Mathematical and Computational Intelligence for Healthcare

Mathematics is an essential mechanism in computational Intelligence for the problem solving mechanism with decision support system. Mathematical Intelligence can be depicted as the combination of Mathematical Reasoning and Computational reasoning. Computational Intelligence for Healthcare Application covers a range of methods that are intended to describe, improve, and support cross-domain research that is computationally intelligent in nature. It includes optimization techniques for mathematical methods, automated mathematical reasoning, Equational and probabilistic logics with Semantic reasoning, Interactive computational methods, Mathematical simulation theories, Auto-formalization artificial intelligence and so on. Computational Intelligence operates as an orientation for the pervasive healthcare field, which considers applications for emerging convergent computing as well as those that go beyond it. Insight and analysis from experts can be made available to a large audience at a low cost because to the technological revolution and medical innovations made possible by merging the massive amounts of existing information with cloud computing based facilities  and the results constructed over Artificial intelligence based mechanisms.

Computational intelligence (CI) methodologies that have lately come to light as promising tools for the creation and use of intelligent systems in healthcare are statistical methods, Fuzzy logic, Advance algorithms, Mathematical Simulation and  Neural networks (ANN, DNN, CNN) (Hybrid methods for Healthcare). As with artificial systems like artificial neural networks, AI systems, distributed and parallel computing systems, and evolutionary programmes, natural systems like the immune system, the nervous system, our society, and our ecology are characterised by obvious complex behaviour that is the result of non-direct spatial transient cooperation among a shifted number of segment frameworks at the association’s diverse dimension. By accounting for the uncertainty that characterises health data, such as omics data, clinical data, sensor, and imaging data, CI-based systems can learn from data and develop in response to changes in the surroundings. Diffusion tensor imaging (DTI), one of the most important tools for structural brain research in recent years, allows for the detection of changes associated with severe neurodegenerative diseases like Alzheimer’s disease (AD). Smart healthcare applications heavily rely on wearable technologies. The technique of physiological data detection and processing from wearable devices is crucial to smart HealthCare to reduce the extra latency caused by cloud computing, fog computing analyses physiological data. The overloading in a fog environment and the latency for emergency health statuses become major obstacles for smart healthcare.

For instance, a variety of tools and pipelines are available to manage large structured datasets for even regulation and investigations such as bivariate mechanism, which is a complicated process requiring the analysis of gene expression data. Innovative deep learning algorithms and conventional statistical bioinformatic pipelines are both inappropriate for extracting meaningful data and evidence from such datasets. It is possible to choose a small subset of genes that can distinguish between the six different types of samples and to define an understandable set of rules that domain experts can use to further investigate the chosen genes, their participation in cancer, and the potential use of them as early biomarkers for the diagnosis of ovarian cancer.

Another instance, a comprehensive picture of the pathological condition is the diverse wealth of biological data supplied by many diagnostic modalities can be used in the pre-clinical stage to identify dementia foundations in pre-symptomatic illnesses.

Bibliography:

Consiglio A, Casalino G, Castellano G, Grillo G, Perlino E, Vessio G, Licciulli F. Explaining Ovarian Cancer Gene Expression Profiles with Fuzzy Rules and Genetic Algorithms. Electronics. 2021; 10(4):375. https://doi.org/10.3390/electronics10040375.

Casalino, G.; Castellano, G. Special Issue on Computational Intelligence for Healthcare. Electronics 2021, 10, 1841. https://doi.org/ 10.3390/electronics1015184

Lella, E.; Pazienza, A.; Lofù, D.; Anglani, R.; Vitulano, F. An Ensemble Learning Approach Based on Diffusion Tensor Imaging Measures for Alzheimer’s Disease Classification. Electronics 2021, 10, 249. https://doi.org/10.3390/electronics10030249.

Ijaz M, Li G, Wang H, El-Sherbeeny AM, Moro Awelisah Y, Lin L, Koubaa A, Noor A. Intelligent Fog-Enabled Smart Healthcare System for Wearable Physiological Parameter Detection. Electronics. 2020; 9(12):2015. https://doi.org/10.3390/electronics9122015.

Sharma, M., Agrawal, S., & Deswal, S. (2020). Application of hybrid computational intelligence in health care. In Hybrid Computational Intelligence (pp. 123-148). Academic Press.