**6. Conclusions**

Artificial intelligence (AI) in healthcare offered a variety of healthcare information results that artificial intelligence (AI) has examined and reviewed the most important types of diseases that artificial intelligence (AI) has arranged. Machine learning (ML) and natural language processing are two major groups of artificial intelligence (AI) devices. For machine learning (ML) process, two most accepted traditional methods are available, that is, neural network and SVM. A typical artificial intelligence (AI) system must have the machine learning (ML) component that can help for conducting the structured data such as EP data, images, and genetic data and another natural language processing (NLP) module for the deduction of unstructured works. The complicated algorithm requires to be taught during the healthcare results previous to the system which can support the physicians for the disease analysis and plans which should be required for treatment. This technique focuses on how computer-oriented assessment methods, within the same roof as artificial intelligence (AI), can help in improving health and clinical area. Even though sophisticated information and machine learning present the base for artificial intelligence (AI), at present, there are revolutionary progresses happening in the subfield of neural networks. This has produced remarkable enthusiasm in several fields of healthcare science, as well as drug analysis and public health. Deep neural networks can execute as well as the most excellent human clinicians in definite diagnostic responsibilities. Additionally, artificial intelligence (AI) tools are already emerging in health-based apps, which can be engaged in handheld, network machines such as smart mobile phones. The major obstructions to be defeated in building health and healthcare data information are the space between digital

**133**

**Author details**

Sudipto Datta1

West Bengal, India

\*, Ranjit Barua1

provided the original work is properly cited.

and Jonali Das2

Science and Technology, Shibpur, Howrah, West Bengal, India

\*Address all correspondence to: dattadip440v@gmail.com

2 Department of Chemistry, Calcutta University, Uttarpara, Hooghly,

1 Centre for Healthcare Science and Technology, Indian Institute of Engineering

© 2019 The Author(s). Licensee IntechOpen. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/ by/3.0), which permits unrestricted use, distribution, and reproduction in any medium,

*Application of Artificial Intelligence in Modern Healthcare System*

data and human cognition. Data information regarding an entity patient is mostly gained in forms designed to be available to healthcare personnel. Typical data may consist of MRI or X-ray or ultrasound pictures of the patient, visual records of lung or heart function differing with time, or verbal similes of the patient as seen by the medical personnel. Alternatively, when data are accumulated in data information process and applied, in health research or to expand treatment procedures, it is regularly concentrated to statistical information that is mainly digital. The transfer of analog input into digital output is an oppressive task and may result in a defeat of important information, which would have been cooperative to the consumer.

*DOI: http://dx.doi.org/10.5772/intechopen.90454*

## *Application of Artificial Intelligence in Modern Healthcare System DOI: http://dx.doi.org/10.5772/intechopen.90454*

*Alginates - Recent Uses of This Natural Polymer*

frequently the calcium used to gel the alginate [69].

**6. Conclusions**

features, and composition [53]. It is feasible to rationally design the structure and composition of the biopolymer to gain suitable useful features [54]. The internal structure of the polymer molecule determines many functional characteristics, for example permeability, integrity, and chargeability [55]. The strength of the biopolymer particles and their summative capability is influenced by the electrical characteristics. Molecules of biopolymers and their electrical properties influence the contact with other molecules present in the neighboring environment. Alginate is one of the most popular natural biopolymers and intensely studied [56, 57]. It is an anionic biopolymer consisting of units of guluronic acid and mannuronic acid in uneven blocks [58]. Guluronic acid and mannuronic acid are linked by glycosidic linkages [59, 60], whereas the guluronic acid forms α bonds (1 → 4) and β (1 → 4) bonds with mannuronic acid [61]. The stiffness of molecular chains is ensured by the rigid and bent conformations of guluronic acid [62]. Hecth et al. have recently discussed their study on the characterization of calcium alginate and sodium alginate with particular importance on their structure [63]. Different applications and properties of alginate have also been examined. Alginate characteristics used biomedical especially in biomedicine can be formed by adjusting the accessibility of their hydroxyl and carboxyl groups [64]. It influences the characteristics of alginates, such as hydrophobicity, solubility, and their biological activity [65]. Alginate hydrogels were formed by cross-linking polymer chains [66]. The chemical properties of alginate hydrogels were found to depend on the cross-linking density of the chain [67]. The cellular viability of MG-63 osteosarcoma cells was improved by blending alginate bioink solution with N-acetyl cysteine (NAC) [68]. One of the techniques used in the design of alginate hydrogels is intermolecular cross-linking, wherein only the alginate guluronan groups react with the divalent cation, most

Artificial intelligence (AI) in healthcare offered a variety of healthcare information results that artificial intelligence (AI) has examined and reviewed the most important types of diseases that artificial intelligence (AI) has arranged. Machine learning (ML) and natural language processing are two major groups of artificial intelligence (AI) devices. For machine learning (ML) process, two most accepted traditional methods are available, that is, neural network and SVM. A typical artificial intelligence (AI) system must have the machine learning (ML) component that can help for conducting the structured data such as EP data, images, and genetic data and another natural language processing (NLP) module for the deduction of unstructured works. The complicated algorithm requires to be taught during the healthcare results previous to the system which can support the physicians for the disease analysis and plans which should be required for treatment. This technique focuses on how computer-oriented assessment methods, within the same roof as artificial intelligence (AI), can help in improving health and clinical area. Even though sophisticated information and machine learning present the base for artificial intelligence (AI), at present, there are revolutionary progresses happening in the subfield of neural networks. This has produced remarkable enthusiasm in several fields of healthcare science, as well as drug analysis and public health. Deep neural networks can execute as well as the most excellent human clinicians in definite diagnostic responsibilities. Additionally, artificial intelligence (AI) tools are already emerging in health-based apps, which can be engaged in handheld, network machines such as smart mobile phones. The major obstructions to be defeated in building health and healthcare data information are the space between digital

**132**

data and human cognition. Data information regarding an entity patient is mostly gained in forms designed to be available to healthcare personnel. Typical data may consist of MRI or X-ray or ultrasound pictures of the patient, visual records of lung or heart function differing with time, or verbal similes of the patient as seen by the medical personnel. Alternatively, when data are accumulated in data information process and applied, in health research or to expand treatment procedures, it is regularly concentrated to statistical information that is mainly digital. The transfer of analog input into digital output is an oppressive task and may result in a defeat of important information, which would have been cooperative to the consumer.
