Computational Intelligence for Machine Learning and Healthcare Informatics

Rajshree Srivastava, Pradeep Kumar Mallick, Siddharth Swarup Rautaray, Manjusha Pandey, Rajshree Srivastava, Pradeep Kumar Mallick, Siddharth Swarup Rautaray, Manjusha Pandey

• Editore: De Gruyter
• Anno: 2020
• ISBN:
  9783110649277
• Edizione: 1
• Argomento: Informatik
• Categoria: Künstliche Intelligenz (KI) & Semantik

This book presents a variety of techniques designed to enhance and empower multi-disciplinary and multi-institutional machine learning research in healthcare informatics. It is intended to provide a unique compendium of current and emerging machine learning paradigms for healthcare informatics, reflecting the diversity, complexity, and depth and breadth of this multi-disciplinary area.

1 A review of bone tissue engineering for the application of artificial intelligence in cellular adhesion prediction

María de Lourdes Sánchez

Advanced Informatics Technology Research Group (GITIA), National Technological University, Tucumán Regional Faculty, San Miguel de Tucumán, Argentina

Adrián Will

Advanced Informatics Technology Research Group (GITIA), National Technological University, Tucumán Regional Faculty, San Miguel de Tucumán, Argentina

Andrea Paola Rodríguez

Laboratorio Advanced Informatics Technology Research Group (GITIA), National Technological University, Tucumán Regional Faculty, San Miguel de Tucumán, Argentina

Luis Octavio Gónzalez-Salcedo

Grupo Materials Catalysis and Environmental Research Group, Faculty of Engineering and Administration, National University of Colombia – Palmira Headquarters, Palmira, Colombia

Abstract

Artificial intelligence (AI) is changing, at a fast pace, all aspects of science, technology, and society in general, giving rise to what is known as the 4th Industrial Revolution. In this chapter, we review the literature regarding AI applications to bone tissue engineering, and more particularly, to cell adhesion in bone scaffolds. The works found are very few (only six works), and we classify them according to the AI technique used. The question we want to address in this chapter is what AI techniques were used and what exactly have they been used for.

The chapter shows that the most used AI tools were the artificial neural network, in their different types, followed by cellular automata and multiagent systems. The intended use varies, but it is mainly related to understanding the variables involved and adjusting a model that provides insight and allows for a better and more informed design process of the scaffold.

Keywords: bone tissue engineering, artificial intelligence, stem cells, scaffolds, cell adhesion,

1.1 Introduction

Regenerative medicine is a multidisciplinary specialty, which seeks the maintenance, improvement, or restoration of the function of cells, tissues, and organs. It is based on four pillars: cell therapy, organ transplantation, biomedical engineering, and, finally, tissue engineering (Rodríguez et al., 2013).

Bone tissue engineering (BTE) is a constitutive part of regenerative medicine. Its main objective is to repair both the shape and function of the damaged bone. The size of bone deficiency constitutes a critical factor because it does not spontaneously regenerate, since it requires surgical intervention. In this regard, at present, many people are affected precisely by bone or joint problems. In third age people, these effects represent almost 50% of chronic diseases that can develop, causing pain and physical disability and, in some cases, requiring surgery, bone grafts, or implants (Moreno et al., 2016).

In addition, one of the problems of regenerative medicine is that many organ transplants are required, but their donors are very few. This leads to an important cooperation with tissue engineering, resulting in a promising strategy for bone reconstruction and in the development as possible solutions of bioengineering structures for this purpose (Roseti et al.,2017).

According to Moreno et al. (2016) and Roseti et al. (2017), blood is the most transplanted, followed by bone transplantation. Although the success of the therapeutic solutions described and used for more than a decade is in the clinical environment, some inconveniences can take place because infections can occur after placing the implant in the body (Gaviria Arias et al., 2018).

Tissue engineering plays a major role in overcoming these limitations, becoming a favorable area to repair bone lesions using porous three-dimensional matrices seeded with growth factors and mesenchymal stem cells (MSC). These matrices are built using different technologies and are known as scaffolds. Once constructed and implanted, the MSCs or other types of cells (i.e., pre-osteoblasts) are seeded on the surface of the scaffold and the natural process of human tissue regeneration is stimulated and helped by the growth factor, in order to produce new bone (Moreno et al., 2016; Suárez Vega et al., 2017).

Tissue engineering takes advantage of the natural ability of the body to regenerate using engineering and biology to replace or repair damaged tissues (Moreno et al., 2016; Granados et al., 2017).

