem response (ABR) thresholds between mutant rats and WT controls. Nevertheless, ABRs show longer latencies in central waves (II–IV) that in some cases disappear when compared to WT. The patient also shows abnormal AEPs presenting only Waves I and II. Distortion product of otoacoustic emissions and immunohistochemistry in the rat show that the peripheral hearing function and morphology of the organ of Corti are normal. We conclude that the tubulin mutation severely impairs the central hearing pathway most probably by progressive central white matter degeneration. Hearing function might be affected in a significant fraction of patients with H‐ABC; therefore, screening for auditory function should be done on patients with tubulinopathies to evaluate hearing support therapies.
Computational approaches have been used for analyzing risk factors together with conventional mammograms for breast cancer detection. Currently, other screening methods like electro-impedance mammography are available. Notwithstanding, as far as we know there is not related work evaluating the role of electrical-conductivity index of the mammary gland as a quantitative factor for early detection of breast cancer. This paper aims to demonstrate the importance of including breast conductivity index as a quantitative local risk-factor by analyzing a dataset of Mexican patients from a machine learning perspective. There are 12 attributes distributed into two groups: electrical-conductivity (3) and medical records (9). According to the obtained results with unsupervised methods, the performance in terms of accuracy of using only electrical-conductivity (43%) is better than using all available features (38%) and the medical records (33%). On the other hand, we identified that SVM achieves higher results in comparison with other algorithms when only the electrical-features are used. The obtained results demonstrate the important role of conductivity index as a quantitative local risk-factor for being considered in screening processes. Besides, it emerges as an important aspect to be included in the development of automatic tools for experts to perform breast cancer diagnosis.INDEX TERMS Electro-impedance, conductivity, machine learning, mammography MEIK, risk factor.
Biomedical classification problems are of great interest to both medical practitioners and computer scientists. Due to the harmful consequences of a wrong decision in this ambit, computational methods must be carefully designed to provide a reliable tool for helping physicians to obtain accurate predictions on unseen cases. Computational Intelligence (CI) provides robust models to perform optimization, classification and regression tasks. These models have been previously designed, mainly based on the expertise of computer scientists, to solve a vast number of biomedical problems. As the number of both CI algorithms and biomedical problems continues to grow, selecting the right method to solve a given problem becomes more challenging. To deal with this complexity, a systematic methodology for selecting a suitable model for a given classification problem is required. In this work, we review the more promising classification and optimization algorithms and reformulate them into a synergic framework to automatically design and optimize pattern classifiers. Our proposal, including state-of-the-art evolutionary algorithms and support vector machines, is tested on a variety of biomedical problems. Experimental results on benchmark datasets allow us to conclude that the automatically designed classifiers reach higher or equal performance than those designed by computer specialists.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.