Therefore, we can say that tissue engineering dramatically increases the capabilities of regenerative medicine. Furthermore, if tissue engineering is combined with cell therapy, the capabilities are even higher. For example, embryonic therapeutic cells or living stem cells can be used alone or in association with scaffolds of biomaterials (Moreno et al., 2016). In this regard, Roseti et al. (2017) mention that, alternatively, different types of cells can be used or combined with scaffolds in vivo, promoting the osteogenic differentiation or releasing the necessary soluble molecules.

To achieve bone regeneration knowledge of cells, three-dimensional scaffolds, and growth factors or signaling molecules are required (Gordeladze et al., 2017). This leads to a series of important questions: (1) type of cells, biological products, biomaterials, and internal microarchitecture of the scaffold to be used; (2) selection of optimal physiological and therapeutic doses; (3) temporal and/or spatial distribution of the mentioned criteria for tissue reconstruction; (4) its dynamics and its kinetics; (5) application related to the visualization of customized and performance-related design specifications; and (6) manipulation of the pathways involved in the requirement of sophisticated tissue engineering therapies (Gordeladze et al., 2017). Answering these questions will lead us to the unequivocal identification of the fundamental factors that are considered necessary to complete the successful regeneration of the tissue. In addition, for a better understanding of the interaction of cells, scaffolds, and growth factors, the possibility of having bioinformatics systems is extremely important because these systems can study what happens with the different variables and thus can propose a simulation and/or prediction model, as mentioned in Gordeladze et al. (2017).

These concerns have been raised for years ago (Estrada et al., 2006). Then, the need of sophisticated experimental tools for analysis is defined, as well as the inclusion of more realistic in vitro models and better forms of acquisition and noninvasive images in vivo, which leads to the development of computational models that are capable of processing a large amount of information.

In this regard, Narváez Tovar et al. (2011) review the different computational models of bone differentiation and adaptation, disregarding how the models have increased in complexity when moving from two-dimensional to three-dimensional representations and have included new factors or variables as developed experimental research and have gone from mechanistic considerations to models that consider biological aspects of the bone adaptation process. However, for the same authors, the mathematical relationships that support these models only represent a small part of all the mechanisms involved in the problem.

Scaffolds must be biomimetic and functional. That is, their internal microarchitecture must mimic the natural microenvironment to which cells are accustomed to achieve the necessary cellular responses in order to form the new tissue. Although there are several methodologies for scaffolding manufacturing, many of these methods produce deficient scaffolds, which fail to promote three-dimensional healing and in the formation of a blood vessel network within the scaffold, as expressed by (Eltom et al., 2019). This leads to the need to predict the result of cell adhesion in the rehabilitation process, which requires the provision of computational tools for this purpose.

However, the different factors to consider in the modeling process create a complexity that is generally resolved in the field of artificial intelligence (AI). AI corresponds to the mathematical and computational technique to generate capacity in artifacts to exhibit intelligent behavior, the main areas being artificial neural networks (ANN), evolutionary programming, fuzzy logic, data mining, machine learning, expert systems, artificial life, and swarm intelligence, among others. However, the different factors to consider in the modeling process create a complexity that is generally better solved in the field of AI. Various applications have been used since AI in regenerative medicine and tissue engineering, as expressed by Biswal et al. (2013). However, most of them have focused on other types of scaffolds (Ramírez López et al., 2019).

We present in this chapter, a review focused on applications of AI to BTE. We will restrict ourselves to works from the last 10 years, focused on bone sca...

Indice dei contenuti

• Title Page
• Copyright
• Contents
• Preface
• 1 A review of bone tissue engineering for the application of artificial intelligence in cellular adhesion prediction
• 2 Implementation and classification of machine learning algorithms in healthcare informatics: approaches, challenges, and future scope
• 3 Cardiac arrhythmia recognition using Stockwell transform and ABC-optimized twin SVM
• 4 Computational intelligence approach to address the language barrier in healthcare
• 5 Recent advancement of machine learning and deep learning in the field of healthcare system
• 6 Predicting psychological disorders using machine learning
• 7 Automatic analysis of cardiovascular diseases using EMD and support vector machines
• 8 Machine learning approach for exploring computational intelligence
• 9 Classification of various image fusion algorithms and their performance evaluation metrics
• 10 Recommender system in healthcare: an overview
• 11 Dense CNN approach for medical diagnosis
• 12 Impact of sentiment analysis tools to improve patients’ life in critical diseases
• 13 A fuzzy entropy-based multilevel image thresholding using neural network optimization algorithm
• 14 Machine learning in healthcare
• 15 Computational health informatics using evolutionary-based feature selection
• Index